diff --git "a/data/dataset_card/dataset_cards_ko.csv" "b/data/dataset_card/dataset_cards_ko.csv" new file mode 100644--- /dev/null +++ "b/data/dataset_card/dataset_cards_ko.csv" @@ -0,0 +1,45959 @@ +dataset_id,yaml_metadata,markdown_content +allenai/c4,"{""pretty_name"": ""C4"", ""annotations_creators"": [""no-annotation""], ""language_creators"": [""found""], ""language"": [""af"", ""am"", ""ar"", ""az"", ""be"", ""bg"", ""bn"", ""ca"", ""ceb"", ""co"", ""cs"", ""cy"", ""da"", ""de"", ""el"", ""en"", ""eo"", ""es"", ""et"", ""eu"", ""fa"", ""fi"", ""fil"", ""fr"", ""fy"", ""ga"", ""gd"", ""gl"", ""gu"", ""ha"", ""haw"", ""he"", ""hi"", ""hmn"", ""ht"", ""hu"", ""hy"", ""id"", ""ig"", ""is"", ""it"", ""iw"", ""ja"", ""jv"", ""ka"", ""kk"", ""km"", ""kn"", ""ko"", ""ku"", ""ky"", ""la"", ""lb"", ""lo"", ""lt"", ""lv"", ""mg"", ""mi"", ""mk"", ""ml"", ""mn"", ""mr"", ""ms"", ""mt"", ""my"", ""ne"", ""nl"", ""no"", ""ny"", ""pa"", ""pl"", ""ps"", ""pt"", ""ro"", ""ru"", ""sd"", ""si"", ""sk"", ""sl"", ""sm"", ""sn"", ""so"", ""sq"", ""sr"", ""st"", ""su"", ""sv"", ""sw"", ""ta"", ""te"", ""tg"", ""th"", ""tr"", ""uk"", ""und"", ""ur"", ""uz"", ""vi"", ""xh"", ""yi"", ""yo"", ""zh"", ""zu""], ""language_bcp47"": [""bg-Latn"", ""el-Latn"", ""hi-Latn"", ""ja-Latn"", ""ru-Latn"", ""zh-Latn""], ""license"": [""odc-by""], ""multilinguality"": [""multilingual""], ""size_categories"": [""n<1K"", ""1K: `` + +### Data Splits + +For each configuration subset, the data is split into ""train"", ""validation"" and ""test"" sets, each containing the +following number of examples: + +| | Train | Validation | Test | +|:-------------|--------:|-------------:|-------:| +| ace | 100 | 100 | 100 | +| af | 5000 | 1000 | 1000 | +| als | 100 | 100 | 100 | +| am | 100 | 100 | 100 | +| an | 1000 | 1000 | 1000 | +| ang | 100 | 100 | 100 | +| ar | 20000 | 10000 | 10000 | +| arc | 100 | 100 | 100 | +| arz | 100 | 100 | 100 | +| as | 100 | 100 | 100 | +| ast | 1000 | 1000 | 1000 | +| ay | 100 | 100 | 100 | +| az | 10000 | 1000 | 1000 | +| ba | 100 | 100 | 100 | +| bar | 100 | 100 | 100 | +| bat-smg | 100 | 100 | 100 | +| be | 15000 | 1000 | 1000 | +| be-x-old | 5000 | 1000 | 1000 | +| bg | 20000 | 10000 | 10000 | +| bh | 100 | 100 | 100 | +| bn | 10000 | 1000 | 1000 | +| bo | 100 | 100 | 100 | +| br | 1000 | 1000 | 1000 | +| bs | 15000 | 1000 | 1000 | +| ca | 20000 | 10000 | 10000 | +| cbk-zam | 100 | 100 | 100 | +| cdo | 100 | 100 | 100 | +| ce | 100 | 100 | 100 | +| ceb | 100 | 100 | 100 | +| ckb | 1000 | 1000 | 1000 | +| co | 100 | 100 | 100 | +| crh | 100 | 100 | 100 | +| cs | 20000 | 10000 | 10000 | +| csb | 100 | 100 | 100 | +| cv | 100 | 100 | 100 | +| cy | 10000 | 1000 | 1000 | +| da | 20000 | 10000 | 10000 | +| de | 20000 | 10000 | 10000 | +| diq | 100 | 100 | 100 | +| dv | 100 | 100 | 100 | +| el | 20000 | 10000 | 10000 | +| eml | 100 | 100 | 100 | +| en | 20000 | 10000 | 10000 | +| eo | 15000 | 10000 | 10000 | +| es | 20000 | 10000 | 10000 | +| et | 15000 | 10000 | 10000 | +| eu | 10000 | 10000 | 10000 | +| ext | 100 | 100 | 100 | +| fa | 20000 | 10000 | 10000 | +| fi | 20000 | 10000 | 10000 | +| fiu-vro | 100 | 100 | 100 | +| fo | 100 | 100 | 100 | +| fr | 20000 | 10000 | 10000 | +| frr | 100 | 100 | 100 | +| fur | 100 | 100 | 100 | +| fy | 1000 | 1000 | 1000 | +| ga | 1000 | 1000 | 1000 | +| gan | 100 | 100 | 100 | +| gd | 100 | 100 | 100 | +| gl | 15000 | 10000 | 10000 | +| gn | 100 | 100 | 100 | +| gu | 100 | 100 | 100 | +| hak | 100 | 100 | 100 | +| he | 20000 | 10000 | 10000 | +| hi | 5000 | 1000 | 1000 | +| hr | 20000 | 10000 | 10000 | +| hsb | 100 | 100 | 100 | +| hu | 20000 | 10000 | 10000 | +| hy | 15000 | 1000 | 1000 | +| ia | 100 | 100 | 100 | +| id | 20000 | 10000 | 10000 | +| ig | 100 | 100 | 100 | +| ilo | 100 | 100 | 100 | +| io | 100 | 100 | 100 | +| is | 1000 | 1000 | 1000 | +| it | 20000 | 10000 | 10000 | +| ja | 20000 | 10000 | 10000 | +| jbo | 100 | 100 | 100 | +| jv | 100 | 100 | 100 | +| ka | 10000 | 10000 | 10000 | +| kk | 1000 | 1000 | 1000 | +| km | 100 | 100 | 100 | +| kn | 100 | 100 | 100 | +| ko | 20000 | 10000 | 10000 | +| ksh | 100 | 100 | 100 | +| ku | 100 | 100 | 100 | +| ky | 100 | 100 | 100 | +| la | 5000 | 1000 | 1000 | +| lb | 5000 | 1000 | 1000 | +| li | 100 | 100 | 100 | +| lij | 100 | 100 | 100 | +| lmo | 100 | 100 | 100 | +| ln | 100 | 100 | 100 | +| lt | 10000 | 10000 | 10000 | +| lv | 10000 | 10000 | 10000 | +| map-bms | 100 | 100 | 100 | +| mg | 100 | 100 | 100 | +| mhr | 100 | 100 | 100 | +| mi | 100 | 100 | 100 | +| min | 100 | 100 | 100 | +| mk | 10000 | 1000 | 1000 | +| ml | 10000 | 1000 | 1000 | +| mn | 100 | 100 | 100 | +| mr | 5000 | 1000 | 1000 | +| ms | 20000 | 1000 | 1000 | +| mt | 100 | 100 | 100 | +| mwl | 100 | 100 | 100 | +| my | 100 | 100 | 100 | +| mzn | 100 | 100 | 100 | +| nap | 100 | 100 | 100 | +| nds | 100 | 100 | 100 | +| ne | 100 | 100 | 100 | +| nl | 20000 | 10000 | 10000 | +| nn | 20000 | 1000 | 1000 | +| no | 20000 | 10000 | 10000 | +| nov | 100 | 100 | 100 | +| oc | 100 | 100 | 100 | +| or | 100 | 100 | 100 | +| os | 100 | 100 | 100 | +| pa | 100 | 100 | 100 | +| pdc | 100 | 100 | 100 | +| pl | 20000 | 10000 | 10000 | +| pms | 100 | 100 | 100 | +| pnb | 100 | 100 | 100 | +| ps | 100 | 100 | 100 | +| pt | 20000 | 10000 | 10000 | +| qu | 100 | 100 | 100 | +| rm | 100 | 100 | 100 | +| ro | 20000 | 10000 | 10000 | +| ru | 20000 | 10000 | 10000 | +| rw | 100 | 100 | 100 | +| sa | 100 | 100 | 100 | +| sah | 100 | 100 | 100 | +| scn | 100 | 100 | 100 | +| sco | 100 | 100 | 100 | +| sd | 100 | 100 | 100 | +| sh | 20000 | 10000 | 10000 | +| si | 100 | 100 | 100 | +| simple | 20000 | 1000 | 1000 | +| sk | 20000 | 10000 | 10000 | +| sl | 15000 | 10000 | 10000 | +| so | 100 | 100 | 100 | +| sq | 5000 | 1000 | 1000 | +| sr | 20000 | 10000 | 10000 | +| su | 100 | 100 | 100 | +| sv | 20000 | 10000 | 10000 | +| sw | 1000 | 1000 | 1000 | +| szl | 100 | 100 | 100 | +| ta | 15000 | 1000 | 1000 | +| te | 1000 | 1000 | 1000 | +| tg | 100 | 100 | 100 | +| th | 20000 | 10000 | 10000 | +| tk | 100 | 100 | 100 | +| tl | 10000 | 1000 | 1000 | +| tr | 20000 | 10000 | 10000 | +| tt | 1000 | 1000 | 1000 | +| ug | 100 | 100 | 100 | +| uk | 20000 | 10000 | 10000 | +| ur | 20000 | 1000 | 1000 | +| uz | 1000 | 1000 | 1000 | +| vec | 100 | 100 | 100 | +| vep | 100 | 100 | 100 | +| vi | 20000 | 10000 | 10000 | +| vls | 100 | 100 | 100 | +| vo | 100 | 100 | 100 | +| wa | 100 | 100 | 100 | +| war | 100 | 100 | 100 | +| wuu | 100 | 100 | 100 | +| xmf | 100 | 100 | 100 | +| yi | 100 | 100 | 100 | +| yo | 100 | 100 | 100 | +| zea | 100 | 100 | 100 | +| zh | 20000 | 10000 | 10000 | +| zh-classical | 100 | 100 | 100 | +| zh-min-nan | 100 | 100 | 100 | +| zh-yue | 20000 | 10000 | 10000 | + +## Dataset Creation + +### Curation Rationale + +[More Information Needed] + +### Source Data + +#### Initial Data Collection and Normalization + +[More Information Needed] + +#### Who are the source language producers? + +[More Information Needed] + +### Annotations + +#### Annotation process + +[More Information Needed] + +#### Who are the annotators? + +[More Information Needed] + +### Personal and Sensitive Information + +[More Information Needed] + +## Considerations for Using the Data + +### Social Impact of Dataset + +[More Information Needed] + +### Discussion of Biases + +[More Information Needed] + +### Other Known Limitations + +[More Information Needed] + +## Additional Information + +### Dataset Curators + +[More Information Needed] + +### Licensing Information + +[More Information Needed] + +### Citation Information + +The original 282 datasets are associated with this article + +``` +@inproceedings{pan-etal-2017-cross, + title = ""Cross-lingual Name Tagging and Linking for 282 Languages"", + author = ""Pan, Xiaoman and + Zhang, Boliang and + May, Jonathan and + Nothman, Joel and + Knight, Kevin and + Ji, Heng"", + booktitle = ""Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"", + month = jul, + year = ""2017"", + address = ""Vancouver, Canada"", + publisher = ""Association for Computational Linguistics"", + url = ""https://www.aclweb.org/anthology/P17-1178"", + doi = ""10.18653/v1/P17-1178"", + pages = ""1946--1958"", + abstract = ""The ambitious goal of this work is to develop a cross-lingual name tagging and linking framework for 282 languages that exist in Wikipedia. Given a document in any of these languages, our framework is able to identify name mentions, assign a coarse-grained or fine-grained type to each mention, and link it to an English Knowledge Base (KB) if it is linkable. We achieve this goal by performing a series of new KB mining methods: generating {``}silver-standard{''} annotations by transferring annotations from English to other languages through cross-lingual links and KB properties, refining annotations through self-training and topic selection, deriving language-specific morphology features from anchor links, and mining word translation pairs from cross-lingual links. Both name tagging and linking results for 282 languages are promising on Wikipedia data and on-Wikipedia data."", +} +``` + +while the 176 languages supported in this version are associated with the following article + +``` +@inproceedings{rahimi-etal-2019-massively, + title = ""Massively Multilingual Transfer for {NER}"", + author = ""Rahimi, Afshin and + Li, Yuan and + Cohn, Trevor"", + booktitle = ""Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics"", + month = jul, + year = ""2019"", + address = ""Florence, Italy"", + publisher = ""Association for Computational Linguistics"", + url = ""https://www.aclweb.org/anthology/P19-1015"", + pages = ""151--164"", +} +``` + + +### Contributions + +Thanks to [@lewtun](https://github.com/lewtun) and [@rabeehk](https://github.com/rabeehk) for adding this dataset." +HAERAE-HUB/KMMLU,"{""configs"": [{""config_name"": ""Accounting"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Accounting-train.csv""}, {""split"": ""dev"", ""path"": ""data/Accounting-dev.csv""}, {""split"": ""test"", ""path"": ""data/Accounting-test.csv""}]}, {""config_name"": ""Agricultural-Sciences"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Agricultural-Sciences-train.csv""}, {""split"": ""dev"", ""path"": ""data/Agricultural-Sciences-dev.csv""}, {""split"": ""test"", ""path"": ""data/Agricultural-Sciences-test.csv""}]}, {""config_name"": ""Aviation-Engineering-and-Maintenance"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Aviation-Engineering-and-Maintenance-train.csv""}, {""split"": ""dev"", ""path"": ""data/Aviation-Engineering-and-Maintenance-dev.csv""}, {""split"": ""test"", ""path"": ""data/Aviation-Engineering-and-Maintenance-test.csv""}]}, {""config_name"": ""Biology"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Biology-train.csv""}, {""split"": ""dev"", ""path"": ""data/Biology-dev.csv""}, {""split"": ""test"", ""path"": ""data/Biology-test.csv""}]}, {""config_name"": ""Chemical-Engineering"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Chemical-Engineering-train.csv""}, {""split"": ""dev"", ""path"": ""data/Chemical-Engineering-dev.csv""}, {""split"": ""test"", ""path"": ""data/Chemical-Engineering-test.csv""}]}, {""config_name"": ""Chemistry"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Chemistry-train.csv""}, {""split"": ""dev"", ""path"": ""data/Chemistry-dev.csv""}, {""split"": ""test"", ""path"": ""data/Chemistry-test.csv""}]}, {""config_name"": ""Civil-Engineering"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Civil-Engineering-train.csv""}, {""split"": ""dev"", ""path"": ""data/Civil-Engineering-dev.csv""}, {""split"": ""test"", ""path"": ""data/Civil-Engineering-test.csv""}]}, {""config_name"": ""Computer-Science"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Computer-Science-train.csv""}, {""split"": ""dev"", ""path"": ""data/Computer-Science-dev.csv""}, {""split"": ""test"", ""path"": ""data/Computer-Science-test.csv""}]}, {""config_name"": ""Construction"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Construction-train.csv""}, {""split"": ""dev"", ""path"": ""data/Construction-dev.csv""}, {""split"": ""test"", ""path"": ""data/Construction-test.csv""}]}, {""config_name"": ""Criminal-Law"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Criminal-Law-train.csv""}, {""split"": ""dev"", ""path"": ""data/Criminal-Law-dev.csv""}, {""split"": ""test"", ""path"": ""data/Criminal-Law-test.csv""}]}, {""config_name"": ""Ecology"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Ecology-train.csv""}, {""split"": ""dev"", ""path"": ""data/Ecology-dev.csv""}, {""split"": ""test"", ""path"": ""data/Ecology-test.csv""}]}, {""config_name"": ""Economics"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Economics-train.csv""}, {""split"": ""dev"", ""path"": ""data/Economics-dev.csv""}, {""split"": ""test"", ""path"": ""data/Economics-test.csv""}]}, {""config_name"": ""Education"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Education-train.csv""}, {""split"": ""dev"", ""path"": ""data/Education-dev.csv""}, {""split"": ""test"", ""path"": ""data/Education-test.csv""}]}, {""config_name"": ""Electrical-Engineering"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Electrical-Engineering-train.csv""}, {""split"": ""dev"", ""path"": ""data/Electrical-Engineering-dev.csv""}, {""split"": ""test"", ""path"": ""data/Electrical-Engineering-test.csv""}]}, {""config_name"": ""Electronics-Engineering"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Electronics-Engineering-train.csv""}, {""split"": ""dev"", ""path"": ""data/Electronics-Engineering-dev.csv""}, {""split"": ""test"", ""path"": ""data/Electronics-Engineering-test.csv""}]}, {""config_name"": ""Energy-Management"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Energy-Management-train.csv""}, {""split"": ""dev"", ""path"": ""data/Energy-Management-dev.csv""}, {""split"": ""test"", ""path"": ""data/Energy-Management-test.csv""}]}, {""config_name"": ""Environmental-Science"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Environmental-Science-train.csv""}, {""split"": ""dev"", ""path"": ""data/Environmental-Science-dev.csv""}, {""split"": ""test"", ""path"": ""data/Environmental-Science-test.csv""}]}, {""config_name"": ""Fashion"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Fashion-train.csv""}, {""split"": ""dev"", ""path"": ""data/Fashion-dev.csv""}, {""split"": ""test"", ""path"": ""data/Fashion-test.csv""}]}, {""config_name"": ""Food-Processing"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Food-Processing-train.csv""}, {""split"": ""dev"", ""path"": ""data/Food-Processing-dev.csv""}, {""split"": ""test"", ""path"": ""data/Food-Processing-test.csv""}]}, {""config_name"": ""Gas-Technology-and-Engineering"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Gas-Technology-and-Engineering-train.csv""}, {""split"": ""dev"", ""path"": ""data/Gas-Technology-and-Engineering-dev.csv""}, {""split"": ""test"", ""path"": ""data/Gas-Technology-and-Engineering-test.csv""}]}, {""config_name"": ""Geomatics"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Geomatics-train.csv""}, {""split"": ""dev"", ""path"": ""data/Geomatics-dev.csv""}, {""split"": ""test"", ""path"": ""data/Geomatics-test.csv""}]}, {""config_name"": ""Health"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Health-train.csv""}, {""split"": ""dev"", ""path"": ""data/Health-dev.csv""}, {""split"": ""test"", ""path"": ""data/Health-test.csv""}]}, {""config_name"": ""Industrial-Engineer"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Industrial-Engineer-train.csv""}, {""split"": ""dev"", ""path"": ""data/Industrial-Engineer-dev.csv""}, {""split"": ""test"", ""path"": ""data/Industrial-Engineer-test.csv""}]}, {""config_name"": ""Information-Technology"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Information-Technology-train.csv""}, {""split"": ""dev"", ""path"": ""data/Information-Technology-dev.csv""}, {""split"": ""test"", ""path"": ""data/Information-Technology-test.csv""}]}, {""config_name"": ""Interior-Architecture-and-Design"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Interior-Architecture-and-Design-train.csv""}, {""split"": ""dev"", ""path"": ""data/Interior-Architecture-and-Design-dev.csv""}, {""split"": ""test"", ""path"": ""data/Interior-Architecture-and-Design-test.csv""}]}, {""config_name"": ""Law"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Law-train.csv""}, {""split"": ""dev"", ""path"": ""data/Law-dev.csv""}, {""split"": ""test"", ""path"": ""data/Law-test.csv""}]}, {""config_name"": ""Machine-Design-and-Manufacturing"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Machine-Design-and-Manufacturing-train.csv""}, {""split"": ""dev"", ""path"": ""data/Machine-Design-and-Manufacturing-dev.csv""}, {""split"": ""test"", ""path"": ""data/Machine-Design-and-Manufacturing-test.csv""}]}, {""config_name"": ""Management"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Management-train.csv""}, {""split"": ""dev"", ""path"": ""data/Management-dev.csv""}, {""split"": ""test"", ""path"": ""data/Management-test.csv""}]}, {""config_name"": ""Maritime-Engineering"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Maritime-Engineering-train.csv""}, {""split"": ""dev"", ""path"": ""data/Maritime-Engineering-dev.csv""}, {""split"": ""test"", ""path"": ""data/Maritime-Engineering-test.csv""}]}, {""config_name"": ""Marketing"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Marketing-train.csv""}, {""split"": ""dev"", ""path"": ""data/Marketing-dev.csv""}, {""split"": ""test"", ""path"": ""data/Marketing-test.csv""}]}, {""config_name"": ""Materials-Engineering"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Materials-Engineering-train.csv""}, {""split"": ""dev"", ""path"": ""data/Materials-Engineering-dev.csv""}, {""split"": ""test"", ""path"": ""data/Materials-Engineering-test.csv""}]}, {""config_name"": ""Mechanical-Engineering"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Mechanical-Engineering-train.csv""}, {""split"": ""dev"", ""path"": ""data/Mechanical-Engineering-dev.csv""}, {""split"": ""test"", ""path"": ""data/Mechanical-Engineering-test.csv""}]}, {""config_name"": ""Nondestructive-Testing"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Nondestructive-Testing-train.csv""}, {""split"": ""dev"", ""path"": ""data/Nondestructive-Testing-dev.csv""}, {""split"": ""test"", ""path"": ""data/Nondestructive-Testing-test.csv""}]}, {""config_name"": ""Patent"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Patent-train.csv""}, {""split"": ""dev"", ""path"": ""data/Patent-dev.csv""}, {""split"": ""test"", ""path"": ""data/Patent-test.csv""}]}, {""config_name"": ""Political-Science-and-Sociology"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Political-Science-and-Sociology-train.csv""}, {""split"": ""dev"", ""path"": ""data/Political-Science-and-Sociology-dev.csv""}, {""split"": ""test"", ""path"": ""data/Political-Science-and-Sociology-test.csv""}]}, {""config_name"": ""Psychology"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Psychology-train.csv""}, {""split"": ""dev"", ""path"": ""data/Psychology-dev.csv""}, {""split"": ""test"", ""path"": ""data/Psychology-test.csv""}]}, {""config_name"": ""Public-Safety"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Public-Safety-train.csv""}, {""split"": ""dev"", ""path"": ""data/Public-Safety-dev.csv""}, {""split"": ""test"", ""path"": ""data/Public-Safety-test.csv""}]}, {""config_name"": ""Railway-and-Automotive-Engineering"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Railway-and-Automotive-Engineering-train.csv""}, {""split"": ""dev"", ""path"": ""data/Railway-and-Automotive-Engineering-dev.csv""}, {""split"": ""test"", ""path"": ""data/Railway-and-Automotive-Engineering-test.csv""}]}, {""config_name"": ""Real-Estate"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Real-Estate-train.csv""}, {""split"": ""dev"", ""path"": ""data/Real-Estate-dev.csv""}, {""split"": ""test"", ""path"": ""data/Real-Estate-test.csv""}]}, {""config_name"": ""Refrigerating-Machinery"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Refrigerating-Machinery-train.csv""}, {""split"": ""dev"", ""path"": ""data/Refrigerating-Machinery-dev.csv""}, {""split"": ""test"", ""path"": ""data/Refrigerating-Machinery-test.csv""}]}, {""config_name"": ""Social-Welfare"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Social-Welfare-train.csv""}, {""split"": ""dev"", ""path"": ""data/Social-Welfare-dev.csv""}, {""split"": ""test"", ""path"": ""data/Social-Welfare-test.csv""}]}, {""config_name"": ""Taxation"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Taxation-train.csv""}, {""split"": ""dev"", ""path"": ""data/Taxation-dev.csv""}, {""split"": ""test"", ""path"": ""data/Taxation-test.csv""}]}, {""config_name"": ""Telecommunications-and-Wireless-Technology"", ""data_files"": [{""split"": ""train"", ""path"": ""data/Telecommunications-and-Wireless-Technology-train.csv""}, {""split"": ""dev"", ""path"": ""data/Telecommunications-and-Wireless-Technology-dev.csv""}, {""split"": ""test"", ""path"": ""data/Telecommunications-and-Wireless-Technology-test.csv""}]}, {""config_name"": ""Korean-History"", ""data_files"": [{""split"": ""train"", ""path"": ""data/korean-history-train.csv""}, {""split"": ""dev"", ""path"": ""data/korean-history-dev.csv""}, {""split"": ""test"", ""path"": ""data/korean-history-test.csv""}]}, {""config_name"": ""Math"", ""data_files"": [{""split"": ""train"", ""path"": ""data/math-train.csv""}, {""split"": ""dev"", ""path"": ""data/math-dev.csv""}, {""split"": ""test"", ""path"": ""data/math-test.csv""}]}], ""task_categories"": [""multiple-choice""], ""language"": [""ko""], ""tags"": [""mmlu"", ""haerae""], ""size_categories"": [""10K + + + +### Supported Tasks and Leaderboards + +The dataset is generally used for Language Modeling. + +### Languages + +You can find the list of languages here: https://meta.wikimedia.org/wiki/List_of_Wikipedias + +## Dataset Structure + +### Data Instances + +An example looks as follows: +``` +{'id': '1', + 'url': 'https://simple.wikipedia.org/wiki/April', + 'title': 'April', + 'text': 'April is the fourth month...' +} +``` + +### Data Fields + +The data fields are the same among all configurations: +- `id` (`str`): ID of the article. +- `url` (`str`): URL of the article. +- `title` (`str`): Title of the article. +- `text` (`str`): Text content of the article. + +### Data Splits + +All configurations contain a single `train` split. + +## Dataset Creation + +### Curation Rationale + +[More Information Needed] + +### Source Data + +#### Initial Data Collection and Normalization + +The dataset is built from the Wikipedia dumps: https://dumps.wikimedia.org + +You can find the full list of languages and dates here: https://dumps.wikimedia.org/backup-index.html + +The articles have been parsed using the [`mwparserfromhell`](https://mwparserfromhell.readthedocs.io) tool. + +When uploading the data files for the 20231101 dump, we noticed that the Wikimedia Dumps website does not contain this date dump +for the ""bbc"", ""dga"", nor ""zgh"" Wikipedias. We have reported the issue to the Wikimedia Phabricator: https://phabricator.wikimedia.org/T351761 + +#### Who are the source language producers? + +[More Information Needed] + +### Annotations + +#### Annotation process + +[More Information Needed] + +#### Who are the annotators? + +[More Information Needed] + +### Personal and Sensitive Information + +[More Information Needed] + +## Considerations for Using the Data + +### Social Impact of Dataset + +[More Information Needed] + +### Discussion of Biases + +[More Information Needed] + +### Other Known Limitations + +[More Information Needed] + +## Additional Information + +### Dataset Curators + +[More Information Needed] + +### Licensing Information + +Copyright licensing information: https://dumps.wikimedia.org/legal.html + +All original textual content is licensed under the [GNU Free Documentation License](https://www.gnu.org/licenses/fdl-1.3.html) (GFDL) +and the [Creative Commons Attribution-Share-Alike 3.0 License](https://creativecommons.org/licenses/by-sa/3.0/). +Some text may be available only under the Creative Commons license; see their [Terms of Use](https://foundation.wikimedia.org/wiki/Policy:Terms_of_Use) for details. +Text written by some authors may be released under additional licenses or into the public domain. + +### Citation Information + +``` +@ONLINE{wikidump, + author = ""Wikimedia Foundation"", + title = ""Wikimedia Downloads"", + url = ""https://dumps.wikimedia.org"" +} +```" +MBZUAI/Bactrian-X,"{""license"": ""cc-by-nc-4.0"", ""task_categories"": [""text-generation""], ""language"": [""af"", ""ar"", ""az"", ""bn"", ""cs"", ""de"", ""en"", ""es"", ""et"", ""fi"", ""fr"", ""gl"", ""gu"", ""he"", ""hi"", ""hr"", ""id"", ""it"", ""ja"", ""ka"", ""kk"", ""km"", ""ko"", ""lt"", ""lv"", ""mk"", ""ml"", ""mn"", ""mr"", ""my"", ""ne"", ""nl"", ""pl"", ""ps"", ""pt"", ""ro"", ""ru"", ""si"", ""sl"", ""sv"", ""sw"", ""ta"", ""te"", ""th"", ""tl"", ""tr"", ""uk"", ""ur"", ""vi"", ""xh"", ""zh""], ""tags"": [""instruction-finetuning"", ""multilingual""], ""pretty_name"": ""Bactrian-X""}","# Dataset Card for ""Bactrian-X"" + +## Table of Contents +- [Dataset Description](#a-dataset-description) + - [Dataset Summary](#dataset-summary) + - [Languages](#languages) +- [Dataset Structure](#b-dataset-structure) + - [Data Fields](#data-fields) + - [Data Instances](#data-instances) + - [Data in 52 Languages](#data-in-52-languages) +- [Dataset Creation](#c-dataset-creation) +- [Considerations for Using the Data](#d-considerations-for-using-the-data) +- [Additional Information](#e-additional-information) + + +## A. Dataset Description + +- **Homepage:** https://github.com/mbzuai-nlp/Bactrian-X +- **Repository:** https://huggingface.co/datasets/MBZUAI/Bactrian-X +- **Paper:** to-be-soon released + +### Dataset Summary + + +

+ +

+ + +The Bactrain-X dataset is a collection of 3.4M instruction-response pairs in 52 languages, that are obtained by translating 67K English instructions ([alpaca-52k](https://github.com/tatsu-lab/stanford_alpaca) + [dolly-15k](https://github.com/databrickslabs/dolly/tree/master/data)) into 51 languages using Google Translate API. The translated instructions are then fed to ChatGPT (`gpt-3.5-turbo`) to obtain its natural responses, resulting in 3.4M instruction-response pairs in 52 languages (52 languages x 67k instances = 3.4M instances). + +### Languages + +We follow 52 languages of [mBART-50](https://arxiv.org/abs/2008.00401), with details can be found [below](#data-in-52-languages). + +## B. Dataset Structure + +### Data Fields + +The data fields are as follows: + +* `instruction`: describes the task the model should perform. Each of the 67K instructions is unique. +* `input`: optional context or input for the task. For example, when the instruction is ""Summarize the following article"", the input is the article. Around 40% of the examples have an input. +* `output`: the answer to the instruction as generated by `gpt-3.5-turbo`. +* `id`: the unique index for each data piece in a specific language. The same `id` across splits corresponds to the same original English data. + +### Data Instances + +An example in `en` looks as follows. + +```json +{ +""instruction"": ""What is the main idea of this text?"", +""input"": ""The robotics industry has become one of the fastest growing sectors in today’s economy. Robotics technology is being applied in various industries and applications, such as manufacturing, healthcare, and defense."", +""output"": ""The main idea of the text is that the robotics industry is rapidly growing and its technology is being used in many different industries and applications."", +""id"": ""alpaca-107"" +} +``` + +An example in `ar` looks as follows. +```json +{ +""instruction"": ""قم بالوصول إلى إعدادات المتصفح الافتراضية على جهاز الكمبيوتر."", +""input"": """", +""output"": ""لا يمكن لي كمساعد افتراضي القيام بهذه المهمة كونها تحتاج إلى الوصول إلى الجهاز المادي. يرجى الرجوع إلى دليل المستخدم للكمبيوتر الخاص بك أو البحث على الإنترنت لمعرفة كيفية الوصول إلى إعدادات المتصفح الافتراضية على جهاز الكمبيوتر الخاص بك."", +""id"": ""alpaca-41997"" +} +``` + +An example in `id` looks as follows. +```json +{ +""instruction"": ""Berapa banyak angka penting yang harus digunakan untuk nilai 0,000187?"", +""input"": """", +""output"": ""Ada tiga angka penting dalam nilai 0,000187."", +""id"": ""alpaca-40382"" +} +``` + +An example in `de` looks as follows. +```json +{ +""instruction"": ""Komponieren Sie ein Musikstück mit einem Titel, der Trauer bezeichnet."", +""input"": """", +""output"": """"Schmerzendes Herz""\n\nDas Stück beginnt mit einer langsamen, traurigen Melodie, gespielt von einem Solo-Violoncello. Die Harmonien, die von einem Klavier begleitet werden, sind durcheinander und dissonant, um ein Gefühl von Schmerz und Trauer zu vermitteln.\n\nIm Laufe des Stücks treten andere Instrumente ein, wie Streicher, Flöte und Oboe, um die Melodie zu unterstützen und zu intensivieren. Der Rhythmus bleibt langsam und schwerfällig, um die Schwere des Schmerzes darzustellen.\n\nIn der Mitte des Stücks gibt es einen Höhepunkt, wo die Melodie und Harmonien sich verdichten und ein Gefühl von Überwältigung erzeugen. Der Solo-Violoncello spielt eine traurige und schnelle Phrase, die die Verzweiflung und Isolation des Protagonisten ausdrückt.\n\nDas Stück endet mit einer Wiederholung der ersten Melodie, gespielt von einem Solo-Klavier, während die anderen Instrumente auslaufen. Die Harmonien werden jedoch weicher und sanfter, um einen Hauch von Hoffnung zu vermitteln, dass der Schmerz langsam vergeht."", +""id"": ""alpaca-33619"" +} +``` + +An example in `fr` looks as follows. +```json +{ +""instruction"": ""Les Ceanothus ont-ils des racines peu profondes ?"", +""input"": """", +""output"": ""En tant qu'IA, je ne peux pas répondre avec une certitude absolue, mais voici des informations générales sur les racines de Ceanothus : \n\nLes Ceanothus ont tendance à avoir un système racinaire étendu et peu profond. Les racines peuvent s'étaler jusqu'à 4 à 6 fois la taille de la plante et s'étendre à environ 60 à 90 cm de profondeur. Cependant, cela peut varier en fonction du type de sol et de la variété de Ceanothus. Certaines variétés de Ceanothus pourraient avoir des racines plus profondes si les conditions s'y prêtent."", +""id"": ""dolly-10940"" +} +``` + + +### Data in 52 Languages + +| No | Languages | Code | Train | +| ---|---------------- | ----- | ----- | +| 1 | [Afrikaans](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/af) | af_ZA | 67017 | +| 2 | [Arabic](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ar) | ar_AR | 67017 | +| 3 | [Azerbaijani](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/az) | az_AZ | 67017 | +| 4 | [Bengali](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/bn) | bn_IN | 67017 | +| 5 | [Czech](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/cs) | cs_CZ | 67017 | +| 6 | [German](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/de) | de_DE | 67017 | +| 7 | [English](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/en) | en_XX | 67017 | +| 8 | [Spanish](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/es) | es_XX | 67017 | +| 9 | [Estonian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/et) | et_EE | 67017 | +| 10 | [Persian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/fa) | fa_IR | 67017 | +| 11 | [Finnish](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/fi) | fi_FI | 67017 | +| 12 | [French](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/fr) | fr_XX | 67017 | +| 13 | [Galician](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/gl) | gl_ES | 67017 | +| 14 | [Gujarati](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/gu) | gu_IN | 67017 | +| 15 | [Hebrew](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/he) | he_IL | 67017 | +| 16 | [Hindi](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/hi) | hi_IN | 67017 | +| 17 | [Croatian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/hr) | hr_HR | 67017 | +| 18 | [Indonesian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/id) | id_ID | 67017 | +| 19 | [Italian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/it) | it_IT | 67017 | +| 20 | [Japanese](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ja) | ja_XX | 67017 | +| 21 | [Georgian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ka) | ka_GE | 67017 | +| 22 | [Kazakh](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/kk) | kk_KZ | 67017 | +| 23 | [Khmer](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/km) | km_KH | 67017 | +| 24 | [Korean](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ko) | ko_KR | 67017 | +| 25 | [Lithuanian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/lt) | lt_LT | 67017 | +| 26 | [Latvian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/lv) | lv_LV | 67017 | +| 27 | [Macedonian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/mk) | mk_MK | 67017 | +| 28 | [Malayalam](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ml) | ml_IN | 67017 | +| 29 | [Mongolian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/mn) | mn_MN | 67017 | +| 30 | [Marathi](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/mr) | mr_IN | 67017 | +| 31 | [Burmese](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/my) | my_MM | 67017 | +| 32 | [Nepali](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ne) | ne_NP | 67017 | +| 33 | [Dutch](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/nl) | nl_XX | 67017 | +| 34 | [Polish](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/pl) | pl_PL | 67017 | +| 35 | [Pashto](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ps) | ps_AF | 67017 | +| 36 | [Portuguese](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/pt) | pt_XX | 67017 | +| 37 | [Romanian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ro) | ro_RO | 67017 | +| 38 | [Russian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ru) | ru_RU | 67017 | +| 39 | [Sinhala](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/si) | si_LK | 67017 | +| 40 | [Slovene](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/sl) | sl_SI | 67017 | +| 41 | [Swedish](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/sv) | sv_SE | 67017 | +| 42 | [Swahili](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/sw) | sw_KE | 67017 | +| 43 | [Tamil](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ta) | ta_IN | 67017 | +| 44 | [Telugu](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/te) | te_IN | 67017 | +| 45 | [Thai](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/th) | th_TH | 67017 | +| 46 | [Tagalog](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/tl) | tl_XX | 67017 | +| 47 | [Turkish](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/tr) | tr_TR | 67017 | +| 48 | [Ukrainian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/uk) | uk_UA | 67017 | +| 49 | [Urdu](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ur) | ur_PK | 67017 | +| 50 | [Vietnamese](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/vi) | vi_VN | 67017 | +| 51 | [Xhosa](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/xh) | xh_ZA | 67017 | +| 52 | [Chinese](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/zh) | zh_CN | 67017 | + +## C. Dataset Creation + +1. English Instructions: The English instuctions are obtained from [alpaca-53k](https://github.com/tatsu-lab/stanford_alpaca), and [dolly-15k](https://github.com/databrickslabs/dolly/tree/master/data). +2. Instruction Translation: The instructions (and inputs) are translated into 51 languages using Google Translation API (conducted on April 2023). +3. Output Generation: We generate output from `gpt-3.5-turbo` for each language (conducted on April 2023). + +## D. Considerations for Using the Data + +### Social Impact of Dataset + +NLP for everyone: this dataset helps to democratize the cutting-edge instruction-following models in 52 languages. This dataset also allows the first experiment on the multilingual LoRA-based LLaMA model. + +### Discussion of Biases + +(1) Translation bias; (2) Potential English-culture bias in the translated dataset. + +### Other Known Limitations + +The `Bactrian-X` data is generated by a language model (`gpt-3.5-turbo`) and inevitably contains some errors or biases. We encourage users to use this data with caution and propose new methods to filter or improve the imperfections. + +## E. Additional Information + +### Dataset Curators + +[Haonan Li](https://haonan-li.github.io/) and [Fajri Koto](http://www.fajrikoto.com) + +### Licensing Information + +The dataset is available under the [Creative Commons NonCommercial (CC BY-NC 4.0)](https://creativecommons.org/licenses/by-nc/4.0/legalcode). + +### Citation Information + + +``` +@misc{li2023bactrianx, + title={Bactrian-X : A Multilingual Replicable Instruction-Following Model with Low-Rank Adaptation}, + author={Haonan Li and Fajri Koto and Minghao Wu and Alham Fikri Aji and Timothy Baldwin}, + year={2023}, + eprint={2305.15011}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +``` + +### Contributions + +Thanks to [@haonan-li](https://github.com/haonan-li), [@fajri91](https://github.com/fajri91) for adding this dataset." +csebuetnlp/xlsum,"{""annotations_creators"": [""found""], ""language_creators"": [""found""], ""language"": [""am"", ""ar"", ""az"", ""bn"", ""my"", ""zh"", ""en"", ""fr"", ""gu"", ""ha"", ""hi"", ""ig"", ""id"", ""ja"", ""rn"", ""ko"", ""ky"", ""mr"", ""ne"", ""om"", ""ps"", ""fa"", ""pcm"", ""pt"", ""pa"", ""ru"", ""gd"", ""sr"", ""si"", ""so"", ""es"", ""sw"", ""ta"", ""te"", ""th"", ""ti"", ""tr"", ""uk"", ""ur"", ""uz"", ""vi"", ""cy"", ""yo""], ""license"": [""cc-by-nc-sa-4.0""], ""multilinguality"": [""multilingual""], ""size_categories"": [""1M \n Q: \n A: \n B: \n C: \n D: \n Answer: ```. We perform prediction by picking the answer within `[A, B, C, D]` that has the highest probability relatively to the others. +- **Few-shot in-context learning (translated examples)** ^ + - Same as above, except the samples from the training set are translated to the target language so that the examples and evaluation data are in the same language. The training samples can be human or machine-translated. + + +#### With finetuning +- **English finetune & multilingual evaluation** + - The model is finetuned to the task using the English training set, probably with a sequence classification head. Then the model is evaluated in all the target languages individually. For results presented in the paper we used [the HuggingFace library](https://huggingface.co/docs/transformers/en/model_doc/xlm-roberta#transformers.XLMRobertaForMultipleChoice). +- **English finetune & cross-lingual evaluation** + - Same as above, except the model is evaluated in a cross-lingual setting, where for each question, the passage & answers could be provided in a different language. For example, passage could be in language `x`, question in language `y`, and answers in language `z`. +- **Translate-train** ^ + - For each target language, the model is individually finetuned on training samples that have been machine-translated from English to that language. Each model is then evaluated in the respective target language. +- **Translate-train-all** + - Similar to above, except here the model is trained on translated samples from all target languages at once. The single finetuned model is then evaluated on all target languages. +- **Translate-train-all & cross-lingual evaluation** + - Same as above, except the single finetuned model is evaluated in a cross-lingual setting, where for each question, the passage & answers could be provided in a different language. +- **Translate-test** + - The model is finetuned using the English training data and then the evaluation dataset is machine-translated to English and evaluated on the English. + - This setting is primarily a reflection of the quality of the machine translation system, but is useful for comparison to multilingual models. + +In addition, there are 83 additional languages in FLORES-200 for which questions were not translated for Belebele. Since the passages exist in those target languages, machine-translating the questions & answers may enable decent evaluation of machine reading comprehension in those languages. + +## Training Set + +As discussed in the paper, we also provide an assembled training set consisting of samples at the [github repo](https://github.com/facebookresearch/belebele). + +The Belebele dataset is intended to be used only as a test set, and not for training or validation. Therefore, for models that require additional task-specific training, we instead propose using an assembled training set consisting of samples from pre-existing multiple-choice QA datasets in English. We considered diverse datasets, and determine the most compatible to be [RACE](https://www.cs.cmu.edu/~glai1/data/race/), [SciQ](https://allenai.org/data/sciq), [MultiRC](https://cogcomp.seas.upenn.edu/multirc/), [MCTest](https://mattr1.github.io/mctest/), [MCScript2.0](https://aclanthology.org/S19-1012/), and [ReClor](https://whyu.me/reclor/). + +For each of the six datasets, we unpack and restructure the passages and questions from their respective formats. We then filter out less suitable samples (e.g. questions with multiple correct answers). In the end, the dataset comprises 67.5k training samples and 3.7k development samples, more than half of which are from RACE. We provide a script (`assemble_training_set.py`) to reconstruct this dataset for anyone to perform task finetuning. + +Since the training set is a joint sample of other datasets, it is governed by a different license. We do not claim any of that work or datasets to be our own. See the Licenses section in the README of https://github.com/facebookresearch/belebele . + +## Languages in Belebele + +FLORES-200 Code | English Name | Script | Family +---|---|---|--- +acm_Arab | Mesopotamian Arabic | Arab | Afro-Asiatic +afr_Latn | Afrikaans | Latn | Germanic +als_Latn | Tosk Albanian | Latn | Paleo-Balkanic +amh_Ethi | Amharic | Ethi | Afro-Asiatic +apc_Arab | North Levantine Arabic | Arab | Afro-Asiatic +arb_Arab | Modern Standard Arabic | Arab | Afro-Asiatic +arb_Latn | Modern Standard Arabic (Romanized) | Latn | Afro-Asiatic +ars_Arab | Najdi Arabic | Arab | Afro-Asiatic +ary_arab | Moroccan Arabic | Arab | Afro-Asiatic +arz_Arab | Egyptian Arabic | Arab | Afro-Asiatic +asm_Beng | Assamese | Beng | Indo-Aryan +azj_Latn | North Azerbaijani | Latn | Turkic +bam_Latn | Bambara | Latn | Mande +ben_Beng | Bengali | Beng | Indo-Aryan +ben_Latn | Bengali (Romanized) | Latn | Indo-Aryan +bod_Tibt | Standard Tibetan | Tibt | Sino-Tibetan +bul_Cyrl | Bulgarian | Cyrl | Balto-Slavic +cat_Latn | Catalan | Latn | Romance +ceb_Latn | Cebuano | Latn | Austronesian +ces_Latn | Czech | Latn | Balto-Slavic +ckb_Arab | Central Kurdish | Arab | Iranian +dan_Latn | Danish | Latn | Germanic +deu_Latn | German | Latn | Germanic +ell_Grek | Greek | Grek | Hellenic +eng_Latn | English | Latn | Germanic +est_Latn | Estonian | Latn | Uralic +eus_Latn | Basque | Latn | Basque +fin_Latn | Finnish | Latn | Uralic +fra_Latn | French | Latn | Romance +fuv_Latn | Nigerian Fulfulde | Latn | Atlantic-Congo +gaz_Latn | West Central Oromo | Latn | Afro-Asiatic +grn_Latn | Guarani | Latn | Tupian +guj_Gujr | Gujarati | Gujr | Indo-Aryan +hat_Latn | Haitian Creole | Latn | Atlantic-Congo +hau_Latn | Hausa | Latn | Afro-Asiatic +heb_Hebr | Hebrew | Hebr | Afro-Asiatic +hin_Deva | Hindi | Deva | Indo-Aryan +hin_Latn | Hindi (Romanized) | Latn | Indo-Aryan +hrv_Latn | Croatian | Latn | Balto-Slavic +hun_Latn | Hungarian | Latn | Uralic +hye_Armn | Armenian | Armn | Armenian +ibo_Latn | Igbo | Latn | Atlantic-Congo +ilo_Latn | Ilocano | Latn | Austronesian +ind_Latn | Indonesian | Latn | Austronesian +isl_Latn | Icelandic | Latn | Germanic +ita_Latn | Italian | Latn | Romance +jav_Latn | Javanese | Latn | Austronesian +jpn_Jpan | Japanese | Jpan | Japonic +kac_Latn | Jingpho | Latn | Sino-Tibetan +kan_Knda | Kannada | Knda | Dravidian +kat_Geor | Georgian | Geor | kartvelian +kaz_Cyrl | Kazakh | Cyrl | Turkic +kea_Latn | Kabuverdianu | Latn | Portuguese Creole +khk_Cyrl | Halh Mongolian | Cyrl | Mongolic +khm_Khmr | Khmer | Khmr | Austroasiatic +kin_Latn | Kinyarwanda | Latn | Atlantic-Congo +kir_Cyrl | Kyrgyz | Cyrl | Turkic +kor_Hang | Korean | Hang | Koreanic +lao_Laoo | Lao | Laoo | Kra-Dai +lin_Latn | Lingala | Latn | Atlantic-Congo +lit_Latn | Lithuanian | Latn | Balto-Slavic +lug_Latn | Ganda | Latn | Atlantic-Congo +luo_Latn | Luo | Latn | Nilo-Saharan +lvs_Latn | Standard Latvian | Latn | Balto-Slavic +mal_Mlym | Malayalam | Mlym | Dravidian +mar_Deva | Marathi | Deva | Indo-Aryan +mkd_Cyrl | Macedonian | Cyrl | Balto-Slavic +mlt_Latn | Maltese | Latn | Afro-Asiatic +mri_Latn | Maori | Latn | Austronesian +mya_Mymr | Burmese | Mymr | Sino-Tibetan +nld_Latn | Dutch | Latn | Germanic +nob_Latn | Norwegian Bokmål | Latn | Germanic +npi_Deva | Nepali | Deva | Indo-Aryan +npi_Latn | Nepali (Romanized) | Latn | Indo-Aryan +nso_Latn | Northern Sotho | Latn | Atlantic-Congo +nya_Latn | Nyanja | Latn | Afro-Asiatic +ory_Orya | Odia | Orya | Indo-Aryan +pan_Guru | Eastern Panjabi | Guru | Indo-Aryan +pbt_Arab | Southern Pashto | Arab | Indo-Aryan +pes_Arab | Western Persian | Arab | Iranian +plt_Latn | Plateau Malagasy | Latn | Austronesian +pol_Latn | Polish | Latn | Balto-Slavic +por_Latn | Portuguese | Latn | Romance +ron_Latn | Romanian | Latn | Romance +rus_Cyrl | Russian | Cyrl | Balto-Slavic +shn_Mymr | Shan | Mymr | Kra-Dai +sin_Latn | Sinhala (Romanized) | Latn | Indo-Aryan +sin_Sinh | Sinhala | Sinh | Indo-Aryan +slk_Latn | Slovak | Latn | Balto-Slavic +slv_Latn | Slovenian | Latn | Balto-Slavic +sna_Latn | Shona | Latn | Atlantic-Congo +snd_Arab | Sindhi | Arab | Indo-Aryan +som_Latn | Somali | Latn | Afro-Asiatic +sot_Latn | Southern Sotho | Latn | Atlantic-Congo +spa_Latn | Spanish | Latn | Romance +srp_Cyrl | Serbian | Cyrl | Balto-Slavic +ssw_Latn | Swati | Latn | Atlantic-Congo +sun_Latn | Sundanese | Latn | Austronesian +swe_Latn | Swedish | Latn | Germanic +swh_Latn | Swahili | Latn | Atlantic-Congo +tam_Taml | Tamil | Taml | Dravidian +tel_Telu | Telugu | Telu | Dravidian +tgk_Cyrl | Tajik | Cyrl | Iranian +tgl_Latn | Tagalog | Latn | Austronesian +tha_Thai | Thai | Thai | Kra-Dai +tir_Ethi | Tigrinya | Ethi | Afro-Asiatic +tsn_Latn | Tswana | Latn | Atlantic-Congo +tso_Latn | Tsonga | Latn | Afro-Asiatic +tur_Latn | Turkish | Latn | Turkic +ukr_Cyrl | Ukrainian | Cyrl | Balto-Slavic +urd_Arab | Urdu | Arab | Indo-Aryan +urd_Latn | Urdu (Romanized) | Latn | Indo-Aryan +uzn_Latn | Northern Uzbek | Latn | Turkic +vie_Latn | Vietnamese | Latn | Austroasiatic +war_Latn | Waray | Latn | Austronesian +wol_Latn | Wolof | Latn | Atlantic-Congo +xho_Latn | Xhosa | Latn | Atlantic-Congo +yor_Latn | Yoruba | Latn | Atlantic-Congo +zho_Hans | Chinese (Simplified) | Hans | Sino-Tibetan +zho_Hant | Chinese (Traditional) | Hant | Sino-Tibetan +zsm_Latn | Standard Malay | Latn | Austronesian +zul_Latn | Zulu | Latn | Atlantic-Congo" +mteb/sts17-crosslingual-sts,"{""language"": [""ar"", ""de"", ""en"", ""es"", ""fr"", ""it"", ""nl"", ""ko"", ""tr""], ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""test"", ""path"": ""test/*""}]}, {""config_name"": ""ko-ko"", ""data_files"": [{""split"": ""test"", ""path"": ""test/ko-ko.jsonl.gz""}]}, {""config_name"": ""ar-ar"", ""data_files"": [{""split"": ""test"", ""path"": ""test/ar-ar.jsonl.gz""}]}, {""config_name"": ""en-ar"", ""data_files"": [{""split"": ""test"", ""path"": ""test/en-ar.jsonl.gz""}]}, {""config_name"": ""en-de"", ""data_files"": [{""split"": ""test"", ""path"": ""test/en-de.jsonl.gz""}]}, {""config_name"": ""en-en"", ""data_files"": [{""split"": ""test"", ""path"": ""test/en-en.jsonl.gz""}]}, {""config_name"": ""en-tr"", ""data_files"": [{""split"": ""test"", ""path"": ""test/en-tr.jsonl.gz""}]}, {""config_name"": ""es-en"", ""data_files"": [{""split"": ""test"", ""path"": ""test/es-en.jsonl.gz""}]}, {""config_name"": ""es-es"", ""data_files"": [{""split"": ""test"", ""path"": ""test/es-es.jsonl.gz""}]}, {""config_name"": ""fr-en"", ""data_files"": [{""split"": ""test"", ""path"": ""test/fr-en.jsonl.gz""}]}, {""config_name"": ""it-en"", ""data_files"": [{""split"": ""test"", ""path"": ""test/it-en.jsonl.gz""}]}, {""config_name"": ""nl-en"", ""data_files"": [{""split"": ""test"", ""path"": ""test/nl-en.jsonl.gz""}]}]}", +skt/kobest_v1,"{""pretty_name"": ""KoBEST"", ""annotations_creators"": [""expert-generated""], ""language_creators"": [""expert-generated""], ""language"": [""ko""], ""license"": [""cc-by-sa-4.0""], ""multilinguality"": [""monolingual""], ""size_categories"": [""10K One of the biggest challenges hindering progress in low-resource and multilingual machine translation is the lack of good evaluation benchmarks. Current evaluation benchmarks either lack good coverage of low-resource languages, consider only restricted domains, or are low quality because they are constructed using semi-automatic procedures. In this work, we introduce the FLORES evaluation benchmark, consisting of 3001 sentences extracted from English Wikipedia and covering a variety of different topics and domains. These sentences have been translated in 101 languages by professional translators through a carefully controlled process. The resulting dataset enables better assessment of model quality on the long tail of low-resource languages, including the evaluation of many-to-many multilingual translation systems, as all translations are multilingually aligned. By publicly releasing such a high-quality and high-coverage dataset, we hope to foster progress in the machine translation community and beyond. + +**Disclaimer**: *The Flores-101 dataset is hosted by the Facebook and licensed under the [Creative Commons Attribution-ShareAlike 4.0 International License](https://creativecommons.org/licenses/by-sa/4.0/). + +### Supported Tasks and Leaderboards + +#### Multilingual Machine Translation + +Refer to the [Dynabench leaderboard](https://dynabench.org/flores/Flores%20MT%20Evaluation%20(FULL)) for additional details on model evaluation on FLORES-101 in the context of the WMT2021 shared task on [Large-Scale Multilingual Machine Translation](http://www.statmt.org/wmt21/large-scale-multilingual-translation-task.html). + +### Languages + +The dataset contains parallel sentences for 101 languages, as mentioned in the original [Github](https://github.com/facebookresearch/flores/blob/master/README.md) page for the project. Languages are identified with the ISO 639-3 code (e.g. `eng`, `fra`, `rus`) as in the original dataset. + +**New:** Use the configuration `all` to access the full set of parallel sentences for all the available languages in a single command. + + +## Dataset Structure + +### Data Instances + +A sample from the `dev` split for the Russian language (`rus` config) is provided below. All configurations have the same structure, and all sentences are aligned across configurations and splits. + +```python +{ + 'id': 1, + 'sentence': 'В понедельник ученые из Медицинской школы Стэнфордского университета объявили об изобретении нового диагностического инструмента, который может сортировать клетки по их типу; это маленький чип, который можно напечатать, используя стандартный струйный принтер примерно за 1 цент США.', + 'URL': 'https://en.wikinews.org/wiki/Scientists_say_new_medical_diagnostic_chip_can_sort_cells_anywhere_with_an_inkjet', + 'domain': 'wikinews', + 'topic': 'health', + 'has_image': 0, + 'has_hyperlink': 0 +} +``` + +The text is provided as-in the original dataset, without further preprocessing or tokenization. + +### Data Fields + +- `id`: Row number for the data entry, starting at 1. +- `sentence`: The full sentence in the specific language. +- `URL`: The URL for the English article from which the sentence was extracted. +- `domain`: The domain of the sentence. +- `topic`: The topic of the sentence. +- `has_image`: Whether the original article contains an image. +- `has_hyperlink`: Whether the sentence contains a hyperlink. + +### Data Splits + +| config| `dev`| `devtest`| +|-----------------:|-----:|---------:| +|all configurations| 997| 1012:| + +### Dataset Creation + +Please refer to the original article [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://arxiv.org/abs/2106.03193) for additional information on dataset creation. + +## Additional Information + +### Dataset Curators + +The original authors of FLORES-101 are the curators of the original dataset. For problems or updates on this 🤗 Datasets version, please contact [gabriele.sarti996@gmail.com](mailto:gabriele.sarti996@gmail.com). + +### Licensing Information + +Licensed with Creative Commons Attribution Share Alike 4.0. License available [here](https://creativecommons.org/licenses/by-sa/4.0/). + +### Citation Information + +Please cite the authors if you use these corpora in your work: + +```bibtex +@inproceedings{flores101, + title={The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation}, + author={Goyal, Naman and Gao, Cynthia and Chaudhary, Vishrav and Chen, Peng-Jen and Wenzek, Guillaume and Ju, Da and Krishnan, Sanjana and Ranzato, Marc'Aurelio and Guzm\'{a}n, Francisco and Fan, Angela}, + journal={arXiv preprint arXiv:2106.03193}, + year={2021} +} +```" +klue/klue,"{""annotations_creators"": [""expert-generated""], ""language_creators"": [""expert-generated""], ""language"": [""ko""], ""license"": [""cc-by-sa-4.0""], ""multilinguality"": [""monolingual""], ""size_categories"": [""10K <강릉:LC> 방향 <문막휴게소:LC>에서 <만종분기점:LC>까지 <5㎞:QT> 구간에는 승용차 전용 임시 갓길차로제를 운영하기로 했다.'} +``` + +#### re +An example of 'train' looks as follows. + +``` +{'guid': 'klue-re-v1_train_00000', + 'label': 0, + 'object_entity': {'word': '조지 해리슨', + 'start_idx': 13, + 'end_idx': 18, + 'type': 'PER'}, + 'sentence': '〈Something〉는 조지 해리슨이 쓰고 비틀즈가 1969년 앨범 《Abbey Road》에 담은 노래다.', + 'source': 'wikipedia', + 'subject_entity': {'word': '비틀즈', + 'start_idx': 24, + 'end_idx': 26, + 'type': 'ORG'}} +``` + +#### dp +An example of 'train' looks as follows. + +``` +{'deprel': ['NP', 'NP_OBJ', 'VP', 'NP', 'NP_SBJ', 'NP', 'NP_MOD', 'NP_CNJ', 'NP_CNJ', 'NP', 'NP', 'NP_OBJ', 'AP', 'VP'], + 'head': [2, 3, 14, 5, 14, 7, 10, 10, 10, 11, 12, 14, 14, 0], + 'index': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14], + 'lemma': ['해당', '그림 을', '보 면', '디즈니', '공주 들 이', '브리트니', '스피어스 의', '앨범 이나', '뮤직 비디오 ,', '화보', '속', '모습 을', '똑같이', '재연 하 였 다 .'], + 'pos': ['NNG', 'NNG+JKO', 'VV+EC', 'NNP', 'NNG+XSN+JKS', 'NNP', 'NNP+JKG', 'NNG+JC', 'NNG+NNG+SP', 'NNG', 'NNG', 'NNG+JKO', 'MAG', 'NNG+XSA+EP+EF+SF'], + 'sentence': '해당 그림을 보면 디즈니 공주들이 브리트니 스피어스의 앨범이나 뮤직비디오, 화보 속 모습을 똑같이 재연했다.', + 'word_form': ['해당', '그림을', '보면', '디즈니', '공주들이', '브리트니', '스피어스의', '앨범이나', '뮤직비디오,', '화보', '속', '모습을', '똑같이', '재연했다.']} +``` + +#### mrc +An example of 'train' looks as follows. + +``` +{'answers': {'answer_start': [478, 478], 'text': ['한 달가량', '한 달']}, + 'context': '올여름 장마가 17일 제주도에서 시작됐다. 서울 등 중부지방은 예년보다 사나흘 정도 늦은 이달 말께 장마가 시작될 전망이다.17일 기상청에 따르면 제주도 남쪽 먼바다에 있는 장마전선의 영향으로 이날 제주도 산간 및 내륙지역에 호우주의보가 내려지면서 곳곳에 100㎜에 육박하는 많은 비가 내렸다. 제주의 장마는 평년보다 2~3일, 지난해보다는 하루 일찍 시작됐다. 장마는 고온다습한 북태평양 기단과 한랭 습윤한 오호츠크해 기단이 만나 형성되는 장마전선에서 내리는 비를 뜻한다.장마전선은 18일 제주도 먼 남쪽 해상으로 내려갔다가 20일께 다시 북상해 전남 남해안까지 영향을 줄 것으로 보인다. 이에 따라 20~21일 남부지방에도 예년보다 사흘 정도 장마가 일찍 찾아올 전망이다. 그러나 장마전선을 밀어올리는 북태평양 고기압 세력이 약해 서울 등 중부지방은 평년보다 사나흘가량 늦은 이달 말부터 장마가 시작될 것이라는 게 기상청의 설명이다. 장마전선은 이후 한 달가량 한반도 중남부를 오르내리며 곳곳에 비를 뿌릴 전망이다. 최근 30년간 평균치에 따르면 중부지방의 장마 시작일은 6월24~25일이었으며 장마기간은 32일, 강수일수는 17.2일이었다.기상청은 올해 장마기간의 평균 강수량이 350~400㎜로 평년과 비슷하거나 적을 것으로 내다봤다. 브라질 월드컵 한국과 러시아의 경기가 열리는 18일 오전 서울은 대체로 구름이 많이 끼지만 비는 오지 않을 것으로 예상돼 거리 응원에는 지장이 없을 전망이다.', + 'guid': 'klue-mrc-v1_train_12759', + 'is_impossible': False, + 'news_category': '종합', + 'question': '북태평양 기단과 오호츠크해 기단이 만나 국내에 머무르는 기간은?', + 'question_type': 1, + 'source': 'hankyung', + 'title': '제주도 장마 시작 … 중부는 이달 말부터'} +``` + +#### wos +An example of 'train' looks as follows. + +``` +{'dialogue': [{'role': 'user', + 'text': '쇼핑을 하려는데 서울 서쪽에 있을까요?', + 'state': ['관광-종류-쇼핑', '관광-지역-서울 서쪽']}, + {'role': 'sys', + 'text': '서울 서쪽에 쇼핑이 가능한 곳이라면 노량진 수산물 도매시장이 있습니다.', + 'state': []}, + {'role': 'user', + 'text': '오 네 거기 주소 좀 알려주세요.', + 'state': ['관광-종류-쇼핑', '관광-지역-서울 서쪽', '관광-이름-노량진 수산물 도매시장']}, + {'role': 'sys', 'text': '노량진 수산물 도매시장의 주소는 서울 동작구 93806입니다.', 'state': []}, + {'role': 'user', + 'text': '알려주시는김에 연락처랑 평점도 좀 알려주세요.', + 'state': ['관광-종류-쇼핑', '관광-지역-서울 서쪽', '관광-이름-노량진 수산물 도매시장']}, + {'role': 'sys', 'text': '그럼. 연락처는 6182006591이고 평점은 4점입니다.', 'state': []}, + {'role': 'user', + 'text': '와 감사합니다.', + 'state': ['관광-종류-쇼핑', '관광-지역-서울 서쪽', '관광-이름-노량진 수산물 도매시장']}, + {'role': 'sys', 'text': '감사합니다.', 'state': []}], + 'domains': ['관광'], + 'guid': 'wos-v1_train_00001'} +``` + +### Data Fields + +#### ynat + ++ `guid`: a `string` feature ++ `title`: a `string` feature ++ `label`: a classification label, with possible values `IT과학`(0), `경제`(1), `사회`(2), `생활문화`(3), `세계`(4), `스포츠`(5), `정치`(6) ++ `url`: a `string` feature ++ `date`: a `string` feature + +#### sts + ++ `guid`: a `string` feature ++ `source`: a `string` feature ++ `sentence1`: a `string` feature ++ `sentence2`: a `string` feature ++ `labels`: a dictionary feature containing + + `label`: a `float64` feature + + `real-label`: a `float64` feature + + `binary-label`: a classification label, with possible values `negative`(0), `positive`(1) + +#### nli + ++ `guid`: a `string` feature ++ `source`: a `string` feature ++ `premise`: a `string` feature ++ `hypothesis`: a `string` feature ++ `label`: a classification label, with possible values `entailment`(0), `neutral`(1), `contradiction`(2) + +#### ner + ++ `sentence`: a `string` feature ++ `tokens`: a list of a `string` feature (tokenization is at character level) ++ `ner_tags`: a list of classification labels, with possible values including `B-DT`(0), `I-DT`(1), + `B-LC`(2), `I-LC`(3), `B-OG`(4), `I-OG`(5), `B-PS`(6), `I-PS`(7), `B-QT`(8), `I-QT`(9), `B-TI`(10), + `I-TI`(11), `O`(12) + +#### re + ++ `guid`: a `string` feature ++ `sentence`: a `string` feature ++ `subject_entity`: a dictionary feature containing + + `word`: a `string` feature + + `start_idx`: a `int32` feature + + `end_idx`: a `int32` feature + + `type`: a `string` feature ++ `object_entity`: a dictionary feature containing + + `word`: a `string` feature + + `start_idx`: a `int32` feature + + `end_idx`: a `int32` feature + + `type`: a `string` feature ++ `label`: a list of labels, with possible values including `no_relation`(0), `org:dissolved`(1), + `org:founded`(2), `org:place_of_headquarters`(3), `org:alternate_names`(4), `org:member_of`(5), + `org:members`(6), `org:political/religious_affiliation`(7), `org:product`(8), `org:founded_by`(9),`org:top_members/employees`(10), + `org:number_of_employees/members`(11), `per:date_of_birth`(12), `per:date_of_death`(13), `per:place_of_birth`(14), + `per:place_of_death`(15), `per:place_of_residence`(16), `per:origin`(17), `per:employee_of`(18), + `per:schools_attended`(19), `per:alternate_names`(20), `per:parents`(21), `per:children`(22), + `per:siblings`(23), `per:spouse`(24), `per:other_family`(25), `per:colleagues`(26), `per:product`(27), + `per:religion`(28), `per:title`(29), ++ `source`: a `string` feature + +#### dp + ++ `sentence`: a `string` feature ++ `index`: a list of `int32` feature ++ `word_form`: a list of `string` feature ++ `lemma`: a list of `string` feature ++ `pos`: a list of `string` feature ++ `head`: a list of `int32` feature ++ `deprel`: a list of `string` feature + + +#### mrc + ++ `title`: a `string` feature ++ `context`: a `string` feature ++ `news_category`: a `string` feature ++ `source`: a `string` feature ++ `guid`: a `string` feature ++ `is_impossible`: a `bool` feature ++ `question_type`: a `int32` feature ++ `question`: a `string` feature ++ `answers`: a dictionary feature containing + + `answer_start`: a `int32` feature + + `text`: a `string` feature + + +#### wos + ++ `guid`: a `string` feature ++ `domains`: a `string` feature ++ `dialogue`: a list of dictionary feature containing + + `role`: a `string` feature + + `text`: a `string` feature + + `state`: a `string` feature + + +### Data Splits + +#### ynat + +You can see more details in [here](https://klue-benchmark.com/tasks/66/data/description). + ++ train: 45,678 ++ validation: 9,107 + + +#### sts + +You can see more details in [here](https://klue-benchmark.com/tasks/67/data/description). + ++ train: 11,668 ++ validation: 519 + +#### nli + +You can see more details in [here](https://klue-benchmark.com/tasks/68/data/description). + ++ train: 24,998 ++ validation: 3,000 + +#### ner + +You can see more details in [here](https://klue-benchmark.com/tasks/69/overview/description). + ++ train: 21,008 ++ validation: 5,000 + +#### re + +You can see more details in [here](https://klue-benchmark.com/tasks/70/overview/description). + ++ train: 32,470 ++ validation: 7,765 + +#### dp + +You can see more details in [here](https://klue-benchmark.com/tasks/71/data/description). + ++ train: 10,000 ++ validation: 2,000 + +#### mrc + +You can see more details in [here](https://klue-benchmark.com/tasks/72/overview/description). + ++ train: 17,554 ++ validation: 5,841 + +#### wos + +You can see more details in [here](https://klue-benchmark.com/tasks/73/overview/description). + ++ train: 8,000 ++ validation: 1,000 + + +## Dataset Creation + +### Curation Rationale + +[Needs More Information] + +### Source Data + +#### Initial Data Collection and Normalization + +[Needs More Information] + +#### Who are the source language producers? + +[Needs More Information] + +### Annotations + +#### Annotation process + +[Needs More Information] + +#### Who are the annotators? + +[Needs More Information] + +### Personal and Sensitive Information + +[Needs More Information] + +## Considerations for Using the Data + +### Social Impact of Dataset + +[Needs More Information] + +### Discussion of Biases + +[Needs More Information] + +### Other Known Limitations + +[Needs More Information] + +## Additional Information + +### Dataset Curators + +[Needs More Information] + +### Licensing Information + +[Needs More Information] + +### Citation Information + +``` +@misc{park2021klue, + title={KLUE: Korean Language Understanding Evaluation}, + author={Sungjoon Park and Jihyung Moon and Sungdong Kim and Won Ik Cho and Jiyoon Han and Jangwon Park and Chisung Song and Junseong Kim and Yongsook Song and Taehwan Oh and Joohong Lee and Juhyun Oh and Sungwon Lyu and Younghoon Jeong and Inkwon Lee and Sangwoo Seo and Dongjun Lee and Hyunwoo Kim and Myeonghwa Lee and Seongbo Jang and Seungwon Do and Sunkyoung Kim and Kyungtae Lim and Jongwon Lee and Kyumin Park and Jamin Shin and Seonghyun Kim and Lucy Park and Alice Oh and Jungwoo Ha and Kyunghyun Cho}, + year={2021}, + eprint={2105.09680}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +``` +### Contributions + +Thanks to [@jungwhank](https://github.com/jungwhank), [@bzantium](https://github.com/bzantium) for adding this dataset." +mozilla-foundation/common_voice_17_0,"{""pretty_name"": ""Common Voice Corpus 17.0"", ""annotations_creators"": [""crowdsourced""], ""language_creators"": [""crowdsourced""], ""language"": [""ab"", ""af"", ""am"", ""ar"", ""as"", ""ast"", ""az"", ""ba"", ""bas"", ""be"", ""bg"", ""bn"", ""br"", ""ca"", ""ckb"", ""cnh"", ""cs"", ""cv"", ""cy"", ""da"", ""de"", ""dv"", ""dyu"", ""el"", ""en"", ""eo"", ""es"", ""et"", ""eu"", ""fa"", ""fi"", ""fr"", ""fy"", ""ga"", ""gl"", ""gn"", ""ha"", ""he"", ""hi"", ""hsb"", ""ht"", ""hu"", ""hy"", ""ia"", ""id"", ""ig"", ""is"", ""it"", ""ja"", ""ka"", ""kab"", ""kk"", ""kmr"", ""ko"", ""ky"", ""lg"", ""lij"", ""lo"", ""lt"", ""ltg"", ""lv"", ""mdf"", ""mhr"", ""mk"", ""ml"", ""mn"", ""mr"", ""mrj"", ""mt"", ""myv"", ""nan"", ""ne"", ""nhi"", ""nl"", ""nn"", ""nso"", ""oc"", ""or"", ""os"", ""pa"", ""pl"", ""ps"", ""pt"", ""quy"", ""rm"", ""ro"", ""ru"", ""rw"", ""sah"", ""sat"", ""sc"", ""sk"", ""skr"", ""sl"", ""sq"", ""sr"", ""sv"", ""sw"", ""ta"", ""te"", ""th"", ""ti"", ""tig"", ""tk"", ""tok"", ""tr"", ""tt"", ""tw"", ""ug"", ""uk"", ""ur"", ""uz"", ""vi"", ""vot"", ""yi"", ""yo"", ""yue"", ""zgh"", ""zh"", ""zu"", ""zza""], ""language_bcp47"": [""zh-CN"", ""zh-HK"", ""zh-TW"", ""sv-SE"", ""rm-sursilv"", ""rm-vallader"", ""pa-IN"", ""nn-NO"", ""ne-NP"", ""nan-tw"", ""hy-AM"", ""ga-IE"", ""fy-NL""], ""license"": [""cc0-1.0""], ""multilinguality"": [""multilingual""], ""source_datasets"": [""extended|common_voice""], ""paperswithcode_id"": ""common-voice"", ""extra_gated_prompt"": ""By clicking on \u201cAccess repository\u201d below, you also agree to not attempt to determine the identity of speakers in the Common Voice dataset.""}","# Dataset Card for Common Voice Corpus 17.0 + +## Table of Contents +- [Dataset Description](#dataset-description) + - [Dataset Summary](#dataset-summary) + - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) + - [Languages](#languages) +- [Dataset Structure](#dataset-structure) + - [Data Instances](#data-instances) + - [Data Fields](#data-fields) + - [Data Splits](#data-splits) +- [Dataset Creation](#dataset-creation) + - [Curation Rationale](#curation-rationale) + - [Source Data](#source-data) + - [Annotations](#annotations) + - [Personal and Sensitive Information](#personal-and-sensitive-information) +- [Considerations for Using the Data](#considerations-for-using-the-data) + - [Social Impact of Dataset](#social-impact-of-dataset) + - [Discussion of Biases](#discussion-of-biases) + - [Other Known Limitations](#other-known-limitations) +- [Additional Information](#additional-information) + - [Dataset Curators](#dataset-curators) + - [Licensing Information](#licensing-information) + - [Citation Information](#citation-information) + - [Contributions](#contributions) + +## Dataset Description + +- **Homepage:** https://commonvoice.mozilla.org/en/datasets +- **Repository:** https://github.com/common-voice/common-voice +- **Paper:** https://arxiv.org/abs/1912.06670 +- **Leaderboard:** https://paperswithcode.com/dataset/common-voice +- **Point of Contact:** [Vaibhav Srivastav](mailto:vaibhav@huggingface.co) + +### Dataset Summary + +The Common Voice dataset consists of a unique MP3 and corresponding text file. +Many of the 31175 recorded hours in the dataset also include demographic metadata like age, sex, and accent +that can help improve the accuracy of speech recognition engines. + +The dataset currently consists of 20408 validated hours in 124 languages, but more voices and languages are always added. +Take a look at the [Languages](https://commonvoice.mozilla.org/en/languages) page to request a language or start contributing. + +You can donate to this non-profit, donation-funded project here (https://commonvoice.mozilla.org/?form=common-voice) + +### Supported Tasks and Leaderboards + +The results for models trained on the Common Voice datasets are available via the +[🤗 Speech Bench](https://huggingface.co/spaces/huggingface/hf-speech-bench) + +### Languages + +``` +Abkhaz, Afrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Asturian, Azerbaijani, Basaa, Bashkir, Basque, Belarusian, Bengali, Breton, Bulgarian, Cantonese, Catalan, Central Kurdish, Chinese (China), Chinese (Hong Kong), Chinese (Taiwan), Chuvash, Czech, Danish, Dhivehi, Dioula, Dutch, English, Erzya, Esperanto, Estonian, Finnish, French, Frisian, Galician, Georgian, German, Greek, Guarani, Haitian, Hakha Chin, Hausa, Hebrew, Hill Mari, Hindi, Hungarian, Icelandic, Igbo, Indonesian, Interlingua, Irish, Italian, Japanese, Kabyle, Kazakh, Kinyarwanda, Korean, Kurmanji Kurdish, Kyrgyz, Lao, Latgalian, Latvian, Ligurian, Lithuanian, Luganda, Macedonian, Malayalam, Maltese, Marathi, Meadow Mari, Moksha, Mongolian, Nepali, Northern Sotho, Norwegian Nynorsk, Occitan, Odia, Ossetian, Pashto, Persian, Polish, Portuguese, Punjabi, Quechua Chanka, Romanian, Romansh Sursilvan, Romansh Vallader, Russian, Sakha, Santali (Ol Chiki), Saraiki, Sardinian, Serbian, Slovak, Slovenian, Sorbian, Upper, Spanish, Swahili, Swedish, Taiwanese (Minnan), Tamazight, Tamil, Tatar, Telugu, Thai, Tigre, Tigrinya, Toki Pona, Turkish, Turkmen, Twi, Ukrainian, Urdu, Uyghur, Uzbek, Vietnamese, Votic, Welsh, Western Sierra Puebla Nahuatl, Yiddish, Yoruba, Zaza, Zulu +``` + +## How to use + +The `datasets` library allows you to load and pre-process your dataset in pure Python, at scale. The dataset can be downloaded and prepared in one call to your local drive by using the `load_dataset` function. + +For example, to download the Hindi config, simply specify the corresponding language config name (i.e., ""hi"" for Hindi): +```python +from datasets import load_dataset + +cv_17 = load_dataset(""mozilla-foundation/common_voice_17_0"", ""hi"", split=""train"") +``` + +Using the datasets library, you can also stream the dataset on-the-fly by adding a `streaming=True` argument to the `load_dataset` function call. Loading a dataset in streaming mode loads individual samples of the dataset at a time, rather than downloading the entire dataset to disk. +```python +from datasets import load_dataset + +cv_17 = load_dataset(""mozilla-foundation/common_voice_17_0"", ""hi"", split=""train"", streaming=True) + +print(next(iter(cv_17))) +``` + +*Bonus*: create a [PyTorch dataloader](https://huggingface.co/docs/datasets/use_with_pytorch) directly with your own datasets (local/streamed). + +### Local + +```python +from datasets import load_dataset +from torch.utils.data.sampler import BatchSampler, RandomSampler + +cv_17 = load_dataset(""mozilla-foundation/common_voice_17_0"", ""hi"", split=""train"") + +batch_sampler = BatchSampler(RandomSampler(cv_17), batch_size=32, drop_last=False) +dataloader = DataLoader(cv_17, batch_sampler=batch_sampler) +``` + +### Streaming + +```python +from datasets import load_dataset +from torch.utils.data import DataLoader + +cv_17 = load_dataset(""mozilla-foundation/common_voice_17_0"", ""hi"", split=""train"") +dataloader = DataLoader(cv_17, batch_size=32) +``` + +To find out more about loading and preparing audio datasets, head over to [hf.co/blog/audio-datasets](https://huggingface.co/blog/audio-datasets). + +### Example scripts + +Train your own CTC or Seq2Seq Automatic Speech Recognition models on Common Voice 16 with `transformers` - [here](https://github.com/huggingface/transformers/tree/main/examples/pytorch/speech-recognition). + +## Dataset Structure + +### Data Instances + +A typical data point comprises the `path` to the audio file and its `sentence`. +Additional fields include `accent`, `age`, `client_id`, `up_votes`, `down_votes`, `gender`, `locale` and `segment`. + +```python +{ + 'client_id': 'd59478fbc1ee646a28a3c652a119379939123784d99131b865a89f8b21c81f69276c48bd574b81267d9d1a77b83b43e6d475a6cfc79c232ddbca946ae9c7afc5', + 'path': 'et/clips/common_voice_et_18318995.mp3', + 'audio': { + 'path': 'et/clips/common_voice_et_18318995.mp3', + 'array': array([-0.00048828, -0.00018311, -0.00137329, ..., 0.00079346, 0.00091553, 0.00085449], dtype=float32), + 'sampling_rate': 48000 + }, + 'sentence': 'Tasub kokku saada inimestega, keda tunned juba ammust ajast saati.', + 'up_votes': 2, + 'down_votes': 0, + 'age': 'twenties', + 'gender': 'male', + 'accent': '', + 'locale': 'et', + 'segment': '' +} +``` + +### Data Fields + +`client_id` (`string`): An id for which client (voice) made the recording + +`path` (`string`): The path to the audio file + +`audio` (`dict`): A dictionary containing the path to the downloaded audio file, the decoded audio array, and the sampling rate. Note that when accessing the audio column: `dataset[0][""audio""]` the audio file is automatically decoded and resampled to `dataset.features[""audio""].sampling_rate`. Decoding and resampling of a large number of audio files might take a significant amount of time. Thus it is important to first query the sample index before the `""audio""` column, *i.e.* `dataset[0][""audio""]` should **always** be preferred over `dataset[""audio""][0]`. + +`sentence` (`string`): The sentence the user was prompted to speak + +`up_votes` (`int64`): How many upvotes the audio file has received from reviewers + +`down_votes` (`int64`): How many downvotes the audio file has received from reviewers + +`age` (`string`): The age of the speaker (e.g. `teens`, `twenties`, `fifties`) + +`gender` (`string`): The gender of the speaker + +`accent` (`string`): Accent of the speaker + +`locale` (`string`): The locale of the speaker + +`segment` (`string`): Usually an empty field + +### Data Splits + +The speech material has been subdivided into portions for dev, train, test, validated, invalidated, reported and other. + +The validated data is data that has been validated with reviewers and received upvotes that the data is of high quality. + +The invalidated data is data has been invalidated by reviewers +and received downvotes indicating that the data is of low quality. + +The reported data is data that has been reported, for different reasons. + +The other data is data that has not yet been reviewed. + +The dev, test, train are all data that has been reviewed, deemed of high quality and split into dev, test and train. + +## Data Preprocessing Recommended by Hugging Face + +The following are data preprocessing steps advised by the Hugging Face team. They are accompanied by an example code snippet that shows how to put them to practice. + +Many examples in this dataset have trailing quotations marks, e.g _“the cat sat on the mat.“_. These trailing quotation marks do not change the actual meaning of the sentence, and it is near impossible to infer whether a sentence is a quotation or not a quotation from audio data alone. In these cases, it is advised to strip the quotation marks, leaving: _the cat sat on the mat_. + +In addition, the majority of training sentences end in punctuation ( . or ? or ! ), whereas just a small proportion do not. In the dev set, **almost all** sentences end in punctuation. Thus, it is recommended to append a full-stop ( . ) to the end of the small number of training examples that do not end in punctuation. + +```python +from datasets import load_dataset + +ds = load_dataset(""mozilla-foundation/common_voice_17"", ""en"", use_auth_token=True) + +def prepare_dataset(batch): + """"""Function to preprocess the dataset with the .map method"""""" + transcription = batch[""sentence""] + + if transcription.startswith('""') and transcription.endswith('""'): + # we can remove trailing quotation marks as they do not affect the transcription + transcription = transcription[1:-1] + + if transcription[-1] not in [""."", ""?"", ""!""]: + # append a full-stop to sentences that do not end in punctuation + transcription = transcription + ""."" + + batch[""sentence""] = transcription + + return batch + +ds = ds.map(prepare_dataset, desc=""preprocess dataset"") +``` + +## Dataset Creation + +### Curation Rationale + +[Needs More Information] + +### Source Data + +#### Initial Data Collection and Normalization + +[Needs More Information] + +#### Who are the source language producers? + +[Needs More Information] + +### Annotations + +#### Annotation process + +[Needs More Information] + +#### Who are the annotators? + +[Needs More Information] + +### Personal and Sensitive Information + +The dataset consists of people who have donated their voice online. You agree to not attempt to determine the identity of speakers in the Common Voice dataset. + +## Considerations for Using the Data + +### Social Impact of Dataset + +The dataset consists of people who have donated their voice online. You agree to not attempt to determine the identity of speakers in the Common Voice dataset. + +### Discussion of Biases + +[More Information Needed] + +### Other Known Limitations + +[More Information Needed] + +## Additional Information + +### Dataset Curators + +[More Information Needed] + +### Licensing Information + +Public Domain, [CC-0](https://creativecommons.org/share-your-work/public-domain/cc0/) + +### Citation Information + +``` +@inproceedings{commonvoice:2020, + author = {Ardila, R. and Branson, M. and Davis, K. and Henretty, M. and Kohler, M. and Meyer, J. and Morais, R. and Saunders, L. and Tyers, F. M. and Weber, G.}, + title = {Common Voice: A Massively-Multilingual Speech Corpus}, + booktitle = {Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)}, + pages = {4211--4215}, + year = 2020 +} +```" +nthngdy/oscar-small,"{""annotations_creators"": [""no-annotation""], ""language_creators"": [""found""], ""language"": [""af"", ""am"", ""ar"", ""arz"", ""as"", ""az"", ""azb"", ""ba"", ""be"", ""bg"", ""bn"", ""bo"", ""br"", ""ca"", ""ce"", ""ceb"", ""ckb"", ""cs"", ""cv"", ""cy"", ""da"", ""de"", ""dv"", ""el"", ""en"", ""eo"", ""es"", ""et"", ""eu"", ""fa"", ""fi"", ""fr"", ""fy"", ""ga"", ""gl"", ""gu"", ""he"", ""hi"", ""hr"", ""hu"", ""hy"", ""id"", ""is"", ""it"", ""ja"", ""ka"", ""kk"", ""km"", ""kn"", ""ko"", ""ku"", ""ky"", ""la"", ""lb"", ""lo"", ""lt"", ""lv"", ""mg"", ""mhr"", ""mk"", ""ml"", ""mn"", ""mr"", ""ms"", ""mt"", ""my"", ""nds"", ""ne"", ""nl"", ""nn"", ""no"", ""or"", ""os"", ""pa"", ""pl"", ""pnb"", ""ps"", ""pt"", ""ro"", ""ru"", ""sa"", ""sah"", ""sd"", ""sh"", ""si"", ""sk"", ""sl"", ""sq"", ""sr"", ""sv"", ""sw"", ""ta"", ""te"", ""tg"", ""th"", ""tk"", ""tl"", ""tr"", ""tt"", ""ug"", ""uk"", ""ur"", ""uz"", ""vi"", ""yi"", ""zh""], ""license"": [""cc0-1.0""], ""multilinguality"": [""multilingual""], ""source_datasets"": [""oscar""], ""task_categories"": [""text-generation""], ""task_ids"": [""language-modeling""], ""paperswithcode_id"": ""oscar"", ""pretty_name"": ""OSCAR""}","## WARNING: this dataset is an extract of the OSCAR dataset published here to simulate the use of the full dataset in low-resource contexts. +Using this dataset is equivalent to using a processed version of OSCAR legally speaking. I take no credit for the gathering of the original data and hence refer entirely to the original dataset in the card below. + +# Dataset Card for ""oscar"" + +## Table of Contents +- [Dataset Description](#dataset-description) + - [Dataset Summary](#dataset-summary) + - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) + - [Languages](#languages) +- [Dataset Structure](#dataset-structure) + - [Data Instances](#data-instances) + - [Data Fields](#data-fields) + - [Data Splits](#data-splits) +- [Dataset Creation](#dataset-creation) + - [Curation Rationale](#curation-rationale) + - [Source Data](#source-data) + - [Annotations](#annotations) + - [Personal and Sensitive Information](#personal-and-sensitive-information) +- [Considerations for Using the Data](#considerations-for-using-the-data) + - [Social Impact of Dataset](#social-impact-of-dataset) + - [Discussion of Biases](#discussion-of-biases) + - [Other Known Limitations](#other-known-limitations) +- [Additional Information](#additional-information) + - [Dataset Curators](#dataset-curators) + - [Licensing Information](#licensing-information) + - [Citation Information](#citation-information) + - [Contributions](#contributions) + +## Dataset Description + +- **Homepage:** [https://oscar-corpus.com](https://oscar-corpus.com) +- **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) +- **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) +- **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) + +### Dataset Summary + +OSCAR or **O**pen **S**uper-large **C**rawled [**A**LMAnaCH](https://team.inria.fr/almanach/) co**R**pus is a huge multilingual corpus obtained by language classification and filtering of the [Common Crawl](https://commoncrawl.org/) corpus using the [goclassy](https://github.com/pjox/goclassy) architecture. Data is distributed by language in both original and deduplicated form. + +### Supported Tasks and Leaderboards + +OSCAR is mainly inteded to pretrain language models and word represantations. + +### Languages + +All the data is distributed by language, both the original and the deduplicated versions of the data are available. 166 different languages are available. The table in subsection [Data Splits Sample Size](#data-splits-sample-size) provides the language code for each subcorpus as well as the number of words (space separated tokens), lines and sizes for both the original and the deduplicated versions of OSCAR. + +## Dataset Structure + +We show detailed information for all the configurations of the dataset. + +## Dataset Creation + +### Curation Rationale + +OSCAR was constructed new pipeline derived from the [fastText's one](https://github.com/facebookresearch/fastText), called [_goclassy_](https://github.com/pjox/goclassy). Goclassy reuses the [fastText linear classifier](https://fasttext.cc) and the pre-trained fastText model for language recognition, but it completely rewrites and parallelises their pipeline in an asynchronous manner. + +The order of operations is more or less the same as in the fastText pre-processing pipeline but instead of clustering multiple operations into a single blocking process, a worker is launched for each operation but bounding the number of possible parallel operations at a given time by the number of available threads instead of the number of CPUs. Goclassy is implemented in the [Go programming language](https://golang.org/) so it lets the [Go runtime](https://golang.org/src/runtime/mprof.go) handle the scheduling of the processes. Thus the goclassy's pipeline one does not have to wait for a whole WET file to download, decompress and classify in order to start downloading and processing the next one, a new file will start downloading and processing as soon as the scheduler is able to allocate a new process. + +Filtering and cleaning processes at line level are done before feeding each line to the classifier. Lines shorter than 100 UTF-8 characters and lines containing invalid UTF-8 characters are discarted and are not classified. After all files are proccesed the deduplicated versions are constructed and everything is then splitted in shards and compressed. + +### Source Data + +#### Initial Data Collection and Normalization + +[Common Crawl](https://commoncrawl.org/) is a non-profit foundation which produces and maintains an open repository of web crawled data that is both accessible and analysable. Common Crawl's complete web archive consists of petabytes of data collected over 8 years of web crawling. The repository contains raw web page HTML data (WARC files), metdata extracts (WAT files) and plain text extracts (WET files). The organisation's crawlers has always respected [nofollow](http://microformats.org/wiki/rel-nofollow) and [robots.txt](https://www.robotstxt.org/) policies. + +Each monthly Common Crawl snapshot is in itself a massive multilingual corpus, where every single file contains data coming from multiple web pages written in a large variety of languages and covering all possible types of topics. + +To construct OSCAR the WET files of Common Crawl were used. These contain the extracted plain texts from the websites mostly converted to UTF-8, as well as headers containing the metatada of each crawled document. Each WET file comes compressed in gzip format and is stored on Amazon Web Services. In the case of OSCAR, the **November 2018** snapshot was used. It surpasses 20TB of uncompressed data and contains more than 50 thousand plain text files where each file consists of the plain text from multiple websites along its metadata header. + +#### Who are the source language producers? + +The data comes from multiple web pages in a large variety of languages. + +### Annotations + +The dataset does not contain any additional annotations. + +#### Annotation process + +N/A + +#### Who are the annotators? + +N/A + +### Personal and Sensitive Information + +Being constructed from Common Crawl, Personal and sensitive information might be present. This **must** be considered before training deep learning models with OSCAR, specially in the case of text-generation models. + +## Considerations for Using the Data + +### Social Impact of Dataset + +OSCAR is intended to bring more data to a wide variety of lanuages, the aim of the corpus is to make large amounts of data available to lower resource languages in order to facilitate the pre-training of state-of-the-art language modeling architectures. + +### Discussion of Biases + +OSCAR is not properly filtered yet and this can be reflected on the models trained with it. Care is advised specially concerning biases of the resulting models. + +### Other Known Limitations + +The [fastText linear classifier](https://fasttext.cc) is limed both in performance and the variety of languages it can recognize, so the quality of some OSCAR sub-corpora might be lower than expected, specially for the lowest-resource langiuages. Some audits have already been done by [third parties](https://arxiv.org/abs/2010.14571). + +## Additional Information + +### Dataset Curators + +The corpus was put together by [Pedro J. Ortiz](https://pjortiz.eu/), [Benoît Sagot](http://pauillac.inria.fr/~sagot/), and [Laurent Romary](https://cv.archives-ouvertes.fr/laurentromary), during work done at [Inria](https://www.inria.fr/en), particularly at the [ALMAnaCH team](https://team.inria.fr/almanach/). + +### Licensing Information + + These data are released under this licensing scheme + We do not own any of the text from which these data has been extracted. + We license the actual packaging of these data under the Creative Commons CC0 license (""no rights reserved"") http://creativecommons.org/publicdomain/zero/1.0/ + To the extent possible under law, Inria has waived all copyright and related or neighboring rights to OSCAR + This work is published from: France. + + Should you consider that our data contains material that is owned by you and should therefore not be reproduced here, please: + * Clearly identify yourself, with detailed contact data such as an address, telephone number or email address at which you can be contacted. + * Clearly identify the copyrighted work claimed to be infringed. + * Clearly identify the material that is claimed to be infringing and information reasonably sufficient to allow us to locate the material. + + We will comply to legitimate requests by removing the affected sources from the next release of the corpus. + +### Citation Information + +``` +@inproceedings{ortiz-suarez-etal-2020-monolingual, + title = ""A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages"", + author = ""Ortiz Su{'a}rez, Pedro Javier and + Romary, Laurent and + Sagot, Benoit"", + booktitle = ""Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics"", + month = jul, + year = ""2020"", + address = ""Online"", + publisher = ""Association for Computational Linguistics"", + url = ""https://www.aclweb.org/anthology/2020.acl-main.156"", + pages = ""1703--1714"", + abstract = ""We use the multilingual OSCAR corpus, extracted from Common Crawl via language classification, filtering and cleaning, to train monolingual contextualized word embeddings (ELMo) for five mid-resource languages. We then compare the performance of OSCAR-based and Wikipedia-based ELMo embeddings for these languages on the part-of-speech tagging and parsing tasks. We show that, despite the noise in the Common-Crawl-based OSCAR data, embeddings trained on OSCAR perform much better than monolingual embeddings trained on Wikipedia. They actually equal or improve the current state of the art in tagging and parsing for all five languages. In particular, they also improve over multilingual Wikipedia-based contextual embeddings (multilingual BERT), which almost always constitutes the previous state of the art, thereby showing that the benefit of a larger, more diverse corpus surpasses the cross-lingual benefit of multilingual embedding architectures."", +} + +@inproceedings{OrtizSuarezSagotRomary2019, + author = {Pedro Javier {Ortiz Su{'a}rez} and Benoit Sagot and Laurent Romary}, + title = {Asynchronous pipelines for processing huge corpora on medium to low resource infrastructures}, + series = {Proceedings of the Workshop on Challenges in the Management of Large Corpora (CMLC-7) 2019. Cardiff, 22nd July 2019}, + editor = {Piotr BaÅ„ski and Adrien Barbaresi and Hanno Biber and Evelyn Breiteneder and Simon Clematide and Marc Kupietz and Harald L{""u}ngen and Caroline Iliadi}, + publisher = {Leibniz-Institut f{""u}r Deutsche Sprache}, + address = {Mannheim}, + doi = {10.14618/ids-pub-9021}, + url = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-90215}, + pages = {9 -- 16}, + year = {2019}, + abstract = {Common Crawl is a considerably large, heterogeneous multilingual corpus comprised of crawled documents from the internet, surpassing 20TB of data and distributed as a set of more than 50 thousand plain text files where each contains many documents written in a wide variety of languages. Even though each document has a metadata block associated to it, this data lacks any information about the language in which each document is written, making it extremely difficult to use Common Crawl for monolingual applications. We propose a general, highly parallel, multithreaded pipeline to clean and classify Common Crawl by language; we specifically design it so that it runs efficiently on medium to low resource infrastructures where I/O speeds are the main constraint. We develop the pipeline so that it can be easily reapplied to any kind of heterogeneous corpus and so that it can be parameterised to a wide range of infrastructures. We also distribute a 6.3TB version of Common Crawl, filtered, classified by language, shuffled at line level in order to avoid copyright issues, and ready to be used for NLP applications.}, + language = {en} +} + +``` + +### Contributions + +Thanks to [@pjox](https://github.com/pjox) and [@lhoestq](https://github.com/lhoestq) for adding this dataset." +Davlan/sib200,"{""annotations_creators"": [""found""], ""language_creators"": [""expert-generated""], ""language"": [""ace"", ""acm"", ""acq"", ""aeb"", ""af"", ""ajp"", ""ak"", ""als"", ""am"", ""apc"", ""ar"", ""ars"", ""ary"", ""arz"", ""as"", ""ast"", ""awa"", ""ayr"", ""azb"", ""azj"", ""ba"", ""bm"", ""ban"", ""be"", ""bem"", ""bn"", ""bho"", ""bjn"", ""bo"", ""bs"", ""bug"", ""bg"", ""ca"", ""ceb"", ""cs"", ""cjk"", ""ckb"", ""crh"", ""cy"", ""da"", ""de"", ""dik"", ""dyu"", ""dz"", ""el"", ""en"", ""eo"", ""et"", ""eu"", ""ee"", ""fo"", ""fj"", ""fi"", ""fon"", ""fr"", ""fur"", ""fuv"", ""gaz"", ""gd"", ""ga"", ""gl"", ""gn"", ""gu"", ""ht"", ""ha"", ""he"", ""hi"", ""hne"", ""hr"", ""hu"", ""hy"", ""ig"", ""ilo"", ""id"", ""is"", ""it"", ""jv"", ""ja"", ""kab"", ""kac"", ""kam"", ""kn"", ""ks"", ""ka"", ""kk"", ""kbp"", ""kea"", ""khk"", ""km"", ""ki"", ""rw"", ""ky"", ""kmb"", ""kmr"", ""knc"", ""kg"", ""ko"", ""lo"", ""lij"", ""li"", ""ln"", ""lt"", ""lmo"", ""ltg"", ""lb"", ""lua"", ""lg"", ""luo"", ""lus"", ""lvs"", ""mag"", ""mai"", ""ml"", ""mar"", ""min"", ""mk"", ""mt"", ""mni"", ""mos"", ""mi"", ""my"", ""nl"", ""nn"", ""nb"", ""npi"", ""nqo"", ""nso"", ""nus"", ""ny"", ""oc"", ""ory"", ""pag"", ""pa"", ""pap"", ""pbt"", ""pes"", ""plt"", ""pl"", ""pt"", ""prs"", ""quy"", ""ro"", ""rn"", ""ru"", ""sg"", ""sa"", ""sat"", ""scn"", ""shn"", ""si"", ""sk"", ""sl"", ""sm"", ""sn"", ""sd"", ""so"", ""st"", ""es"", ""sc"", ""sr"", ""ss"", ""su"", ""sv"", ""swh"", ""szl"", ""ta"", ""taq"", ""tt"", ""te"", ""tg"", ""tl"", ""th"", ""ti"", ""tpi"", ""tn"", ""ts"", ""tk"", ""tum"", ""tr"", ""tw"", ""tzm"", ""ug"", ""uk"", ""umb"", ""ur"", ""uzn"", ""vec"", ""vi"", ""war"", ""wo"", ""xh"", ""ydd"", ""yo"", ""yue"", ""zh"", ""zsm"", ""zu""], ""license"": [""cc-by-sa-4.0""], ""multilinguality"": [""multilingual""], ""pretty_name"": ""sib200"", ""language_details"": ""ace_Arab, ace_Latn, acm_Arab, acq_Arab, aeb_Arab, afr_Latn, ajp_Arab, aka_Latn, amh_Ethi, apc_Arab, arb_Arab, ars_Arab, ary_Arab, arz_Arab, asm_Beng, ast_Latn, awa_Deva, ayr_Latn, azb_Arab, azj_Latn, bak_Cyrl, bam_Latn, ban_Latn,bel_Cyrl, bem_Latn, ben_Beng, bho_Deva, bjn_Arab, bjn_Latn, bod_Tibt, bos_Latn, bug_Latn, bul_Cyrl, cat_Latn, ceb_Latn, ces_Latn, cjk_Latn, ckb_Arab, crh_Latn, cym_Latn, dan_Latn, deu_Latn, dik_Latn, dyu_Latn, dzo_Tibt, ell_Grek, eng_Latn, epo_Latn, est_Latn, eus_Latn, ewe_Latn, fao_Latn, pes_Arab, fij_Latn, fin_Latn, fon_Latn, fra_Latn, fur_Latn, fuv_Latn, gla_Latn, gle_Latn, glg_Latn, grn_Latn, guj_Gujr, hat_Latn, hau_Latn, heb_Hebr, hin_Deva, hne_Deva, hrv_Latn, hun_Latn, hye_Armn, ibo_Latn, ilo_Latn, ind_Latn, isl_Latn, ita_Latn, jav_Latn, jpn_Jpan, kab_Latn, kac_Latn, kam_Latn, kan_Knda, kas_Arab, kas_Deva, kat_Geor, knc_Arab, knc_Latn, kaz_Cyrl, kbp_Latn, kea_Latn, khm_Khmr, kik_Latn, kin_Latn, kir_Cyrl, kmb_Latn, kon_Latn, kor_Hang, kmr_Latn, lao_Laoo, lvs_Latn, lij_Latn, lim_Latn, lin_Latn, lit_Latn, lmo_Latn, ltg_Latn, ltz_Latn, lua_Latn, lug_Latn, luo_Latn, lus_Latn, mag_Deva, mai_Deva, mal_Mlym, mar_Deva, min_Latn, mkd_Cyrl, plt_Latn, mlt_Latn, mni_Beng, khk_Cyrl, mos_Latn, mri_Latn, zsm_Latn, mya_Mymr, nld_Latn, nno_Latn, nob_Latn, npi_Deva, nso_Latn, nus_Latn, nya_Latn, oci_Latn, gaz_Latn, ory_Orya, pag_Latn, pan_Guru, pap_Latn, pol_Latn, por_Latn, prs_Arab, pbt_Arab, quy_Latn, ron_Latn, run_Latn, rus_Cyrl, sag_Latn, san_Deva, sat_Beng, scn_Latn, shn_Mymr, sin_Sinh, slk_Latn, slv_Latn, smo_Latn, sna_Latn, snd_Arab, som_Latn, sot_Latn, spa_Latn, als_Latn, srd_Latn, srp_Cyrl, ssw_Latn, sun_Latn, swe_Latn, swh_Latn, szl_Latn, tam_Taml, tat_Cyrl, tel_Telu, tgk_Cyrl, tgl_Latn, tha_Thai, tir_Ethi, taq_Latn, taq_Tfng, tpi_Latn, tsn_Latn, tso_Latn, tuk_Latn, tum_Latn, tur_Latn, twi_Latn, tzm_Tfng, uig_Arab, ukr_Cyrl, umb_Latn, urd_Arab, uzn_Latn, vec_Latn, vie_Latn, war_Latn, wol_Latn, xho_Latn, ydd_Hebr, yor_Latn, yue_Hant, zho_Hans, zho_Hant, zul_Latn"", ""size_categories"": [""1K + + + +## Dataset Structure + +### Data Instances +``` +>>> from datasets import load_dataset +>>> data = load_dataset('aiana94/polynews-parallel', 'eng_Latn-ron_Latn') + +# Please, specify the language code, + +# A data point example is below: + +{ +""src"": ""They continue to support the view that this decision will have a lasting negative impact on the rule of law in the country. "", +""tgt"": ""Ei continuă să creadă că această decizie va avea efecte negative pe termen lung asupra statului de drept în țară. "", +""provenance"": ""globalvoices"" +} + +``` + +### Data Fields + +- src (string): source news text +- tgt (string): target news text +- provenance (string) : source dataset for the news example + +### Data Splits + +For all languages, there is only the `train` split. + + +## Dataset Creation + +### Curation Rationale + +Multiple multilingual, human-translated, datasets containing news texts have been released in recent years. +However, these datasets are stored in different formats and various websites, and many contain numerous near duplicates. +With PolyNewsParallel, we aim to provide an easily-accessible, unified and deduplicated parallel dataset that combines these disparate data sources. +It can be used for machine translation or text retrieval in both high-resource and low-resource languages. + +### Source Data + +The source data consists of five multilingual news datasets. + +- [GlobalVoices](https://opus.nlpl.eu/GlobalVoices/corpus/version/GlobalVoices) (v2018q4) +- [WMT-News](https://opus.nlpl.eu/WMT-News/corpus/version/WMT-News) (v2019) +- [MAFAND](https://huggingface.co/datasets/masakhane/mafand) (`train` split) + +#### Data Collection and Processing + +We processed the data using a **working script** which covers the entire processing pipeline. It can be found [here](https://github.com/andreeaiana/nase/blob/main/scripts/construct_polynews.sh). + +The data processing pipeline consists of: +1. Downloading the WMT-News and GlobalVoices News from OPUS. +2. Loading MAFAND datasets from Hugging Face Hub (only the `train` splits). +4. Concatenating, per language, all news texts from the source datasets. +5. Data cleaning (e.g., removal of exact duplicates, short texts, texts in other scripts) +6. [MinHash near-deduplication](https://github.com/bigcode-project/bigcode-dataset/blob/main/near_deduplication/minhash_deduplication.py) per language. + + +### Annotations + +We augment the original samples with the `provenance` annotation which specifies the original data source from which a particular examples stems. + + +#### Personal and Sensitive Information + +The data is sourced from newspaper sources and contains mentions of public figures and individuals. + + +## Considerations for Using the Data + +### Social Impact of Dataset +[More Information Needed] + + +### Discussion of Biases +[More Information Needed] + + +### Other Known Limitations + +Users should keep in mind that the dataset contains short news texts (e.g., mostly titles), which might limit the applicability of the developed systems to other domains. + + +## Additional Information + +### Licensing Information +The dataset is released under the [CC BY-NC Attribution-NonCommercial 4.0 International license](https://creativecommons.org/licenses/by-nc/4.0/). + +### Citation Infomation + +**BibTeX:** + +```bibtex +@misc{iana2024news, + title={News Without Borders: Domain Adaptation of Multilingual Sentence Embeddings for Cross-lingual News Recommendation}, + author={Andreea Iana and Fabian David Schmidt and Goran Glavaš and Heiko Paulheim}, + year={2024}, + eprint={2406.12634}, + archivePrefix={arXiv}, + url={https://arxiv.org/abs/2406.12634} +} +```" +OpenAssistant/oasst1,"{""license"": ""apache-2.0"", ""dataset_info"": {""features"": [{""name"": ""message_id"", ""dtype"": ""string""}, {""name"": ""parent_id"", ""dtype"": ""string""}, {""name"": ""user_id"", ""dtype"": ""string""}, {""name"": ""created_date"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""role"", ""dtype"": ""string""}, {""name"": ""lang"", ""dtype"": ""string""}, {""name"": ""review_count"", ""dtype"": ""int32""}, {""name"": ""review_result"", ""dtype"": ""bool""}, {""name"": ""deleted"", ""dtype"": ""bool""}, {""name"": ""rank"", ""dtype"": ""int32""}, {""name"": ""synthetic"", ""dtype"": ""bool""}, {""name"": ""model_name"", ""dtype"": ""string""}, {""name"": ""detoxify"", ""struct"": [{""name"": ""toxicity"", ""dtype"": ""float64""}, {""name"": ""severe_toxicity"", ""dtype"": ""float64""}, {""name"": ""obscene"", ""dtype"": ""float64""}, {""name"": ""identity_attack"", ""dtype"": ""float64""}, {""name"": ""insult"", ""dtype"": ""float64""}, {""name"": ""threat"", ""dtype"": ""float64""}, {""name"": ""sexual_explicit"", ""dtype"": ""float64""}]}, {""name"": ""message_tree_id"", ""dtype"": ""string""}, {""name"": ""tree_state"", ""dtype"": ""string""}, {""name"": ""emojis"", ""sequence"": [{""name"": ""name"", ""dtype"": ""string""}, {""name"": ""count"", ""dtype"": ""int32""}]}, {""name"": ""labels"", ""sequence"": [{""name"": ""name"", ""dtype"": ""string""}, {""name"": ""value"", ""dtype"": ""float64""}, {""name"": ""count"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 100367999, ""num_examples"": 84437}, {""name"": ""validation"", ""num_bytes"": 5243405, ""num_examples"": 4401}], ""download_size"": 41596430, ""dataset_size"": 105611404}, ""language"": [""en"", ""es"", ""ru"", ""de"", ""pl"", ""th"", ""vi"", ""sv"", ""bn"", ""da"", ""he"", ""it"", ""fa"", ""sk"", ""id"", ""nb"", ""el"", ""nl"", ""hu"", ""eu"", ""zh"", ""eo"", ""ja"", ""ca"", ""cs"", ""bg"", ""fi"", ""pt"", ""tr"", ""ro"", ""ar"", ""uk"", ""gl"", ""fr"", ""ko""], ""tags"": [""human-feedback""], ""size_categories"": [""100K + Languages with under 1000 messages +
    +
  • Vietnamese: 952
    • +
  • Basque: 947
    • +
  • Polish: 886
    • +
  • Hungarian: 811
    • +
  • Arabic: 666
    • +
  • Dutch: 628
    • +
  • Swedish: 512
    • +
  • Turkish: 454
    • +
  • Finnish: 386
    • +
  • Czech: 372
    • +
  • Danish: 358
    • +
  • Galician: 339
    • +
  • Hebrew: 255
    • +
  • Romanian: 200
    • +
  • Norwegian Bokmål: 133
    • +
  • Indonesian: 115
    • +
  • Bulgarian: 95
    • +
  • Bengali: 82
    • +
  • Persian: 72
    • +
  • Greek: 66
    • +
  • Esperanto: 59
    • +
  • Slovak: 19
    • +
+ + +## Contact + +- Discord [Open Assistant Discord Server](https://ykilcher.com/open-assistant-discord) +- GitHub: [LAION-AI/Open-Assistant](https://github.com/LAION-AI/Open-Assistant) +- E-Mail: [open-assistant@laion.ai](mailto:open-assistant@laion.ai)" +uonlp/CulturaX,"{""configs"": [{""config_name"": ""af"", ""data_files"": ""af/*.parquet""}, {""config_name"": ""als"", ""data_files"": ""als/*.parquet""}, {""config_name"": ""am"", ""data_files"": ""am/*.parquet""}, {""config_name"": ""an"", ""data_files"": ""an/*.parquet""}, {""config_name"": ""ar"", ""data_files"": ""ar/*.parquet""}, {""config_name"": ""arz"", ""data_files"": ""arz/*.parquet""}, {""config_name"": ""as"", ""data_files"": ""as/*.parquet""}, {""config_name"": ""ast"", ""data_files"": ""ast/*.parquet""}, {""config_name"": ""av"", ""data_files"": ""av/*.parquet""}, {""config_name"": ""az"", ""data_files"": ""az/*.parquet""}, {""config_name"": ""azb"", ""data_files"": ""azb/*.parquet""}, {""config_name"": ""ba"", ""data_files"": ""ba/*.parquet""}, {""config_name"": ""bar"", ""data_files"": ""bar/*.parquet""}, {""config_name"": ""bcl"", ""data_files"": ""bcl/*.parquet""}, {""config_name"": ""be"", ""data_files"": ""be/*.parquet""}, {""config_name"": ""bg"", ""data_files"": ""bg/*.parquet""}, {""config_name"": ""bh"", ""data_files"": ""bh/*.parquet""}, {""config_name"": ""bn"", ""data_files"": ""bn/*.parquet""}, {""config_name"": ""bo"", ""data_files"": ""bo/*.parquet""}, {""config_name"": ""bpy"", ""data_files"": ""bpy/*.parquet""}, {""config_name"": ""br"", ""data_files"": ""br/*.parquet""}, {""config_name"": ""bs"", ""data_files"": ""bs/*.parquet""}, {""config_name"": ""bxr"", ""data_files"": ""bxr/*.parquet""}, {""config_name"": ""ca"", ""data_files"": ""ca/*.parquet""}, {""config_name"": ""cbk"", ""data_files"": ""cbk/*.parquet""}, {""config_name"": ""ce"", ""data_files"": ""ce/*.parquet""}, {""config_name"": ""ceb"", ""data_files"": ""ceb/*.parquet""}, {""config_name"": ""ckb"", ""data_files"": ""ckb/*.parquet""}, {""config_name"": ""cs"", ""data_files"": ""cs/*.parquet""}, {""config_name"": ""cv"", ""data_files"": ""cv/*.parquet""}, {""config_name"": ""cy"", ""data_files"": ""cy/*.parquet""}, {""config_name"": ""da"", ""data_files"": ""da/*.parquet""}, {""config_name"": ""de"", ""data_files"": ""de/*.parquet""}, {""config_name"": ""dsb"", ""data_files"": ""dsb/*.parquet""}, {""config_name"": ""dv"", ""data_files"": ""dv/*.parquet""}, {""config_name"": ""el"", ""data_files"": ""el/*.parquet""}, {""config_name"": ""eml"", ""data_files"": ""eml/*.parquet""}, {""config_name"": ""en"", ""data_files"": ""en/*.parquet""}, {""config_name"": ""eo"", ""data_files"": ""eo/*.parquet""}, {""config_name"": ""es"", ""data_files"": ""es/*.parquet""}, {""config_name"": ""et"", ""data_files"": ""et/*.parquet""}, {""config_name"": ""eu"", ""data_files"": ""eu/*.parquet""}, {""config_name"": ""fa"", ""data_files"": ""fa/*.parquet""}, {""config_name"": ""fi"", ""data_files"": ""fi/*.parquet""}, {""config_name"": ""fr"", ""data_files"": ""fr/*.parquet""}, {""config_name"": ""frr"", ""data_files"": ""frr/*.parquet""}, {""config_name"": ""fy"", ""data_files"": ""fy/*.parquet""}, {""config_name"": ""ga"", ""data_files"": ""ga/*.parquet""}, {""config_name"": ""gd"", ""data_files"": ""gd/*.parquet""}, {""config_name"": ""gl"", ""data_files"": ""gl/*.parquet""}, {""config_name"": ""gn"", ""data_files"": ""gn/*.parquet""}, {""config_name"": ""gom"", ""data_files"": ""gom/*.parquet""}, {""config_name"": ""gu"", ""data_files"": ""gu/*.parquet""}, {""config_name"": ""he"", ""data_files"": ""he/*.parquet""}, {""config_name"": ""hi"", ""data_files"": ""hi/*.parquet""}, {""config_name"": ""hr"", ""data_files"": ""hr/*.parquet""}, {""config_name"": ""hsb"", ""data_files"": ""hsb/*.parquet""}, {""config_name"": ""ht"", ""data_files"": ""ht/*.parquet""}, {""config_name"": ""hu"", ""data_files"": ""hu/*.parquet""}, {""config_name"": ""hy"", ""data_files"": ""hy/*.parquet""}, {""config_name"": ""ia"", ""data_files"": ""ia/*.parquet""}, {""config_name"": ""id"", ""data_files"": ""id/*.parquet""}, {""config_name"": ""ie"", ""data_files"": ""ie/*.parquet""}, {""config_name"": ""ilo"", ""data_files"": ""ilo/*.parquet""}, {""config_name"": ""io"", ""data_files"": ""io/*.parquet""}, {""config_name"": ""is"", ""data_files"": ""is/*.parquet""}, {""config_name"": ""it"", ""data_files"": ""it/*.parquet""}, {""config_name"": ""ja"", ""data_files"": ""ja/*.parquet""}, {""config_name"": ""jbo"", ""data_files"": ""jbo/*.parquet""}, {""config_name"": ""jv"", ""data_files"": ""jv/*.parquet""}, {""config_name"": ""ka"", ""data_files"": ""ka/*.parquet""}, {""config_name"": ""kk"", ""data_files"": ""kk/*.parquet""}, {""config_name"": ""km"", ""data_files"": ""km/*.parquet""}, {""config_name"": ""kn"", ""data_files"": ""kn/*.parquet""}, {""config_name"": ""ko"", ""data_files"": ""ko/*.parquet""}, {""config_name"": ""krc"", ""data_files"": ""krc/*.parquet""}, {""config_name"": ""ku"", ""data_files"": ""ku/*.parquet""}, {""config_name"": ""kv"", ""data_files"": ""kv/*.parquet""}, {""config_name"": ""kw"", ""data_files"": ""kw/*.parquet""}, {""config_name"": ""ky"", ""data_files"": ""ky/*.parquet""}, {""config_name"": ""la"", ""data_files"": ""la/*.parquet""}, {""config_name"": ""lb"", ""data_files"": ""lb/*.parquet""}, {""config_name"": ""lez"", ""data_files"": ""lez/*.parquet""}, {""config_name"": ""li"", ""data_files"": ""li/*.parquet""}, {""config_name"": ""lmo"", ""data_files"": ""lmo/*.parquet""}, {""config_name"": ""lo"", ""data_files"": ""lo/*.parquet""}, {""config_name"": ""lrc"", ""data_files"": ""lrc/*.parquet""}, {""config_name"": ""lt"", ""data_files"": ""lt/*.parquet""}, {""config_name"": ""lv"", ""data_files"": ""lv/*.parquet""}, {""config_name"": ""mai"", ""data_files"": ""mai/*.parquet""}, {""config_name"": ""mg"", ""data_files"": ""mg/*.parquet""}, {""config_name"": ""mhr"", ""data_files"": ""mhr/*.parquet""}, {""config_name"": ""min"", ""data_files"": ""min/*.parquet""}, {""config_name"": ""mk"", ""data_files"": ""mk/*.parquet""}, {""config_name"": ""ml"", ""data_files"": ""ml/*.parquet""}, {""config_name"": ""mn"", ""data_files"": ""mn/*.parquet""}, {""config_name"": ""mr"", ""data_files"": ""mr/*.parquet""}, {""config_name"": ""mrj"", ""data_files"": ""mrj/*.parquet""}, {""config_name"": ""ms"", ""data_files"": ""ms/*.parquet""}, {""config_name"": ""mt"", ""data_files"": ""mt/*.parquet""}, {""config_name"": ""mwl"", ""data_files"": ""mwl/*.parquet""}, {""config_name"": ""my"", ""data_files"": ""my/*.parquet""}, {""config_name"": ""myv"", ""data_files"": ""myv/*.parquet""}, {""config_name"": ""mzn"", ""data_files"": ""mzn/*.parquet""}, {""config_name"": ""nah"", ""data_files"": ""nah/*.parquet""}, {""config_name"": ""nap"", ""data_files"": ""nap/*.parquet""}, {""config_name"": ""nds"", ""data_files"": ""nds/*.parquet""}, {""config_name"": ""ne"", ""data_files"": ""ne/*.parquet""}, {""config_name"": ""new"", ""data_files"": ""new/*.parquet""}, {""config_name"": ""nl"", ""data_files"": ""nl/*.parquet""}, {""config_name"": ""nn"", ""data_files"": ""nn/*.parquet""}, {""config_name"": ""no"", ""data_files"": ""no/*.parquet""}, {""config_name"": ""oc"", ""data_files"": ""oc/*.parquet""}, {""config_name"": ""or"", ""data_files"": ""or/*.parquet""}, {""config_name"": ""os"", ""data_files"": ""os/*.parquet""}, {""config_name"": ""pa"", ""data_files"": ""pa/*.parquet""}, {""config_name"": ""pam"", ""data_files"": ""pam/*.parquet""}, {""config_name"": ""pl"", ""data_files"": ""pl/*.parquet""}, {""config_name"": ""pms"", ""data_files"": ""pms/*.parquet""}, {""config_name"": ""pnb"", ""data_files"": ""pnb/*.parquet""}, {""config_name"": ""ps"", ""data_files"": ""ps/*.parquet""}, {""config_name"": ""pt"", ""data_files"": ""pt/*.parquet""}, {""config_name"": ""qu"", ""data_files"": ""qu/*.parquet""}, {""config_name"": ""rm"", ""data_files"": ""rm/*.parquet""}, {""config_name"": ""ro"", ""data_files"": ""ro/*.parquet""}, {""config_name"": ""ru"", ""data_files"": ""ru/*.parquet""}, {""config_name"": ""rue"", ""data_files"": ""rue/*.parquet""}, {""config_name"": ""sa"", ""data_files"": ""sa/*.parquet""}, {""config_name"": ""sah"", ""data_files"": ""sah/*.parquet""}, {""config_name"": ""scn"", ""data_files"": ""scn/*.parquet""}, {""config_name"": ""sd"", ""data_files"": ""sd/*.parquet""}, {""config_name"": ""sh"", ""data_files"": ""sh/*.parquet""}, {""config_name"": ""si"", ""data_files"": ""si/*.parquet""}, {""config_name"": ""sk"", ""data_files"": ""sk/*.parquet""}, {""config_name"": ""sl"", ""data_files"": ""sl/*.parquet""}, {""config_name"": ""so"", ""data_files"": ""so/*.parquet""}, {""config_name"": ""sq"", ""data_files"": ""sq/*.parquet""}, {""config_name"": ""sr"", ""data_files"": ""sr/*.parquet""}, {""config_name"": ""su"", ""data_files"": ""su/*.parquet""}, {""config_name"": ""sv"", ""data_files"": ""sv/*.parquet""}, {""config_name"": ""sw"", ""data_files"": ""sw/*.parquet""}, {""config_name"": ""ta"", ""data_files"": ""ta/*.parquet""}, {""config_name"": ""te"", ""data_files"": ""te/*.parquet""}, {""config_name"": ""tg"", ""data_files"": ""tg/*.parquet""}, {""config_name"": ""th"", ""data_files"": ""th/*.parquet""}, {""config_name"": ""tk"", ""data_files"": ""tk/*.parquet""}, {""config_name"": ""tl"", ""data_files"": ""tl/*.parquet""}, {""config_name"": ""tr"", ""data_files"": ""tr/*.parquet""}, {""config_name"": ""tt"", ""data_files"": ""tt/*.parquet""}, {""config_name"": ""tyv"", ""data_files"": ""tyv/*.parquet""}, {""config_name"": ""ug"", ""data_files"": ""ug/*.parquet""}, {""config_name"": ""uk"", ""data_files"": ""uk/*.parquet""}, {""config_name"": ""ur"", ""data_files"": ""ur/*.parquet""}, {""config_name"": ""uz"", ""data_files"": ""uz/*.parquet""}, {""config_name"": ""vec"", ""data_files"": ""vec/*.parquet""}, {""config_name"": ""vi"", ""data_files"": ""vi/*.parquet""}, {""config_name"": ""vls"", ""data_files"": ""vls/*.parquet""}, {""config_name"": ""vo"", ""data_files"": ""vo/*.parquet""}, {""config_name"": ""wa"", ""data_files"": ""wa/*.parquet""}, {""config_name"": ""war"", ""data_files"": ""war/*.parquet""}, {""config_name"": ""wuu"", ""data_files"": ""wuu/*.parquet""}, {""config_name"": ""xal"", ""data_files"": ""xal/*.parquet""}, {""config_name"": ""xmf"", ""data_files"": ""xmf/*.parquet""}, {""config_name"": ""yi"", ""data_files"": ""yi/*.parquet""}, {""config_name"": ""yo"", ""data_files"": ""yo/*.parquet""}, {""config_name"": ""yue"", ""data_files"": ""yue/*.parquet""}, {""config_name"": ""zh"", ""data_files"": ""zh/*.parquet""}], ""pretty_name"": ""CulturaX"", ""annotations_creators"": [""no-annotation""], ""language_creators"": [""found""], ""language"": [""af"", ""als"", ""am"", ""an"", ""ar"", ""arz"", ""as"", ""ast"", ""av"", ""az"", ""azb"", ""ba"", ""bar"", ""bcl"", ""be"", ""bg"", ""bh"", ""bn"", ""bo"", ""bpy"", ""br"", ""bs"", ""bxr"", ""ca"", ""cbk"", ""ce"", ""ceb"", ""ckb"", ""cs"", ""cv"", ""cy"", ""da"", ""de"", ""dsb"", ""dv"", ""el"", ""eml"", ""en"", ""eo"", ""es"", ""et"", ""eu"", ""fa"", ""fi"", ""fr"", ""frr"", ""fy"", ""ga"", ""gd"", ""gl"", ""gn"", ""gom"", ""gu"", ""he"", ""hi"", ""hr"", ""hsb"", ""ht"", ""hu"", ""hy"", ""ia"", ""id"", ""ie"", ""ilo"", ""io"", ""is"", ""it"", ""ja"", ""jbo"", ""jv"", ""ka"", ""kk"", ""km"", ""kn"", ""ko"", ""krc"", ""ku"", ""kv"", ""kw"", ""ky"", ""la"", ""lb"", ""lez"", ""li"", ""lmo"", ""lo"", ""lrc"", ""lt"", ""lv"", ""mai"", ""mg"", ""mhr"", ""min"", ""mk"", ""ml"", ""mn"", ""mr"", ""mrj"", ""ms"", ""mt"", ""mwl"", ""my"", ""myv"", ""mzn"", ""nah"", ""nap"", ""nds"", ""ne"", ""new"", ""nl"", ""nn"", ""no"", ""oc"", ""or"", ""os"", ""pa"", ""pam"", ""pl"", ""pms"", ""pnb"", ""ps"", ""pt"", ""qu"", ""rm"", ""ro"", ""ru"", ""rue"", ""sa"", ""sah"", ""scn"", ""sd"", ""sh"", ""si"", ""sk"", ""sl"", ""so"", ""sq"", ""sr"", ""su"", ""sv"", ""sw"", ""ta"", ""te"", ""tg"", ""th"", ""tk"", ""tl"", ""tr"", ""tt"", ""tyv"", ""ug"", ""uk"", ""ur"", ""uz"", ""vec"", ""vi"", ""vls"", ""vo"", ""wa"", ""war"", ""wuu"", ""xal"", ""xmf"", ""yi"", ""yo"", ""yue"", ""zh""], ""multilinguality"": [""multilingual""], ""size_categories"": [""n<1K"", ""1K +

CulturaX

+

Cleaned, Enormous, and Public: The Multilingual Fuel to Democratize Large Language Models for 167 Languages

+ + + + + +## Dataset Description + +- **Repository:** [https://github.com/nlp-uoregon/CulturaX](https://github.com/nlp-uoregon/CulturaX) +- **Papers:** [CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages](https://arxiv.org/abs/2309.09400) + + +## Dataset Summary + +We present CulturaX, a substantial multilingual dataset with 6.3 trillion tokens in 167 languages, tailored for large language model (LLM) development. Our dataset undergoes meticulous cleaning and deduplication through a rigorous pipeline of multiple stages to accomplish the best quality for model training, including language identification, URL-based filtering, metric-based cleaning, document refinement, and data deduplication. We employ MinHash at document level to achieve fuzzy deduplication for the datasets in different languages. Our data cleaning framework includes diverse criteria and threshold selections, guided by extensive data samples, ensuring comprehensive noise filtering in various aspects. CulturaX is fully released to the public in HuggingFace to facilitate research and advancements in multilingual LLMs. + +Our dataset combines the most recent iteration of mC4 (version 3.1.0) [1] with all accessible OSCAR corpora up to the present year, including 20.19, 21.09, 22.01, and 23.01 [2]. After deep cleaning and deduplication, CulturaX involves 16TB data in the parquet format (expanding to 27TB when unpacked). More than a half of our dataset is dedicated to non-English languages to significantly boost the data size and enhance the feasibility of training models in multilingual scenarios. + +To obtain perplexity scores for data cleaning, we train a SentencePiece tokenizer and 5-gram Kneser-Ney language models as provided in the KenLM library [3] using the 20230501 dumps of Wikipedia. Our KenLM models are also released in HuggingFace: https://huggingface.co/uonlp/kenlm. + +Details for the dataset can be found in our technical paper: [https://arxiv.org/abs/2309.09400](https://arxiv.org/abs/2309.09400) + + +You can download the dataset using Hugging Face datasets: + +*You may need to follow these instructions to setup authentication before downloading the dataset: [https://huggingface.co/docs/huggingface_hub/quick-start#login](https://huggingface.co/docs/huggingface_hub/quick-start#login)* + +```python +from datasets import load_dataset +ds = load_dataset(""uonlp/CulturaX"", + ""en"", + use_auth_token=True) +``` + + +### Languages + +The supported languages and statistics for our dataset can be found below: + +*(Note that the language code `als` and `eml` refer to `gsw` and `x-eml` in the OSCAR-2301 dataset.)* + + + +| | Code | Language | # Documents | # Tokens | # Tokens (%) | +|----:|:-------|:-------------------------|:----------------|:--------------------|:------| +| 0 | en | English | 3,241,065,682 | 2,846,970,578,793 | 45.13 | +| 1 | ru | Russian | 799,310,908 | 737,201,800,363 | 11.69 | +| 2 | es | Spanish | 450,937,645 | 373,845,662,394 | 5.93 | +| 3 | de | German | 420,017,484 | 357,030,348,021 | 5.66 | +| 4 | fr | French | 363,754,348 | 319,332,674,695 | 5.06 | +| 5 | zh | Chinese | 218,624,604 | 227,055,380,882 | 3.60 | +| 6 | it | Italian | 211,309,922 | 165,446,410,843 | 2.62 | +| 7 | pt | Portuguese | 190,289,658 | 136,941,763,923 | 2.17 | +| 8 | pl | Polish | 142,167,217 | 117,269,087,143 | 1.86 | +| 9 | ja | Japanese | 111,188,475 | 107,873,841,351 | 1.71 | +| 10 | nl | Dutch | 117,392,666 | 80,032,209,900 | 1.27 | +| 11 | ar | Arabic | 74,027,952 | 69,354,335,076 | 1.10 | +| 12 | tr | Turkish | 94,207,460 | 64,292,787,164 | 1.02 | +| 13 | cs | Czech | 65,350,564 | 56,910,486,745 | 0.90 | +| 14 | vi | Vietnamese | 57,606,341 | 55,380,123,774 | 0.88 | +| 15 | fa | Persian | 59,531,144 | 45,947,657,495 | 0.73 | +| 16 | hu | Hungarian | 44,132,152 | 43,417,981,714 | 0.69 | +| 17 | el | Greek | 51,430,226 | 43,147,590,757 | 0.68 | +| 18 | ro | Romanian | 40,325,424 | 39,647,954,768 | 0.63 | +| 19 | sv | Swedish | 49,709,189 | 38,486,181,494 | 0.61 | +| 20 | uk | Ukrainian | 44,740,545 | 38,226,128,686 | 0.61 | +| 21 | fi | Finnish | 30,467,667 | 28,925,009,180 | 0.46 | +| 22 | ko | Korean | 20,557,310 | 24,765,448,392 | 0.39 | +| 23 | da | Danish | 25,429,808 | 22,921,651,314 | 0.36 | +| 24 | bg | Bulgarian | 24,131,819 | 22,917,954,776 | 0.36 | +| 25 | no | Norwegian | 18,907,310 | 18,426,628,868 | 0.29 | +| 26 | hi | Hindi | 19,665,355 | 16,791,362,871 | 0.27 | +| 27 | sk | Slovak | 18,582,517 | 16,442,669,076 | 0.26 | +| 28 | th | Thai | 20,960,550 | 15,717,374,014 | 0.25 | +| 29 | lt | Lithuanian | 13,339,785 | 14,247,110,836 | 0.23 | +| 30 | ca | Catalan | 15,531,777 | 12,530,288,006 | 0.20 | +| 31 | id | Indonesian | 23,251,368 | 12,062,966,061 | 0.19 | +| 32 | bn | Bangla | 12,436,596 | 9,572,929,804 | 0.15 | +| 33 | et | Estonian | 8,004,753 | 8,805,656,165 | 0.14 | +| 34 | sl | Slovenian | 7,335,378 | 8,007,587,522 | 0.13 | +| 35 | lv | Latvian | 7,136,587 | 7,845,180,319 | 0.12 | +| 36 | he | Hebrew | 4,653,979 | 4,937,152,096 | 0.08 | +| 37 | sr | Serbian | 4,053,166 | 4,619,482,725 | 0.07 | +| 38 | ta | Tamil | 4,728,460 | 4,378,078,610 | 0.07 | +| 39 | sq | Albanian | 5,205,579 | 3,648,893,215 | 0.06 | +| 40 | az | Azerbaijani | 5,084,505 | 3,513,351,967 | 0.06 | +| 41 | kk | Kazakh | 2,733,982 | 2,802,485,195 | 0.04 | +| 42 | ur | Urdu | 2,757,279 | 2,703,052,627 | 0.04 | +| 43 | ka | Georgian | 3,120,321 | 2,617,625,564 | 0.04 | +| 44 | hy | Armenian | 2,964,488 | 2,395,179,284 | 0.04 | +| 45 | is | Icelandic | 2,373,560 | 2,350,592,857 | 0.04 | +| 46 | ml | Malayalam | 2,693,052 | 2,100,556,809 | 0.03 | +| 47 | ne | Nepali | 3,124,040 | 2,061,601,961 | 0.03 | +| 48 | mk | Macedonian | 2,762,807 | 2,003,302,006 | 0.03 | +| 49 | mr | Marathi | 2,266,588 | 1,955,227,796 | 0.03 | +| 50 | mn | Mongolian | 1,928,828 | 1,850,667,656 | 0.03 | +| 51 | be | Belarusian | 1,643,486 | 1,791,473,041 | 0.03 | +| 52 | te | Telugu | 1,822,865 | 1,566,972,146 | 0.02 | +| 53 | gl | Galician | 1,785,963 | 1,382,539,693 | 0.02 | +| 54 | eu | Basque | 1,598,822 | 1,262,066,759 | 0.02 | +| 55 | kn | Kannada | 1,352,142 | 1,242,285,201 | 0.02 | +| 56 | gu | Gujarati | 1,162,878 | 1,131,730,537 | 0.02 | +| 57 | af | Afrikaans | 826,519 | 1,119,009,767 | 0.02 | +| 58 | my | Burmese | 865,575 | 882,606,546 | 0.01 | +| 59 | si | Sinhala | 753,655 | 880,289,097 | 0.01 | +| 60 | eo | Esperanto | 460,088 | 803,948,528 | 0.01 | +| 61 | km | Khmer | 1,013,181 | 746,664,132 | 0.01 | +| 62 | pa | Punjabi | 646,987 | 727,546,145 | 0.01 | +| 63 | cy | Welsh | 549,955 | 576,743,162 | 0.01 | +| 64 | ky | Kyrgyz | 570,922 | 501,442,620 | 0.01 | +| 65 | ga | Irish | 304,251 | 376,947,935 | 0.01 | +| 66 | ps | Pashto | 376,914 | 363,007,770 | 0.01 | +| 67 | am | Amharic | 243,349 | 358,206,762 | 0.01 | +| 68 | ku | Kurdish | 295,314 | 302,990,910 | 0.00 | +| 69 | tl | Filipino | 348,453 | 242,086,456 | 0.00 | +| 70 | yi | Yiddish | 141,156 | 217,584,643 | 0.00 | +| 71 | lo | Lao | 217,842 | 168,256,876 | 0.00 | +| 72 | fy | Western Frisian | 223,268 | 167,193,111 | 0.00 | +| 73 | sd | Sindhi | 109,162 | 147,487,058 | 0.00 | +| 74 | mg | Malagasy | 115,910 | 142,685,412 | 0.00 | +| 75 | or | Odia | 153,461 | 100,323,213 | 0.00 | +| 76 | as | Assamese | 52,627 | 83,787,896 | 0.00 | +| 77 | ug | Uyghur | 47,035 | 77,677,306 | 0.00 | +| 78 | uz | Uzbek | 87,219 | 75,250,787 | 0.00 | +| 79 | la | Latin | 48,968 | 44,176,580 | 0.00 | +| 80 | hr | Croatian | 460,690 | 40,796,811 | 0.00 | +| 81 | sw | Swahili | 66,506 | 30,708,309 | 0.00 | +| 82 | ms | Malay | 238,151 | 19,375,976 | 0.00 | +| 83 | br | Breton | 43,765 | 13,987,037 | 0.00 | +| 84 | sa | Sanskrit | 16,290 | 13,561,367 | 0.00 | +| 85 | gd | Scottish Gaelic | 8,408 | 4,796,485 | 0.00 | +| 86 | su | Sundanese | 1,554 | 1,308,460 | 0.00 | +| 87 | jv | Javanese | 2,058 | 625,429 | 0.00 | +| 88 | tg | Tajik | 483,835 | - | - | +| 89 | ceb | Cebuano | 263,890 | - | - | +| 90 | tt | Tatar | 218,102 | - | - | +| 91 | ckb | Central Kurdish | 172,035 | - | - | +| 92 | lb | Luxembourgish | 165,891 | - | - | +| 93 | mt | Maltese | 151,320 | - | - | +| 94 | nn | Norwegian Nynorsk | 126,083 | - | - | +| 95 | qu | Quechua | 1,202 | 72,101 | 0.00 | +| 96 | ba | Bashkir | 71,957 | - | - | +| 97 | arz | Egyptian Arabic | 71,625 | - | - | +| 98 | dv | Divehi | 66,702 | - | - | +| 99 | bo | Tibetan | 54,185 | - | - | +| 100 | sh | Serbian (Latin) | 45,619 | - | - | +| 101 | yo | Yoruba | 192 | 42,943 | 0.00 | +| 102 | bs | Bosnian | 1,237 | 39,768 | 0.00 | +| 103 | azb | South Azerbaijani | 29,833 | - | - | +| 104 | ht | Haitian Creole | 12 | 26,183 | 0.00 | +| 105 | war | Waray | 23,687 | - | - | +| 106 | cv | Chuvash | 22,570 | - | - | +| 107 | sah | Sakha | 22,141 | - | - | +| 108 | li | Limburgish | 206 | 18,532 | 0.00 | +| 109 | ce | Chechen | 17,322 | - | - | +| 110 | pnb | Western Panjabi | 15,625 | - | - | +| 111 | nds | Low German | 15,139 | - | - | +| 112 | tk | Turkmen | 14,393 | - | - | +| 113 | gn | Guarani | 103 | 12,708 | 0.00 | +| 114 | oc | Occitan | 10,556 | - | - | +| 115 | xmf | Mingrelian | 9,706 | - | - | +| 116 | ast | Asturian | 9,002 | - | - | +| 117 | os | Ossetic | 8,596 | - | - | +| 118 | mhr | Eastern Mari | 7,883 | - | - | +| 119 | pms | Piedmontese | 7,566 | - | - | +| 120 | als[*] | Swiss German | 6,936 | - | - | +| 121 | vo | Volapük | 6,621 | - | - | +| 122 | so | Somali | 39 | 6,053 | 0.00 | +| 123 | bpy | Bishnupriya | 5,087 | - | - | +| 124 | new | Newari | 4,344 | - | - | +| 125 | hsb | Upper Sorbian | 4,244 | - | - | +| 126 | lmo | Lombard | 3,530 | - | - | +| 127 | an | Aragonese | 2,746 | - | - | +| 128 | ilo | Iloko | 2,328 | - | - | +| 129 | mzn | Mazanderani | 1,914 | - | - | +| 130 | lez | Lezghian | 1,806 | - | - | +| 131 | rm | Romansh | 30 | 1,769 | 0.00 | +| 132 | krc | Karachay-Balkar | 1,745 | - | - | +| 133 | min | Minangkabau | 1,429 | - | - | +| 134 | kv | Komi | 1,396 | - | - | +| 135 | wa | Walloon | 1,383 | - | - | +| 136 | jbo | Lojban | 1,349 | - | - | +| 137 | io | Ido | 1,144 | - | - | +| 138 | mrj | Western Mari | 1,056 | - | - | +| 139 | gom | Goan Konkani | 721 | - | - | +| 140 | ia | Interlingua | 613 | - | - | +| 141 | av | Avaric | 438 | - | - | +| 142 | bh | Bihari languages | 265 | - | - | +| 143 | wuu | Wu Chinese | 222 | - | - | +| 144 | nah | Nahuatl languages | 131 | - | - | +| 145 | vec | Venetian | 113 | - | - | +| 146 | bxr | Russia Buriat | 100 | - | - | +| 147 | kw | Cornish | 94 | - | - | +| 148 | mai | Maithili | 93 | - | - | +| 149 | eml[*] | Emiliano-Romagnol | 91 | - | - | +| 150 | dsb | Lower Sorbian | 59 | - | - | +| 151 | xal | Kalmyk | 51 | - | - | +| 152 | lrc | Northern Luri | 43 | - | - | +| 153 | nap | Neapolitan | 31 | - | - | +| 154 | tyv | Tuvinian | 23 | - | - | +| 155 | scn | Sicilian | 21 | - | - | +| 156 | frr | Northern Frisian | 11 | - | - | +| 157 | mwl | Mirandese | 9 | - | - | +| 158 | myv | Erzya | 4 | - | - | +| 159 | ie | Interlingue | 4 | - | - | +| 160 | pam | Pampanga | 4 | - | - | +| 161 | bar | Bavarian | 3 | - | - | +| 162 | yue | Yue Chinese | 3 | - | - | +| 163 | cbk | Chavacano | 2 | - | - | +| 164 | bcl | Central Bikol | 1 | - | - | +| 165 | vls | West Flemish | 1 | - | - | +| 166 | rue | Rusyn | 1 | - | - | + + + + +### Dataset Structure + +```json +{ + ""text"": ..., + ""timestamp"": ..., + ""url"": ..., + ""source"": ""mc4"" | ""OSCAR-xxxx"", +} +``` + + + +## Considerations for Using the Data + +As CulturaX is the cleaned version of the mC4 and OSCAR datasets, which were both extracted from CommonCrawl, personal and sensitive information might still contain personal and sensitive information. +This must be considered prior to using this dataset for any purpose, such as training deep learning models, etc. + + +## License Information + +The licence terms for CulturaX strictly follows those of `mC4` and `OSCAR`. Please refer to both below licenses when using this dataset. + +- [mC4 license](https://huggingface.co/datasets/allenai/c4#license) +- [OSCAR license](https://huggingface.co/datasets/oscar-corpus/OSCAR-2301#licensing-information) + + +## Acknowledgements + +We would like to extend our sincere thanks to Google Cloud for providing the TPU resources that made this project possible. Their support has been invaluable in enabling our team to run evaluations on our dataset efficiently. + + + +## Citation + +To cite CulturaX, please use: + +``` +@inproceedings{nguyen-etal-2024-culturax, + title = ""{C}ultura{X}: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages"", + author = ""Nguyen, Thuat and + Nguyen, Chien Van and + Lai, Viet Dac and + Man, Hieu and + Ngo, Nghia Trung and + Dernoncourt, Franck and + Rossi, Ryan A. and + Nguyen, Thien Huu"", + editor = ""Calzolari, Nicoletta and + Kan, Min-Yen and + Hoste, Veronique and + Lenci, Alessandro and + Sakti, Sakriani and + Xue, Nianwen"", + booktitle = ""Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)"", + month = may, + year = ""2024"", + address = ""Torino, Italia"", + publisher = ""ELRA and ICCL"", + url = ""https://aclanthology.org/2024.lrec-main.377"", + pages = ""4226--4237"", + abstract = ""Extensive training datasets represent one of the important factors for the impressive learning capabilities of large language models (LLMs). However, these training datasets for current LLMs, especially the recent state-of-the-art models, are often not fully disclosed. Creating training data for high-performing LLMs involves extensive cleaning and deduplication to ensure the necessary level of quality. The lack of transparency for training data has thus hampered research on attributing and addressing hallucination and bias issues in LLMs, hindering replication efforts and further advancements in the community. These challenges become even more pronounced in multilingual learning scenarios, where the available multilingual text datasets are often inadequately collected and cleaned. Consequently, there is a lack of open-source and readily usable dataset to effectively train LLMs in multiple languages. To overcome this issue, we present CulturaX, a substantial multilingual dataset with 6.3 trillion tokens in 167 languages, tailored for LLM development. Our dataset undergoes meticulous cleaning and deduplication through a rigorous pipeline of multiple stages to accomplish the best quality for model training, including language identification, URL-based filtering, metric-based cleaning, document refinement, and data deduplication. CulturaX is released in Hugging Face facilitate research and advancements in multilingual LLMs: https://huggingface.co/datasets/uonlp/CulturaX."", +} +``` + + +## Reference + +[1] Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, and Colin Raffel. 2021. mT5: A massively multilingual +pre-trained text-to-text transformer. In NAACL 2021. https://huggingface.co/datasets/mc4 + +[2] Pedro Javier Ortiz Suárez, Benoît Sagot, and Laurent Romary. 2019. Asynchronous pipelines for processing huge corpora on medium to low resource infrastructures. In Proceedings of the Workshop on Challenges in the Management of Large Corpora (CMLC- +7) 2019. https://oscar-project.org/ + +[3] KenLM: Faster and smaller language model queries. In Proceedings of the Sixth +Workshop on Statistical Machine Translation, 2011." +mozilla-foundation/common_voice_16_1,"{""pretty_name"": ""Common Voice Corpus 16.1"", ""annotations_creators"": [""crowdsourced""], ""language_creators"": [""crowdsourced""], ""language"": [""ab"", ""af"", ""am"", ""ar"", ""as"", ""ast"", ""az"", ""ba"", ""bas"", ""be"", ""bg"", ""bn"", ""br"", ""ca"", ""ckb"", ""cnh"", ""cs"", ""cv"", ""cy"", ""da"", ""de"", ""dv"", ""dyu"", ""el"", ""en"", ""eo"", ""es"", ""et"", ""eu"", ""fa"", ""fi"", ""fr"", ""fy"", ""ga"", ""gl"", ""gn"", ""ha"", ""he"", ""hi"", ""hsb"", ""hu"", ""hy"", ""ia"", ""id"", ""ig"", ""is"", ""it"", ""ja"", ""ka"", ""kab"", ""kk"", ""kmr"", ""ko"", ""ky"", ""lg"", ""lij"", ""lo"", ""lt"", ""ltg"", ""lv"", ""mdf"", ""mhr"", ""mk"", ""ml"", ""mn"", ""mr"", ""mrj"", ""mt"", ""myv"", ""nan"", ""ne"", ""nhi"", ""nl"", ""nn"", ""oc"", ""or"", ""os"", ""pa"", ""pl"", ""ps"", ""pt"", ""quy"", ""rm"", ""ro"", ""ru"", ""rw"", ""sah"", ""sat"", ""sc"", ""sk"", ""skr"", ""sl"", ""sq"", ""sr"", ""sv"", ""sw"", ""ta"", ""te"", ""th"", ""ti"", ""tig"", ""tk"", ""tok"", ""tr"", ""tt"", ""tw"", ""ug"", ""uk"", ""ur"", ""uz"", ""vi"", ""vot"", ""yi"", ""yo"", ""yue"", ""zgh"", ""zh""], ""language_bcp47"": [""zh-CN"", ""zh-HK"", ""zh-TW"", ""sv-SE"", ""rm-sursilv"", ""rm-vallader"", ""pa-IN"", ""nn-NO"", ""ne-NP"", ""nan-tw"", ""hy-AM"", ""ga-IE"", ""fy-NL""], ""license"": [""cc0-1.0""], ""multilinguality"": [""multilingual""], ""paperswithcode_id"": ""common-voice"", ""extra_gated_prompt"": ""By clicking on \u201cAccess repository\u201d below, you also agree to not attempt to determine the identity of speakers in the Common Voice dataset.""}","# Dataset Card for Common Voice Corpus 16 + +## Table of Contents +- [Dataset Description](#dataset-description) + - [Dataset Summary](#dataset-summary) + - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) + - [Languages](#languages) +- [Dataset Structure](#dataset-structure) + - [Data Instances](#data-instances) + - [Data Fields](#data-fields) + - [Data Splits](#data-splits) +- [Dataset Creation](#dataset-creation) + - [Curation Rationale](#curation-rationale) + - [Source Data](#source-data) + - [Annotations](#annotations) + - [Personal and Sensitive Information](#personal-and-sensitive-information) +- [Considerations for Using the Data](#considerations-for-using-the-data) + - [Social Impact of Dataset](#social-impact-of-dataset) + - [Discussion of Biases](#discussion-of-biases) + - [Other Known Limitations](#other-known-limitations) +- [Additional Information](#additional-information) + - [Dataset Curators](#dataset-curators) + - [Licensing Information](#licensing-information) + - [Citation Information](#citation-information) + - [Contributions](#contributions) + +## Dataset Description + +- **Homepage:** https://commonvoice.mozilla.org/en/datasets +- **Repository:** https://github.com/common-voice/common-voice +- **Paper:** https://arxiv.org/abs/1912.06670 +- **Leaderboard:** https://paperswithcode.com/dataset/common-voice +- **Point of Contact:** [Vaibhav Srivastav](mailto:vaibhav@huggingface.co) + +### Dataset Summary + +The Common Voice dataset consists of a unique MP3 and corresponding text file. +Many of the 30328 recorded hours in the dataset also include demographic metadata like age, sex, and accent +that can help improve the accuracy of speech recognition engines. + +The dataset currently consists of 19673 validated hours in 120 languages, but more voices and languages are always added. +Take a look at the [Languages](https://commonvoice.mozilla.org/en/languages) page to request a language or start contributing. + +### Languages + +``` +Abkhaz, Afrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Asturian, Azerbaijani, Basaa, Bashkir, Basque, Belarusian, Bengali, Breton, Bulgarian, Cantonese, Catalan, Central Kurdish, Chinese (China), Chinese (Hong Kong), Chinese (Taiwan), Chuvash, Czech, Danish, Dhivehi, Dioula, Dutch, English, Erzya, Esperanto, Estonian, Finnish, French, Frisian, Galician, Georgian, German, Greek, Guarani, Hakha Chin, Hausa, Hebrew, Hill Mari, Hindi, Hungarian, Icelandic, Igbo, Indonesian, Interlingua, Irish, Italian, Japanese, Kabyle, Kazakh, Kinyarwanda, Korean, Kurmanji Kurdish, Kyrgyz, Lao, Latgalian, Latvian, Ligurian, Lithuanian, Luganda, Macedonian, Malayalam, Maltese, Marathi, Meadow Mari, Moksha, Mongolian, Nepali, Norwegian Nynorsk, Occitan, Odia, Ossetian, Pashto, Persian, Polish, Portuguese, Punjabi, Quechua Chanka, Romanian, Romansh Sursilvan, Romansh Vallader, Russian, Sakha, Santali (Ol Chiki), Saraiki, Sardinian, Serbian, Slovak, Slovenian, Sorbian, Upper, Spanish, Swahili, Swedish, Taiwanese (Minnan), Tamazight, Tamil, Tatar, Telugu, Thai, Tigre, Tigrinya, Toki Pona, Turkish, Turkmen, Twi, Ukrainian, Urdu, Uyghur, Uzbek, Vietnamese, Votic, Welsh, Western Sierra Puebla Nahuatl, Yiddish, Yoruba +``` + +## How to use + +The `datasets` library allows you to load and pre-process your dataset in pure Python, at scale. The dataset can be downloaded and prepared in one call to your local drive by using the `load_dataset` function. + +For example, to download the Hindi config, simply specify the corresponding language config name (i.e., ""hi"" for Hindi): +```python +from datasets import load_dataset + +cv_16 = load_dataset(""mozilla-foundation/common_voice_16_1"", ""hi"", split=""train"") +``` + +Using the datasets library, you can also stream the dataset on-the-fly by adding a `streaming=True` argument to the `load_dataset` function call. Loading a dataset in streaming mode loads individual samples of the dataset at a time, rather than downloading the entire dataset to disk. +```python +from datasets import load_dataset + +cv_16 = load_dataset(""mozilla-foundation/common_voice_16_1"", ""hi"", split=""train"", streaming=True) + +print(next(iter(cv_16))) +``` + +*Bonus*: create a [PyTorch dataloader](https://huggingface.co/docs/datasets/use_with_pytorch) directly with your own datasets (local/streamed). + +### Local + +```python +from datasets import load_dataset +from torch.utils.data.sampler import BatchSampler, RandomSampler + +cv_16 = load_dataset(""mozilla-foundation/common_voice_16_1"", ""hi"", split=""train"") + +batch_sampler = BatchSampler(RandomSampler(cv_16), batch_size=32, drop_last=False) +dataloader = DataLoader(cv_16, batch_sampler=batch_sampler) +``` + +### Streaming + +```python +from datasets import load_dataset +from torch.utils.data import DataLoader + +cv_16 = load_dataset(""mozilla-foundation/common_voice_16_1"", ""hi"", split=""train"") +dataloader = DataLoader(cv_16, batch_size=32) +``` + +To find out more about loading and preparing audio datasets, head over to [hf.co/blog/audio-datasets](https://huggingface.co/blog/audio-datasets). + +### Example scripts + +Train your own CTC or Seq2Seq Automatic Speech Recognition models on Common Voice 16 with `transformers` - [here](https://github.com/huggingface/transformers/tree/main/examples/pytorch/speech-recognition). + +## Dataset Structure + +### Data Instances + +A typical data point comprises the `path` to the audio file and its `sentence`. +Additional fields include `accent`, `age`, `client_id`, `up_votes`, `down_votes`, `gender`, `locale` and `segment`. + +```python +{ + 'client_id': 'd59478fbc1ee646a28a3c652a119379939123784d99131b865a89f8b21c81f69276c48bd574b81267d9d1a77b83b43e6d475a6cfc79c232ddbca946ae9c7afc5', + 'path': 'et/clips/common_voice_et_18318995.mp3', + 'audio': { + 'path': 'et/clips/common_voice_et_18318995.mp3', + 'array': array([-0.00048828, -0.00018311, -0.00137329, ..., 0.00079346, 0.00091553, 0.00085449], dtype=float32), + 'sampling_rate': 48000 + }, + 'sentence': 'Tasub kokku saada inimestega, keda tunned juba ammust ajast saati.', + 'up_votes': 2, + 'down_votes': 0, + 'age': 'twenties', + 'gender': 'male', + 'accent': '', + 'locale': 'et', + 'segment': '' +} +``` + +### Data Fields + +`client_id` (`string`): An id for which client (voice) made the recording + +`path` (`string`): The path to the audio file + +`audio` (`dict`): A dictionary containing the path to the downloaded audio file, the decoded audio array, and the sampling rate. Note that when accessing the audio column: `dataset[0][""audio""]` the audio file is automatically decoded and resampled to `dataset.features[""audio""].sampling_rate`. Decoding and resampling of a large number of audio files might take a significant amount of time. Thus it is important to first query the sample index before the `""audio""` column, *i.e.* `dataset[0][""audio""]` should **always** be preferred over `dataset[""audio""][0]`. + +`sentence` (`string`): The sentence the user was prompted to speak + +`up_votes` (`int64`): How many upvotes the audio file has received from reviewers + +`down_votes` (`int64`): How many downvotes the audio file has received from reviewers + +`age` (`string`): The age of the speaker (e.g. `teens`, `twenties`, `fifties`) + +`gender` (`string`): The gender of the speaker + +`accent` (`string`): Accent of the speaker + +`locale` (`string`): The locale of the speaker + +`segment` (`string`): Usually an empty field + +### Data Splits + +The speech material has been subdivided into portions for dev, train, test, validated, invalidated, reported and other. + +The validated data is data that has been validated with reviewers and received upvotes that the data is of high quality. + +The invalidated data is data has been invalidated by reviewers +and received downvotes indicating that the data is of low quality. + +The reported data is data that has been reported, for different reasons. + +The other data is data that has not yet been reviewed. + +The dev, test, train are all data that has been reviewed, deemed of high quality and split into dev, test and train. + +## Data Preprocessing Recommended by Hugging Face + +The following are data preprocessing steps advised by the Hugging Face team. They are accompanied by an example code snippet that shows how to put them to practice. + +Many examples in this dataset have trailing quotations marks, e.g _“the cat sat on the mat.“_. These trailing quotation marks do not change the actual meaning of the sentence, and it is near impossible to infer whether a sentence is a quotation or not a quotation from audio data alone. In these cases, it is advised to strip the quotation marks, leaving: _the cat sat on the mat_. + +In addition, the majority of training sentences end in punctuation ( . or ? or ! ), whereas just a small proportion do not. In the dev set, **almost all** sentences end in punctuation. Thus, it is recommended to append a full-stop ( . ) to the end of the small number of training examples that do not end in punctuation. + +```python +from datasets import load_dataset + +ds = load_dataset(""mozilla-foundation/common_voice_16_1"", ""en"", use_auth_token=True) + +def prepare_dataset(batch): + """"""Function to preprocess the dataset with the .map method"""""" + transcription = batch[""sentence""] + + if transcription.startswith('""') and transcription.endswith('""'): + # we can remove trailing quotation marks as they do not affect the transcription + transcription = transcription[1:-1] + + if transcription[-1] not in [""."", ""?"", ""!""]: + # append a full-stop to sentences that do not end in punctuation + transcription = transcription + ""."" + + batch[""sentence""] = transcription + + return batch + +ds = ds.map(prepare_dataset, desc=""preprocess dataset"") +``` + +## Dataset Creation + +### Curation Rationale + +[Needs More Information] + +### Source Data + +#### Initial Data Collection and Normalization + +[Needs More Information] + +#### Who are the source language producers? + +[Needs More Information] + +### Annotations + +#### Annotation process + +[Needs More Information] + +#### Who are the annotators? + +[Needs More Information] + +### Personal and Sensitive Information + +The dataset consists of people who have donated their voice online. You agree to not attempt to determine the identity of speakers in the Common Voice dataset. + +## Considerations for Using the Data + +### Social Impact of Dataset + +The dataset consists of people who have donated their voice online. You agree to not attempt to determine the identity of speakers in the Common Voice dataset. + +### Discussion of Biases + +[More Information Needed] + +### Other Known Limitations + +[More Information Needed] + +## Additional Information + +### Dataset Curators + +[More Information Needed] + +### Licensing Information + +Public Domain, [CC-0](https://creativecommons.org/share-your-work/public-domain/cc0/) + +### Citation Information + +``` +@inproceedings{commonvoice:2020, + author = {Ardila, R. and Branson, M. and Davis, K. and Henretty, M. and Kohler, M. and Meyer, J. and Morais, R. and Saunders, L. and Tyers, F. M. and Weber, G.}, + title = {Common Voice: A Massively-Multilingual Speech Corpus}, + booktitle = {Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)}, + pages = {4211--4215}, + year = 2020 +} +```" +KorQuAD/squad_kor_v1,"{""annotations_creators"": [""crowdsourced""], ""language_creators"": [""found""], ""language"": [""ko""], ""license"": [""cc-by-nd-4.0""], ""multilinguality"": [""monolingual""], ""size_categories"": [""10K +and identify the date. + +### 2. [Optional] Get a refreshed list of languages + +This is optional because it not very likely that a new language will have +suddenly appeared since the last version _and_ have a significant dataset. + +Navigate to and copy the +languages column from the ""Detailed list"" table (near the end of the page). + +Copy that content in the form of a Python list into `lang_def.py` (at the top +of the repo) under a new date. + +### 3. [Optional] Create Media and Category aliases + +In order to properly extract links to images and media in all languages, we +must refresh the two corresponding files. To do so, from the root of the repo, +run + +```sh +python -m prep.create_aliases +``` + +This will create or update these two files at the root of the repo: + +- `media_aliases.py` +- `category_aliases.py` + +These files are used in the final step + +### 4. Build and prepare the datasets into sharded parquet files + +Running this script downloads the wikipedia dumps for each language in +`lang_def.py` and shards each language dataset into the appropriate number of +shards (max size ~ 250MB). + +```sh +python -m prep.build --date 20230601 +``` + +There are other options: + +```text +$ python -m prep.build --help +usage: Wikipedia Builder [-h] [--date DATE] [--language [LANG ...]] [--cache-dir DIR] [--mirror MIRROR] + +Prepares the Wikipedia dataset for each language + +optional arguments: + -h, --help show this help message and exit + --date DATE Wikipedia dump date (e.g. 20230601) + --language [LANG ...] Language code (e.g. en). If missing, all languages are processed + --cache-dir DIR Cache directory for 🤗 Datasets + --mirror MIRROR Mirror URL +``` + +For instance, for faster downloads of the dumps, use the mirror option: + +```sh +python -m prep.build \ + --date 20230601 \ + --language bs \ + --mirror https://mirror.accum.se/mirror/wikimedia.org/dumps/ +``` + +It will download the dumps at around 60MB/s instead of the capped speed +(~4MB/s) from . The script will skip existing +directories, allowing you to run the script in several passes. + +Notes: + +- These instructions build upon the build process of the + [Wikipedia](https://huggingface.co/datasets/wikipedia) 🤗 Dataset. HF did a + fantastic job, I just pushed it a bit further. +- Be aware that not all mirrors contain all dumps. For instance mirror.accum.se + does not contain dumps for languages such as be-x-old or cbk-zam. My own + solution is to run a first pass using the aforementioned mirror, and a second + pass with the official `https://dumps.wikimedia.org` site (omitting the + `--mirror` parameter)." +amphion/Emilia-Dataset,"{""license"": ""cc-by-nc-4.0"", ""task_categories"": [""text-to-speech"", ""automatic-speech-recognition""], ""language"": [""zh"", ""en"", ""ja"", ""fr"", ""de"", ""ko""], ""pretty_name"": ""Emilia"", ""size_categories"": [""10M +This is the official repository 👑 for the **Emilia** dataset and the source code for the **Emilia-Pipe** speech data preprocessing pipeline. + +
+ +## News 🔥 +- **2024/08/28**: Welcome to join Amphion's [Discord channel](https://discord.com/invite/ZxxREr3Y) to stay connected and engage with our community! +- **2024/08/27**: *The Emilia dataset is now publicly available!* Discover the most extensive and diverse speech generation dataset with 101k hours of in-the-wild speech data now at [HuggingFace](https://huggingface.co/datasets/amphion/Emilia-Dataset) or [OpenDataLab](https://opendatalab.com/Amphion/Emilia)! 👑👑👑 +- **2024/07/08**: Our preprint [paper](https://arxiv.org/abs/2407.05361) is now available! 🔥🔥🔥 +- **2024/07/03**: We welcome everyone to check our [homepage](https://emilia-dataset.github.io/Emilia-Demo-Page/) for our brief introduction for Emilia dataset and our demos! +- **2024/07/01**: We release of Emilia and Emilia-Pipe! We welcome everyone to explore it on our [GitHub](https://github.com/open-mmlab/Amphion/tree/main/preprocessors/Emilia)! 🎉🎉🎉 + +## Emilia Overview ⭐️ +The **Emilia** dataset is a comprehensive, multilingual dataset with the following features: +- containing over *101k* hours of speech data; +- covering six different languages: *English (En), Chinese (Zh), German (De), French (Fr), Japanese (Ja), and Korean (Ko)*; +- containing diverse speech data with *various speaking styles* from diverse video platforms and podcasts on the Internet, covering various content genres such as talk shows, interviews, debates, sports commentary, and audiobooks. + +The table below provides the duration statistics for each language in the dataset. + +| Language | Duration (hours) | +|:-----------:|:----------------:| +| English | 46,828 | +| Chinese | 49,922 | +| German | 1,590 | +| French | 1,381 | +| Japanese | 1,715 | +| Korean | 217 | + + +The **Emilia-Pipe** is the first open-source preprocessing pipeline designed to transform raw, in-the-wild speech data into high-quality training data with annotations for speech generation. This pipeline can process one hour of raw audio into model-ready data in just a few minutes, requiring only the raw speech data. + +Detailed descriptions for the Emilia and Emilia-Pipe can be found in our [paper](https://arxiv.org/abs/2407.05361). + +## Emilia Dataset Usage 📖 +Emilia is publicly available at [HuggingFace](https://huggingface.co/datasets/amphion/Emilia-Dataset). + +If you are from mainland China or having a connecting issue with HuggingFace, you can also download Emilia from [OpenDataLab](https://opendatalab.com/Amphion/Emilia). + +- To download from HuggingFace: + + 1. Gain access to the dataset and get the HF access token from: [https://huggingface.co/settings/tokens](https://huggingface.co/settings/tokens). + 2. Install dependencies and login HF: + - Install Python + - Run `pip install librosa soundfile datasets huggingface_hub[cli]` + - Login by `huggingface-cli login` and paste the HF access token. Check [here](https://huggingface.co/docs/huggingface_hub/guides/cli#huggingface-cli-login) for details. + 3. Use following code to load Emilia: + ```py + from datasets import load_dataset + dataset = load_dataset(""amphion/Emilia-Dataset"", streaming=True) + print(dataset) + print(next(iter(dataset['train']))) + ``` + +- To download from OpenDataLab (i.e., OpenXLab), please follow the guidance [here](https://speechteam.feishu.cn/wiki/PC8Ew5igviqBiJkElMJcJxNonJc) to gain access. + +**ENJOY USING EMILIA!!!** 🔥 + +### Use cases + +If you want to load a subset of Emilia, e.g., only language `DE`, you can use the following code: + +```py +from datasets import load_dataset +path = ""DE/*.tar"" +dataset = load_dataset(""amphion/Emilia-Dataset"", data_files={""de"": path}, split=""de"", streaming=True) +print(dataset) # here should only shows 90 n_shards instead of 2360 +print(next(iter(dataset['train']))) +``` + +If you want to download all files to your local before using Emilia, remove the `streaming=True` argument: + +```py +from datasets import load_dataset +dataset = load_dataset(""amphion/Emilia-Dataset"") # prepare 2.4TB space to store Emilia +print(dataset) +``` + + +### Re-build or Processing your own data + +If you wish to re-build Emilia from scratch, you may download the raw audio files from the [provided URL list](https://huggingface.co/datasets/amphion/Emilia) and use our open-source [Emilia-Pipe](https://github.com/open-mmlab/Amphion/tree/main/preprocessors/Emilia) preprocessing pipeline to preprocess the raw data. Additionally, users can easily use Emilia-Pipe to preprocess their own raw speech data for custom needs. By open-sourcing the Emilia-Pipe code, we aim to enable the speech community to collaborate on large-scale speech generation research. + +### Notes + +*Please note that Emilia does not own the copyright to the audio files; the copyright remains with the original owners of the videos or audio. Users are permitted to use this dataset only for non-commercial purposes under the CC BY-NC-4.0 license.* + +## Emilia Dataset Structure ⛪️ + +### Structure on HuggingFace + +On HuggingFace, Emilia is now formatted as [WebDataset](https://github.com/webdataset/webdataset). + +Each audio is tared with a corresponding JSON file (having the same prefix filename) within 2360 tar files. + +By utilizing WebDataset, you can easily stream audio data, which is magnitude faster than reading separate data files one by one. + +Read the *Emilia Dataset Usage 📖* part for a detailed usage guide. + +Learn more about WebDataset [here](https://huggingface.co/docs/hub/datasets-webdataset). + +*PS: If you want to download the `OpenDataLab` format from HuggingFace, you can specify the `revision` argument to `fc71e07e8572f5f3be1dbd02ed3172a4d298f152`, [which](https://huggingface.co/datasets/amphion/Emilia-Dataset/tree/fc71e07e8572f5f3be1dbd02ed3172a4d298f152) is the old format.* + + +### Structure on OpenDataLab +On OpenDataLab, Emilia is formatted using the following structure. + +Structure example: +``` +|-- openemilia_all.tar.gz (all .JSONL files are gzipped with directory structure in this file) +|-- EN (114 batches) +| |-- EN_B00000.jsonl +| |-- EN_B00000 (= EN_B00000.tar.gz) +| | |-- EN_B00000_S00000 +| | | `-- mp3 +| | | |-- EN_B00000_S00000_W000000.mp3 +| | | `-- EN_B00000_S00000_W000001.mp3 +| | |-- ... +| |-- ... +| |-- EN_B00113.jsonl +| `-- EN_B00113 +|-- ZH (92 batches) +|-- DE (9 batches) +|-- FR (10 batches) +|-- JA (7 batches) +|-- KO (4 batches) + +``` + +JSONL files example: +``` +{""id"": ""EN_B00000_S00000_W000000"", ""wav"": ""EN_B00000/EN_B00000_S00000/mp3/EN_B00000_S00000_W000000.mp3"", ""text"": "" You can help my mother and you- No. You didn't leave a bad situation back home to get caught up in another one here. What happened to you, Los Angeles?"", ""duration"": 6.264, ""speaker"": ""EN_B00000_S00000"", ""language"": ""en"", ""dnsmos"": 3.2927} +{""id"": ""EN_B00000_S00000_W000001"", ""wav"": ""EN_B00000/EN_B00000_S00000/mp3/EN_B00000_S00000_W000001.mp3"", ""text"": "" Honda's gone, 20 squads done. X is gonna split us up and put us on different squads. The team's come and go, but 20 squad, can't believe it's ending."", ""duration"": 8.031, ""speaker"": ""EN_B00000_S00000"", ""language"": ""en"", ""dnsmos"": 3.0442} +``` + + +## Reference 📖 +If you use the Emilia dataset or the Emilia-Pipe pipeline, please cite the following papers: +```bibtex +@inproceedings{emilia, + author={He, Haorui and Shang, Zengqiang and Wang, Chaoren and Li, Xuyuan and Gu, Yicheng and Hua, Hua and Liu, Liwei and Yang, Chen and Li, Jiaqi and Shi, Peiyang and Wang, Yuancheng and Chen, Kai and Zhang, Pengyuan and Wu, Zhizheng}, + title={Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation}, + booktitle={Proc.~of SLT}, + year={2024} +} +``` +```bibtex +@inproceedings{amphion, + author={Zhang, Xueyao and Xue, Liumeng and Gu, Yicheng and Wang, Yuancheng and Li, Jiaqi and He, Haorui and Wang, Chaoren and Song, Ting and Chen, Xi and Fang, Zihao and Chen, Haopeng and Zhang, Junan and Tang, Tze Ying and Zou, Lexiao and Wang, Mingxuan and Han, Jun and Chen, Kai and Li, Haizhou and Wu, Zhizheng}, + title={Amphion: An Open-Source Audio, Music and Speech Generation Toolkit}, + booktitle={Proc.~of SLT}, + year={2024} +} +```" +miracl/miracl-corpus,"{""annotations_creators"": [""expert-generated""], ""language"": [""ar"", ""bn"", ""en"", ""es"", ""fa"", ""fi"", ""fr"", ""hi"", ""id"", ""ja"", ""ko"", ""ru"", ""sw"", ""te"", ""th"", ""zh""], ""multilinguality"": [""multilingual""], ""pretty_name"": ""MIRACL-corpus"", ""size_categories"": [], ""source_datasets"": [], ""tags"": [], ""task_categories"": [""text-retrieval""], ""license"": [""apache-2.0""], ""task_ids"": [""document-retrieval""]}","# Dataset Card for MIRACL Corpus + + +## Dataset Description +* **Homepage:** http://miracl.ai +* **Repository:** https://github.com/project-miracl/miracl +* **Paper:** https://arxiv.org/abs/2210.09984 + +MIRACL 🌍🙌🌏 (Multilingual Information Retrieval Across a Continuum of Languages) is a multilingual retrieval dataset that focuses on search across 18 different languages, which collectively encompass over three billion native speakers around the world. + +This dataset contains the collection data of the 16 ""known languages"". The remaining 2 ""surprise languages"" will not be released until later. + +The corpus for each language is prepared from a Wikipedia dump, where we keep only the plain text and discard images, tables, etc. Each article is segmented into multiple passages using WikiExtractor based on natural discourse units (e.g., `\n\n` in the wiki markup). Each of these passages comprises a ""document"" or unit of retrieval. We preserve the Wikipedia article title of each passage. + +## Dataset Structure +Each retrieval unit contains three fields: `docid`, `title`, and `text`. Consider an example from the English corpus: + +``` +{ + ""docid"": ""39#0"", + ""title"": ""Albedo"", + ""text"": ""Albedo (meaning 'whiteness') is the measure of the diffuse reflection of solar radiation out of the total solar radiation received by an astronomical body (e.g. a planet like Earth). It is dimensionless and measured on a scale from 0 (corresponding to a black body that absorbs all incident radiation) to 1 (corresponding to a body that reflects all incident radiation)."" +} +``` +The `docid` has the schema `X#Y`, where all passages with the same `X` come from the same Wikipedia article, whereas `Y` denotes the passage within that article, numbered sequentially. The text field contains the text of the passage. The title field contains the name of the article the passage comes from. + + +The collection can be loaded using: +``` +lang='ar' # or any of the 16 languages +miracl_corpus = datasets.load_dataset('miracl/miracl-corpus', lang)['train'] +for doc in miracl_corpus: + docid = doc['docid'] + title = doc['title'] + text = doc['text'] +``` + +## Dataset Statistics and Links +The following table contains the number of passage and Wikipedia articles in the collection of each language, along with the links to the datasets and raw Wikipedia dumps. +| Language | # of Passages | # of Articles | Links | Raw Wiki Dump | +|:----------------|--------------:|--------------:|:------|:------| +| Arabic (ar) | 2,061,414 | 656,982 | [🤗](https://huggingface.co/datasets/miracl/miracl-corpus/tree/main/miracl-corpus-v1.0-ar) | [🌏](https://archive.org/download/arwiki-20190201/arwiki-20190201-pages-articles-multistream.xml.bz2) +| Bengali (bn) | 297,265 | 63,762 | [🤗](https://huggingface.co/datasets/miracl/miracl-corpus/tree/main/miracl-corpus-v1.0-bn) | [🌏](https://archive.org/download/bnwiki-20190201/bnwiki-20190201-pages-articles-multistream.xml.bz2) +| English (en) | 32,893,221 | 5,758,285 | [🤗](https://huggingface.co/datasets/miracl/miracl-corpus/tree/main/miracl-corpus-v1.0-en) | [🌏](https://archive.org/download/enwiki-20190201/enwiki-20190201-pages-articles-multistream.xml.bz2) +| Spanish (es) | 10,373,953 | 1,669,181 | [🤗](https://huggingface.co/datasets/miracl/miracl-corpus/tree/main/miracl-corpus-v1.0-es) | [🌏](https://archive.org/download/eswiki-20220301/eswiki-20220301-pages-articles-multistream.xml.bz2) +| Persian (fa) | 2,207,172 | 857,827 | [🤗](https://huggingface.co/datasets/miracl/miracl-corpus/tree/main/miracl-corpus-v1.0-fa) | [🌏](https://archive.org/download/fawiki-20220301/fawiki-20220301-pages-articles-multistream.xml.bz2) +| Finnish (fi) | 1,883,509 | 447,815 | [🤗](https://huggingface.co/datasets/miracl/miracl-corpus/tree/main/miracl-corpus-v1.0-fi) | [🌏](https://archive.org/download/fiwiki-20190201/fiwiki-20190201-pages-articles-multistream.xml.bz2) +| French (fr) | 14,636,953 | 2,325,608 | [🤗](https://huggingface.co/datasets/miracl/miracl-corpus/tree/main/miracl-corpus-v1.0-fr) | [🌏](https://archive.org/download/frwiki-20220301/frwiki-20220301-pages-articles-multistream.xml.bz2) +| Hindi (hi) | 506,264 | 148,107 | [🤗](https://huggingface.co/datasets/miracl/miracl-corpus/tree/main/miracl-corpus-v1.0-hi) | [🌏](https://archive.org/download/hiwiki-20220301/hiwiki-20220301-pages-articles-multistream.xml.bz2) +| Indonesian (id) | 1,446,315 | 446,330 | [🤗](https://huggingface.co/datasets/miracl/miracl-corpus/tree/main/miracl-corpus-v1.0-id) | [🌏](https://archive.org/download/idwiki-20190201/idwiki-20190201-pages-articles-multistream.xml.bz2) +| Japanese (ja) | 6,953,614 | 1,133,444 | [🤗](https://huggingface.co/datasets/miracl/miracl-corpus/tree/main/miracl-corpus-v1.0-ja) | [🌏](https://archive.org/download/jawiki-20190201/jawiki-20190201-pages-articles-multistream.xml.bz2) +| Korean (ko) | 1,486,752 | 437,373 | [🤗](https://huggingface.co/datasets/miracl/miracl-corpus/tree/main/miracl-corpus-v1.0-ko) | [🌏](https://archive.org/download/kowiki-20190201/kowiki-20190201-pages-articles-multistream.xml.bz2) +| Russian (ru) | 9,543,918 | 1,476,045 | [🤗](https://huggingface.co/datasets/miracl/miracl-corpus/tree/main/miracl-corpus-v1.0-ru) | [🌏](https://archive.org/download/ruwiki-20190201/ruwiki-20190201-pages-articles-multistream.xml.bz2) +| Swahili (sw) | 131,924 | 47,793 | [🤗](https://huggingface.co/datasets/miracl/miracl-corpus/tree/main/miracl-corpus-v1.0-sw) | [🌏](https://archive.org/download/swwiki-20190201/swwiki-20190201-pages-articles-multistream.xml.bz2) +| Telugu (te) | 518,079 | 66,353 | [🤗](https://huggingface.co/datasets/miracl/miracl-corpus/tree/main/miracl-corpus-v1.0-te) | [🌏](https://archive.org/download/tewiki-20190201/tewiki-20190201-pages-articles-multistream.xml.bz2) +| Thai (th) | 542,166 | 128,179 | [🤗](https://huggingface.co/datasets/miracl/miracl-corpus/tree/main/miracl-corpus-v1.0-th) | [🌏](https://archive.org/download/thwiki-20190101/thwiki-20190101-pages-articles-multistream.xml.bz2) +| Chinese (zh) | 4,934,368 | 1,246,389 | [🤗](https://huggingface.co/datasets/miracl/miracl-corpus/tree/main/miracl-corpus-v1.0-zh) | [🌏](https://archive.org/download/zhwiki-20220301/zhwiki-20220301-pages-articles-multistream.xml.bz2)" +HPLT/HPLT2.0_cleaned,"{""configs"": [{""config_name"": ""ace_Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""ace_Arab*/train-*""}]}, {""config_name"": ""ace_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""ace_Latn*/train-*""}]}, {""config_name"": ""afr_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""afr_Latn*/train-*""}]}, {""config_name"": ""als_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""als_Latn*/train-*""}]}, {""config_name"": ""amh_Ethi"", ""data_files"": [{""split"": ""train"", ""path"": ""amh_Ethi*/train-*""}]}, {""config_name"": ""ara_Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""ara_Arab*/train-*""}]}, {""config_name"": ""asm_Beng"", ""data_files"": [{""split"": ""train"", ""path"": ""asm_Beng*/train-*""}]}, {""config_name"": ""ast_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""ast_Latn*/train-*""}]}, {""config_name"": ""awa_Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""awa_Deva*/train-*""}]}, {""config_name"": ""ayr_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""ayr_Latn*/train-*""}]}, {""config_name"": ""azb_Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""azb_Arab*/train-*""}]}, {""config_name"": ""azj_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""azj_Latn*/train-*""}]}, {""config_name"": ""bak_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""bak_Cyrl*/train-*""}]}, {""config_name"": ""ban_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""ban_Latn*/train-*""}]}, {""config_name"": ""bel_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""bel_Cyrl*/train-*""}]}, {""config_name"": ""bem_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""bem_Latn*/train-*""}]}, {""config_name"": ""ben_Beng"", ""data_files"": [{""split"": ""train"", ""path"": ""ben_Beng*/train-*""}]}, {""config_name"": ""bho_Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""bho_Deva*/train-*""}]}, {""config_name"": ""bjn_Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""bjn_Arab*/train-*""}]}, {""config_name"": ""bjn_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""bjn_Latn*/train-*""}]}, {""config_name"": ""bod_Tibt"", ""data_files"": [{""split"": ""train"", ""path"": ""bod_Tibt*/train-*""}]}, {""config_name"": ""bos_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""bos_Latn*/train-*""}]}, {""config_name"": ""bug_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""bug_Latn*/train-*""}]}, {""config_name"": ""bul_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""bul_Cyrl*/train-*""}]}, {""config_name"": ""cat_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""cat_Latn*/train-*""}]}, {""config_name"": ""ceb_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""ceb_Latn*/train-*""}]}, {""config_name"": ""ces_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""ces_Latn*/train-*""}]}, {""config_name"": ""cjk_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""cjk_Latn*/train-*""}]}, {""config_name"": ""ckb_Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""ckb_Arab*/train-*""}]}, {""config_name"": ""crh_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""crh_Latn*/train-*""}]}, {""config_name"": ""cym_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""cym_Latn*/train-*""}]}, {""config_name"": ""dan_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""dan_Latn*/train-*""}]}, {""config_name"": ""deu_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""deu_Latn*/train-*""}]}, {""config_name"": ""dik_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""dik_Latn*/train-*""}]}, {""config_name"": ""dyu_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""dyu_Latn*/train-*""}]}, {""config_name"": ""dzo_Tibt"", ""data_files"": [{""split"": ""train"", ""path"": ""dzo_Tibt*/train-*""}]}, {""config_name"": ""ell_Grek"", ""data_files"": [{""split"": ""train"", ""path"": ""ell_Grek*/train-*""}]}, {""config_name"": ""eng_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""eng_Latn*/train-*""}]}, {""config_name"": ""epo_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""epo_Latn*/train-*""}]}, {""config_name"": ""est_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""est_Latn*/train-*""}]}, {""config_name"": ""eus_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""eus_Latn*/train-*""}]}, {""config_name"": ""ewe_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""ewe_Latn*/train-*""}]}, {""config_name"": ""fao_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""fao_Latn*/train-*""}]}, {""config_name"": ""fij_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""fij_Latn*/train-*""}]}, {""config_name"": ""fin_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""fin_Latn*/train-*""}]}, {""config_name"": ""fon_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""fon_Latn*/train-*""}]}, {""config_name"": ""fra_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""fra_Latn*/train-*""}]}, {""config_name"": ""fur_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""fur_Latn*/train-*""}]}, {""config_name"": ""fuv_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""fuv_Latn*/train-*""}]}, {""config_name"": ""gaz_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""gaz_Latn*/train-*""}]}, {""config_name"": ""gla_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""gla_Latn*/train-*""}]}, {""config_name"": ""gle_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""gle_Latn*/train-*""}]}, {""config_name"": ""glg_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""glg_Latn*/train-*""}]}, {""config_name"": ""grn_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""grn_Latn*/train-*""}]}, {""config_name"": ""guj_Gujr"", ""data_files"": [{""split"": ""train"", ""path"": ""guj_Gujr*/train-*""}]}, {""config_name"": ""hat_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""hat_Latn*/train-*""}]}, {""config_name"": ""hau_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""hau_Latn*/train-*""}]}, {""config_name"": ""heb_Hebr"", ""data_files"": [{""split"": ""train"", ""path"": ""heb_Hebr*/train-*""}]}, {""config_name"": ""hin_Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""hin_Deva*/train-*""}]}, {""config_name"": ""hne_Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""hne_Deva*/train-*""}]}, {""config_name"": ""hrv_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""hrv_Latn*/train-*""}]}, {""config_name"": ""hun_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""hun_Latn*/train-*""}]}, {""config_name"": ""hye_Armn"", ""data_files"": [{""split"": ""train"", ""path"": ""hye_Armn*/train-*""}]}, {""config_name"": ""ibo_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""ibo_Latn*/train-*""}]}, {""config_name"": ""ilo_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""ilo_Latn*/train-*""}]}, {""config_name"": ""ind_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""ind_Latn*/train-*""}]}, {""config_name"": ""isl_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""isl_Latn*/train-*""}]}, {""config_name"": ""ita_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""ita_Latn*/train-*""}]}, {""config_name"": ""jav_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""jav_Latn*/train-*""}]}, {""config_name"": ""jpn_Jpan"", ""data_files"": [{""split"": ""train"", ""path"": ""jpn_Jpan*/train-*""}]}, {""config_name"": ""kab_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""kab_Latn*/train-*""}]}, {""config_name"": ""kac_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""kac_Latn*/train-*""}]}, {""config_name"": ""kam_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""kam_Latn*/train-*""}]}, {""config_name"": ""kan_Knda"", ""data_files"": [{""split"": ""train"", ""path"": ""kan_Knda*/train-*""}]}, {""config_name"": ""kas_Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""kas_Arab*/train-*""}]}, {""config_name"": ""kas_Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""kas_Deva*/train-*""}]}, {""config_name"": ""kat_Geor"", ""data_files"": [{""split"": ""train"", ""path"": ""kat_Geor*/train-*""}]}, {""config_name"": ""kaz_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""kaz_Cyrl*/train-*""}]}, {""config_name"": ""kbp_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""kbp_Latn*/train-*""}]}, {""config_name"": ""kea_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""kea_Latn*/train-*""}]}, {""config_name"": ""khk_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""khk_Cyrl*/train-*""}]}, {""config_name"": ""khm_Khmr"", ""data_files"": [{""split"": ""train"", ""path"": ""khm_Khmr*/train-*""}]}, {""config_name"": ""kik_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""kik_Latn*/train-*""}]}, {""config_name"": ""kin_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""kin_Latn*/train-*""}]}, {""config_name"": ""kir_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""kir_Cyrl*/train-*""}]}, {""config_name"": ""kmb_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""kmb_Latn*/train-*""}]}, {""config_name"": ""kmr_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""kmr_Latn*/train-*""}]}, {""config_name"": ""knc_Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""knc_Arab*/train-*""}]}, {""config_name"": ""kon_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""kon_Latn*/train-*""}]}, {""config_name"": ""kor_Hang"", ""data_files"": [{""split"": ""train"", ""path"": ""kor_Hang*/train-*""}]}, {""config_name"": ""lao_Laoo"", ""data_files"": [{""split"": ""train"", ""path"": ""lao_Laoo*/train-*""}]}, {""config_name"": ""lij_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""lij_Latn*/train-*""}]}, {""config_name"": ""lim_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""lim_Latn*/train-*""}]}, {""config_name"": ""lin_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""lin_Latn*/train-*""}]}, {""config_name"": ""lit_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""lit_Latn*/train-*""}]}, {""config_name"": ""lmo_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""lmo_Latn*/train-*""}]}, {""config_name"": ""ltg_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""ltg_Latn*/train-*""}]}, {""config_name"": ""ltz_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""ltz_Latn*/train-*""}]}, {""config_name"": ""lua_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""lua_Latn*/train-*""}]}, {""config_name"": ""lug_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""lug_Latn*/train-*""}]}, {""config_name"": ""luo_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""luo_Latn*/train-*""}]}, {""config_name"": ""lus_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""lus_Latn*/train-*""}]}, {""config_name"": ""lvs_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""lvs_Latn*/train-*""}]}, {""config_name"": ""mag_Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""mag_Deva*/train-*""}]}, {""config_name"": ""mai_Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""mai_Deva*/train-*""}]}, {""config_name"": ""mal_Mlym"", ""data_files"": [{""split"": ""train"", ""path"": ""mal_Mlym*/train-*""}]}, {""config_name"": ""mar_Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""mar_Deva*/train-*""}]}, {""config_name"": ""min_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""min_Latn*/train-*""}]}, {""config_name"": ""mkd_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""mkd_Cyrl*/train-*""}]}, {""config_name"": ""mlt_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""mlt_Latn*/train-*""}]}, {""config_name"": ""mni_Beng"", ""data_files"": [{""split"": ""train"", ""path"": ""mni_Beng*/train-*""}]}, {""config_name"": ""mos_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""mos_Latn*/train-*""}]}, {""config_name"": ""mri_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""mri_Latn*/train-*""}]}, {""config_name"": ""mya_Mymr"", ""data_files"": [{""split"": ""train"", ""path"": ""mya_Mymr*/train-*""}]}, {""config_name"": ""nld_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""nld_Latn*/train-*""}]}, {""config_name"": ""nno_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""nno_Latn*/train-*""}]}, {""config_name"": ""nob_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""nob_Latn*/train-*""}]}, {""config_name"": ""npi_Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""npi_Deva*/train-*""}]}, {""config_name"": ""nso_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""nso_Latn*/train-*""}]}, {""config_name"": ""nus_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""nus_Latn*/train-*""}]}, {""config_name"": ""nya_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""nya_Latn*/train-*""}]}, {""config_name"": ""oci_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""oci_Latn*/train-*""}]}, {""config_name"": ""ory_Orya"", ""data_files"": [{""split"": ""train"", ""path"": ""ory_Orya*/train-*""}]}, {""config_name"": ""pan_Guru"", ""data_files"": [{""split"": ""train"", ""path"": ""pan_Guru*/train-*""}]}, {""config_name"": ""pap_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""pap_Latn*/train-*""}]}, {""config_name"": ""pbt_Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""pbt_Arab*/train-*""}]}, {""config_name"": ""pes_Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""pes_Arab*/train-*""}]}, {""config_name"": ""plt_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""plt_Latn*/train-*""}]}, {""config_name"": ""pol_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""pol_Latn*/train-*""}]}, {""config_name"": ""por_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""por_Latn*/train-*""}]}, {""config_name"": ""prs_Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""prs_Arab*/train-*""}]}, {""config_name"": ""quy_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""quy_Latn*/train-*""}]}, {""config_name"": ""ron_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""ron_Latn*/train-*""}]}, {""config_name"": ""run_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""run_Latn*/train-*""}]}, {""config_name"": ""rus_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""rus_Cyrl*/train-*""}]}, {""config_name"": ""san_Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""san_Deva*/train-*""}]}, {""config_name"": ""sat_Olck"", ""data_files"": [{""split"": ""train"", ""path"": ""sat_Olck*/train-*""}]}, {""config_name"": ""scn_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""scn_Latn*/train-*""}]}, {""config_name"": ""shn_Mymr"", ""data_files"": [{""split"": ""train"", ""path"": ""shn_Mymr*/train-*""}]}, {""config_name"": ""sin_Sinh"", ""data_files"": [{""split"": ""train"", ""path"": ""sin_Sinh*/train-*""}]}, {""config_name"": ""slk_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""slk_Latn*/train-*""}]}, {""config_name"": ""slv_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""slv_Latn*/train-*""}]}, {""config_name"": ""smo_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""smo_Latn*/train-*""}]}, {""config_name"": ""sna_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""sna_Latn*/train-*""}]}, {""config_name"": ""snd_Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""snd_Arab*/train-*""}]}, {""config_name"": ""som_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""som_Latn*/train-*""}]}, {""config_name"": ""sot_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""sot_Latn*/train-*""}]}, {""config_name"": ""spa_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""spa_Latn*/train-*""}]}, {""config_name"": ""srd_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""srd_Latn*/train-*""}]}, {""config_name"": ""srp_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""srp_Cyrl*/train-*""}]}, {""config_name"": ""ssw_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""ssw_Latn*/train-*""}]}, {""config_name"": ""sun_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""sun_Latn*/train-*""}]}, {""config_name"": ""swe_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""swe_Latn*/train-*""}]}, {""config_name"": ""swh_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""swh_Latn*/train-*""}]}, {""config_name"": ""szl_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""szl_Latn*/train-*""}]}, {""config_name"": ""tam_Taml"", ""data_files"": [{""split"": ""train"", ""path"": ""tam_Taml*/train-*""}]}, {""config_name"": ""taq_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""taq_Latn*/train-*""}]}, {""config_name"": ""tat_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""tat_Cyrl*/train-*""}]}, {""config_name"": ""tel_Telu"", ""data_files"": [{""split"": ""train"", ""path"": ""tel_Telu*/train-*""}]}, {""config_name"": ""tgk_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""tgk_Cyrl*/train-*""}]}, {""config_name"": ""tgl_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""tgl_Latn*/train-*""}]}, {""config_name"": ""tha_Thai"", ""data_files"": [{""split"": ""train"", ""path"": ""tha_Thai*/train-*""}]}, {""config_name"": ""tir_Ethi"", ""data_files"": [{""split"": ""train"", ""path"": ""tir_Ethi*/train-*""}]}, {""config_name"": ""tpi_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""tpi_Latn*/train-*""}]}, {""config_name"": ""tsn_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""tsn_Latn*/train-*""}]}, {""config_name"": ""tso_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""tso_Latn*/train-*""}]}, {""config_name"": ""tuk_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""tuk_Latn*/train-*""}]}, {""config_name"": ""tum_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""tum_Latn*/train-*""}]}, {""config_name"": ""tur_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""tur_Latn*/train-*""}]}, {""config_name"": ""twi_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""twi_Latn*/train-*""}]}, {""config_name"": ""uig_Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""uig_Arab*/train-*""}]}, {""config_name"": ""ukr_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""ukr_Cyrl*/train-*""}]}, {""config_name"": ""umb_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""umb_Latn*/train-*""}]}, {""config_name"": ""urd_Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""urd_Arab*/train-*""}]}, {""config_name"": ""uzn_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""uzn_Latn*/train-*""}]}, {""config_name"": ""vec_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""vec_Latn*/train-*""}]}, {""config_name"": ""vie_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""vie_Latn*/train-*""}]}, {""config_name"": ""war_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""war_Latn*/train-*""}]}, {""config_name"": ""wol_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""wol_Latn*/train-*""}]}, {""config_name"": ""xho_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""xho_Latn*/train-*""}]}, {""config_name"": ""ydd_Hebr"", ""data_files"": [{""split"": ""train"", ""path"": ""ydd_Hebr*/train-*""}]}, {""config_name"": ""yor_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""yor_Latn*/train-*""}]}, {""config_name"": ""yue_Hant"", ""data_files"": [{""split"": ""train"", ""path"": ""yue_Hant*/train-*""}]}, {""config_name"": ""zho_Hans"", ""data_files"": [{""split"": ""train"", ""path"": ""zho_Hans*/train-*""}]}, {""config_name"": ""zho_Hant"", ""data_files"": [{""split"": ""train"", ""path"": ""zho_Hant*/train-*""}]}, {""config_name"": ""zsm_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""zsm_Latn*/train-*""}]}, {""config_name"": ""zul_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""zul_Latn*/train-*""}]}, {""config_name"": ""pag_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""pag_Latn*/train-*""}]}, {""config_name"": ""sag_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""sag_Latn*/train-*""}]}, {""config_name"": ""bam_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""bam_Latn*/train-*""}]}, {""config_name"": ""knc_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""knc_Latn*/train-*""}]}], ""license"": ""cc0-1.0"", ""size_categories"": [""n>1T""], ""multilinguality"": [""multilingual""], ""task_categories"": [""fill-mask"", ""text-generation""], ""task_ids"": [""language-modeling""], ""language"": [""ace"", ""af"", ""als"", ""am"", ""ar"", ""as"", ""ast"", ""awa"", ""ayr"", ""azb"", ""azj"", ""ba"", ""bm"", ""ban"", ""be"", ""bem"", ""bn"", ""bho"", ""bjn"", ""bo"", ""bs"", ""bug"", ""bg"", ""ca"", ""ceb"", ""cs"", ""cjk"", ""ckb"", ""crh"", ""cy"", ""da"", ""de"", ""dik"", ""dyu"", ""dz"", ""el"", ""en"", ""eo"", ""et"", ""eu"", ""ee"", ""fo"", ""fj"", ""fi"", ""fon"", ""fr"", ""fur"", ""fuv"", ""gaz"", ""gd"", ""ga"", ""gl"", ""gn"", ""gu"", ""ht"", ""ha"", ""he"", ""hi"", ""hne"", ""hr"", ""hu"", ""hy"", ""ig"", ""ilo"", ""id"", ""is"", ""it"", ""jv"", ""ja"", ""kab"", ""kac"", ""kam"", ""kn"", ""ks"", ""ka"", ""kk"", ""kbp"", ""kea"", ""khk"", ""km"", ""ki"", ""rw"", ""ky"", ""kmb"", ""kmr"", ""knc"", ""kg"", ""ko"", ""lo"", ""lij"", ""li"", ""ln"", ""lt"", ""lmo"", ""ltg"", ""lb"", ""lua"", ""lg"", ""luo"", ""lus"", ""lvs"", ""mag"", ""mai"", ""ml"", ""mr"", ""min"", ""mk"", ""mt"", ""mni"", ""mos"", ""mi"", ""my"", ""nl"", ""nn"", ""nb"", ""npi"", ""nso"", ""nus"", ""ny"", ""oc"", ""ory"", ""pag"", ""pa"", ""pap"", ""pbt"", ""pes"", ""plt"", ""pl"", ""pt"", ""prs"", ""quy"", ""ro"", ""rn"", ""ru"", ""sg"", ""sa"", ""sat"", ""scn"", ""shn"", ""si"", ""sk"", ""sl"", ""sm"", ""sn"", ""sd"", ""so"", ""st"", ""es"", ""sc"", ""sr"", ""ss"", ""su"", ""sv"", ""swh"", ""szl"", ""ta"", ""taq"", ""tt"", ""te"", ""tg"", ""tl"", ""th"", ""ti"", ""tpi"", ""tn"", ""ts"", ""tk"", ""tum"", ""tr"", ""tw"", ""ug"", ""uk"", ""umb"", ""ur"", ""uzn"", ""vec"", ""vi"", ""war"", ""wo"", ""xh"", ""ydd"", ""yo"", ""yue"", ""zh"", ""zsm"", ""zu""]}","This is a large-scale collection of web-crawled documents in 191 world languages, produced by the [HPLT project](https://hplt-project.org/). +The source of the data is mostly [Internet Archive](https://archive.org/) with some additions from [Common Crawl](https://commoncrawl.org/). + +For a detailed description of the dataset, please refer to https://hplt-project.org/datasets/v2.0 + +**The Cleaned variant of HPLT Datasets v2.0** + +This is the ```cleaned``` variant of the HPLT Datasets v2.0 converted to the Parquet format semi-automatically when being uploaded here. +The original JSONL files (which take ~4x fewer disk space than this HF version) and the larger non-cleaned version can be found at https://hplt-project.org/datasets/v2.0. + +**Dataset Performance** + +***External Evaluation*** + +The HuggingFace team has [compared the utility of various multilingual corpora for training large language models in their FineWeb2 initiative](https://huggingface.co/datasets/HuggingFaceFW/fineweb-2). +They found that the HPLT v2 datasets are next to their FineWeb 2, on par with the CulturaX dataset as shown in this figure produced by HuggingFace: + + + +This is a massive improvement compared to the HPLT v1 datasets, as can be seen on the plot above. +In fact, it’s even better: if one looks at the language-specific results, it becomes clear that on +Arabic, Hindi, Russian, Thai and Turkish (5 out of 9 languages HuggingFace evaluated on), [HPLT v2 is on par or better than FineWeb 2](https://huggingface.co/datasets/HuggingFaceFW/fineweb-2#comparison-with-other-datasets). +The average score is lower mostly because of Chinese, so we have some work ahead for this language! +Note that the source of the FineWeb 2 (and CulturaX) data is exclusively CommonCrawl, while the HPLT datasets are to a large extent composed of Internet Archive crawls. +Thus, **FineWeb 2 and HPLTv2 are complementary to each other and should be used together**. + +***Internal Evaluation*** + + +We also conducted FineWeb-style evaluations within the HPLT project, for now limited to English. +It confirmed the findings of HuggingFace in that HPLT v2 datasets are of much better quality than HPLT v1.2 data, which was released almost a year ago. + +We replicated the FineWeb evaluation setting, training large language models with the same architecture and pretraining configuration +(e.g. 1.82B parameters, Llama architecture with a sequence length of 2048 tokens, GPT 2 tokenizer, and a global batch size of ~2 million tokens), with the only difference between the models being the training data. +We randomly sampled approximately 100B tokens from different versions of HPLT as well as FineWeb-data and trained a separate model on each of these datasets. + +Each model was trained with the GPT-NeoX framework on 8 nodes on the LUMI cluster, where each node has 4 MI250X GPUs. +For evaluation, we use the HuggingFace LightEval in a zero-shot setting with the tasks ARC (Easy and Challenge), Hellaswag, PICA, and OpenbookQA. +The figure shows the macro average of the acc_norm values for these evaluations. + + + + + +***Languages*** + +The ```cleaned``` version of HPLT Datasets v2.0 consists of subsets corresponding to 191 language codes. +Below we provide a list of language codes. For each language code the amount of text is shown as measured in: +- segments: the number of sequences of characters (possibly empty) separated by the newline symbol, +- wcwords: the number of words as defined by the Unix ```wc``` utility, i.e. the number of non-whitespaces with a whitespace or the beginning of document before, +- chars: the number of characters, +- docs: the number of documents, each document corresponds to an individual web page from the sourcing web crawls. + +| | lang | segments | wcwords | chars | docs | Language Name | ISO693-3 code | ISO693-3 code macro | ISO693-1 direct code | ISO693-1 through macro | +|-----|----------|----------|----------|----------|----------|-------------------------------|---------------|---------------------|----------------------|------------------------| +| 0 | *TOTAL* | 3.00e+11 | 5.56e+12 | 3.74e+13 | 1.06e+10 | | | | | | +| 1 | ace_Arab | 1.17e+02 | 8.36e+03 | 4.97e+04 | 1.60e+01 | Achinese | ace | | | | +| 2 | ace_Latn | 2.06e+05 | 8.20e+06 | 5.08e+07 | 1.29e+04 | Achinese | ace | | | | +| 3 | afr_Latn | 3.77e+07 | 1.00e+09 | 5.95e+09 | 1.46e+06 | Afrikaans | afr | | af | af | +| 4 | als_Latn | 9.51e+07 | 2.71e+09 | 1.61e+10 | 5.38e+06 | Tosk Albanian | als | sqi | | sq | +| 5 | amh_Ethi | 7.01e+06 | 1.96e+08 | 1.03e+09 | 2.96e+05 | Amharic | amh | | am | am | +| 6 | ara_Arab | 2.20e+09 | 4.81e+10 | 2.80e+11 | 8.27e+07 | Arabic | ara | | ar | ar | +| 7 | asm_Beng | 2.68e+06 | 7.34e+07 | 4.76e+08 | 1.76e+05 | Assamese | asm | | as | as | +| 8 | ast_Latn | 7.43e+06 | 1.95e+08 | 1.24e+09 | 2.73e+05 | Asturian | ast | | | | +| 9 | awa_Deva | 1.32e+05 | 6.05e+06 | 2.88e+07 | 7.28e+03 | Awadhi | awa | | | | +| 10 | ayr_Latn | 1.88e+05 | 3.07e+06 | 2.51e+07 | 9.22e+03 | Central Aymara | ayr | aym | | ay | +| 11 | azb_Arab | 2.39e+06 | 3.96e+07 | 2.60e+08 | 6.61e+04 | South Azerbaijani | azb | aze | | az | +| 12 | azj_Latn | 1.27e+08 | 2.57e+09 | 1.96e+10 | 6.48e+06 | North Azerbaijani | azj | aze | | az | +| 13 | bak_Cyrl | 3.14e+06 | 7.53e+07 | 5.58e+08 | 1.71e+05 | Bashkir | bak | | ba | ba | +| 14 | bam_Latn | 9.17e+04 | 3.98e+06 | 2.07e+07 | 5.72e+03 | Bambara | bam | | bm | bm | +| 15 | ban_Latn | 6.01e+05 | 1.13e+07 | 7.72e+07 | 1.07e+04 | Balinese | ban | | | | +| 16 | bel_Cyrl | 4.88e+07 | 1.21e+09 | 8.54e+09 | 2.32e+06 | Belarusian | bel | | be | be | +| 17 | bem_Latn | 1.34e+05 | 4.52e+06 | 3.23e+07 | 6.14e+03 | Bemba (Zambia) | bem | | | | +| 18 | ben_Beng | 1.76e+08 | 4.64e+09 | 3.02e+10 | 1.10e+07 | Bengali | ben | | bn | bn | +| 19 | bho_Deva | 4.58e+05 | 1.35e+07 | 6.86e+07 | 2.86e+04 | Bhojpuri | bho | | | | +| 20 | bjn_Arab | 1.95e+04 | 5.48e+05 | 3.32e+06 | 1.11e+03 | Banjar | bjn | msa | | ms | +| 21 | bjn_Latn | 3.66e+05 | 8.05e+06 | 5.60e+07 | 1.88e+04 | Banjar | bjn | msa | | ms | +| 22 | bod_Tibt | 4.65e+05 | 5.78e+06 | 2.68e+08 | 2.74e+04 | Tibetan | bod | | bo | bo | +| 23 | bos_Latn | 2.68e+08 | 7.26e+09 | 4.61e+10 | 1.46e+07 | Bosnian | bos | hbs | bs | bs | +| 24 | bug_Latn | 3.86e+04 | 2.70e+06 | 1.93e+07 | 2.02e+03 | Buginese | bug | | | | +| 25 | bul_Cyrl | 6.81e+08 | 1.53e+10 | 9.69e+10 | 2.81e+07 | Bulgarian | bul | | bg | bg | +| 26 | cat_Latn | 3.83e+08 | 1.00e+10 | 6.02e+10 | 1.86e+07 | Catalan | cat | | ca | ca | +| 27 | ceb_Latn | 2.86e+06 | 8.59e+07 | 5.16e+08 | 1.39e+05 | Cebuano | ceb | | | | +| 28 | ces_Latn | 1.93e+09 | 4.21e+10 | 2.74e+11 | 7.53e+07 | Czech | ces | | cs | cs | +| 29 | cjk_Latn | 3.67e+04 | 9.65e+05 | 7.43e+06 | 1.20e+03 | Chokwe | cjk | | | | +| 30 | ckb_Arab | 5.23e+06 | 1.43e+08 | 9.13e+08 | 2.74e+05 | Central Kurdish | ckb | kur | | ku | +| 31 | crh_Latn | 1.38e+06 | 3.68e+07 | 2.81e+08 | 1.23e+05 | Crimean Tatar | crh | | | | +| 32 | cym_Latn | 1.56e+07 | 4.09e+08 | 2.40e+09 | 7.58e+05 | Welsh | cym | | cy | cy | +| 33 | dan_Latn | 8.73e+08 | 2.12e+10 | 1.33e+11 | 3.38e+07 | Danish | dan | | da | da | +| 34 | deu_Latn | 1.11e+10 | 2.52e+11 | 1.78e+12 | 4.82e+08 | German | deu | | de | de | +| 35 | dik_Latn | 3.46e+04 | 2.30e+06 | 1.15e+07 | 2.32e+03 | Southwestern Dinka | dik | din | | | +| 36 | dyu_Latn | 2.46e+04 | 1.19e+06 | 5.55e+06 | 1.39e+03 | Dyula | dyu | | | | +| 37 | dzo_Tibt | 4.00e+04 | 4.22e+05 | 7.38e+06 | 1.63e+03 | Dzongkha | dzo | | dz | dz | +| 38 | ell_Grek | 1.85e+09 | 4.27e+10 | 2.84e+11 | 7.03e+07 | Modern Greek (1453-) | ell | | el | el | +| 39 | eng_Latn | 1.16e+11 | 2.86e+12 | 1.71e+13 | 4.39e+09 | English | eng | | en | en | +| 40 | epo_Latn | 2.04e+07 | 4.72e+08 | 2.98e+09 | 8.19e+05 | Esperanto | epo | | eo | eo | +| 41 | est_Latn | 2.64e+08 | 4.74e+09 | 3.60e+10 | 8.45e+06 | Estonian | est | | et | et | +| 42 | eus_Latn | 3.76e+07 | 7.77e+08 | 6.05e+09 | 1.97e+06 | Basque | eus | | eu | eu | +| 43 | ewe_Latn | 1.43e+05 | 4.31e+06 | 2.13e+07 | 3.77e+03 | Ewe | ewe | | ee | ee | +| 44 | fao_Latn | 4.53e+06 | 9.34e+07 | 5.82e+08 | 2.40e+05 | Faroese | fao | | fo | fo | +| 45 | fij_Latn | 1.79e+05 | 7.26e+06 | 3.77e+07 | 8.91e+03 | Fijian | fij | | fj | fj | +| 46 | fin_Latn | 9.77e+08 | 1.84e+10 | 1.56e+11 | 3.48e+07 | Finnish | fin | | fi | fi | +| 47 | fon_Latn | 1.48e+04 | 1.23e+06 | 5.34e+06 | 1.23e+03 | Fon | fon | | | | +| 48 | fra_Latn | 1.06e+10 | 2.37e+11 | 1.46e+12 | 4.02e+08 | French | fra | | fr | fr | +| 49 | fur_Latn | 7.30e+05 | 2.08e+07 | 1.15e+08 | 3.67e+04 | Friulian | fur | | | | +| 50 | fuv_Latn | 1.34e+05 | 5.14e+06 | 2.99e+07 | 7.76e+03 | Nigerian Fulfulde | fuv | ful | | ff | +| 51 | gaz_Latn | 9.74e+05 | 2.89e+07 | 2.19e+08 | 4.91e+04 | West Central Oromo | gaz | orm | | om | +| 52 | gla_Latn | 3.31e+06 | 8.07e+07 | 4.84e+08 | 1.37e+05 | Scottish Gaelic | gla | | gd | gd | +| 53 | gle_Latn | 1.10e+07 | 2.96e+08 | 1.75e+09 | 4.91e+05 | Irish | gle | | ga | ga | +| 54 | glg_Latn | 6.12e+07 | 1.64e+09 | 1.01e+10 | 3.02e+06 | Galician | glg | | gl | gl | +| 55 | grn_Latn | 1.71e+06 | 3.07e+07 | 2.19e+08 | 7.34e+04 | Guarani | grn | | gn | gn | +| 56 | guj_Gujr | 2.06e+07 | 5.77e+08 | 3.39e+09 | 1.13e+06 | Gujarati | guj | | gu | gu | +| 57 | hat_Latn | 4.64e+06 | 1.22e+08 | 6.39e+08 | 2.13e+05 | Haitian | hat | | ht | ht | +| 58 | hau_Latn | 5.69e+06 | 1.53e+08 | 8.54e+08 | 3.16e+05 | Hausa | hau | | ha | ha | +| 59 | heb_Hebr | 4.67e+08 | 9.97e+09 | 5.68e+10 | 1.71e+07 | Hebrew | heb | | he | he | +| 60 | hin_Deva | 2.67e+08 | 8.64e+09 | 4.40e+10 | 1.36e+07 | Hindi | hin | | hi | hi | +| 61 | hne_Deva | 5.50e+04 | 2.20e+06 | 1.06e+07 | 2.81e+03 | Chhattisgarhi | hne | | | | +| 62 | hrv_Latn | 2.97e+08 | 7.31e+09 | 4.80e+10 | 1.23e+07 | Croatian | hrv | hbs | hr | hr | +| 63 | hun_Latn | 1.42e+09 | 3.05e+10 | 2.25e+11 | 5.19e+07 | Hungarian | hun | | hu | hu | +| 64 | hye_Armn | 6.52e+07 | 1.40e+09 | 1.07e+10 | 3.60e+06 | Armenian | hye | | hy | hy | +| 65 | ibo_Latn | 1.41e+06 | 3.83e+07 | 2.05e+08 | 5.63e+04 | Igbo | ibo | | ig | ig | +| 66 | ilo_Latn | 1.12e+06 | 2.48e+07 | 1.57e+08 | 4.88e+04 | Iloko | ilo | | | | +| 67 | ind_Latn | 2.39e+09 | 5.46e+10 | 3.84e+11 | 9.81e+07 | Indonesian | ind | msa | id | id | +| 68 | isl_Latn | 6.96e+07 | 1.54e+09 | 9.59e+09 | 2.84e+06 | Icelandic | isl | | is | is | +| 69 | ita_Latn | 5.13e+09 | 1.27e+11 | 8.21e+11 | 2.22e+08 | Italian | ita | | it | it | +| 70 | jav_Latn | 6.43e+06 | 1.38e+08 | 9.38e+08 | 1.96e+05 | Javanese | jav | | jv | jv | +| 71 | jpn_Jpan | 2.33e+10 | 4.24e+10 | 9.01e+11 | 4.18e+08 | Japanese | jpn | | ja | ja | +| 72 | kab_Latn | 3.45e+05 | 9.22e+06 | 5.42e+07 | 1.51e+04 | Kabyle | kab | | | | +| 73 | kac_Latn | 1.59e+05 | 5.96e+06 | 2.84e+07 | 7.59e+03 | Kachin | kac | | | | +| 74 | kam_Latn | 1.43e+04 | 6.74e+05 | 4.64e+06 | 1.18e+03 | Kamba (Kenya) | kam | | | | +| 75 | kan_Knda | 2.49e+07 | 5.33e+08 | 4.30e+09 | 1.34e+06 | Kannada | kan | | kn | kn | +| 76 | kas_Arab | 2.71e+04 | 6.78e+05 | 3.47e+06 | 9.49e+02 | Kashmiri | kas | | ks | ks | +| 77 | kas_Deva | 1.36e+03 | 3.19e+04 | 1.85e+05 | 1.06e+02 | Kashmiri | kas | | ks | ks | +| 78 | kat_Geor | 6.37e+07 | 1.24e+09 | 1.02e+10 | 3.34e+06 | Georgian | kat | | ka | ka | +| 79 | kaz_Cyrl | 8.10e+07 | 1.41e+09 | 1.11e+10 | 2.64e+06 | Kazakh | kaz | | kk | kk | +| 80 | kbp_Latn | 4.68e+04 | 4.26e+06 | 2.09e+07 | 7.08e+03 | Kabiyè | kbp | | | | +| 81 | kea_Latn | 4.39e+04 | 1.14e+06 | 6.14e+06 | 1.96e+03 | Kabuverdianu | kea | | | | +| 82 | khk_Cyrl | 5.35e+07 | 1.34e+09 | 9.33e+09 | 2.12e+06 | Halh Mongolian | khk | mon | | mn | +| 83 | khm_Khmr | 9.86e+06 | 1.14e+08 | 2.12e+09 | 7.01e+05 | Khmer | khm | | km | km | +| 84 | kik_Latn | 5.19e+04 | 1.43e+06 | 9.29e+06 | 4.00e+03 | Kikuyu | kik | | ki | ki | +| 85 | kin_Latn | 1.92e+06 | 5.07e+07 | 3.67e+08 | 9.27e+04 | Kinyarwanda | kin | | rw | rw | +| 86 | kir_Cyrl | 1.00e+07 | 2.47e+08 | 1.92e+09 | 6.76e+05 | Kirghiz | kir | | ky | ky | +| 87 | kmb_Latn | 1.18e+04 | 3.83e+05 | 2.07e+06 | 5.31e+02 | Kimbundu | kmb | | | | +| 88 | kmr_Latn | 7.15e+06 | 1.96e+08 | 1.12e+09 | 3.64e+05 | Northern Kurdish | kmr | kur | | ku | +| 89 | knc_Arab | 1.08e+04 | 2.62e+05 | 1.30e+06 | 2.45e+02 | Central Kanuri | knc | kau | | kr | +| 90 | knc_Latn | 1.05e+04 | 2.41e+06 | 1.20e+07 | 2.47e+03 | Central Kanuri | knc | kau | | kr | +| 91 | kon_Latn | 4.75e+04 | 1.94e+06 | 1.13e+07 | 2.54e+03 | Kongo | kon | | kg | kg | +| 92 | kor_Hang | 1.36e+09 | 1.97e+10 | 8.92e+10 | 3.89e+07 | Korean | kor | | ko | ko | +| 93 | lao_Laoo | 3.20e+05 | 5.18e+06 | 8.47e+07 | 2.95e+04 | Lao | lao | | lo | lo | +| 94 | lij_Latn | 1.58e+05 | 5.59e+06 | 3.15e+07 | 8.37e+03 | Ligurian | lij | | | | +| 95 | lim_Latn | 7.14e+06 | 1.81e+08 | 1.12e+09 | 3.68e+05 | Limburgan | lim | | li | li | +| 96 | lin_Latn | 2.00e+05 | 5.56e+06 | 3.29e+07 | 7.59e+03 | Lingala | lin | | ln | ln | +| 97 | lit_Latn | 3.22e+08 | 6.68e+09 | 5.04e+10 | 1.33e+07 | Lithuanian | lit | | lt | lt | +| 98 | lmo_Latn | 2.12e+06 | 5.96e+07 | 3.45e+08 | 1.46e+05 | Lombard | lmo | | | | +| 99 | ltg_Latn | 1.51e+05 | 3.79e+06 | 2.69e+07 | 9.21e+03 | Latgalian | ltg | lav | | lv | +| 100 | ltz_Latn | 5.06e+06 | 1.07e+08 | 7.10e+08 | 2.47e+05 | Luxembourgish | ltz | | lb | lb | +| 101 | lua_Latn | 3.87e+04 | 1.37e+06 | 9.00e+06 | 1.08e+03 | Luba-Lulua | lua | | | | +| 102 | lug_Latn | 4.08e+05 | 9.18e+06 | 6.80e+07 | 2.13e+04 | Ganda | lug | | lg | lg | +| 103 | luo_Latn | 8.41e+04 | 3.73e+06 | 2.03e+07 | 4.15e+03 | Luo (Kenya and Tanzania) | luo | | | | +| 104 | lus_Latn | 3.43e+06 | 1.25e+08 | 6.52e+08 | 1.60e+05 | Lushai | lus | | | | +| 105 | lvs_Latn | 1.74e+08 | 3.46e+09 | 2.52e+10 | 6.77e+06 | Standard Latvian | lvs | lav | | lv | +| 106 | mag_Deva | 1.93e+04 | 8.91e+05 | 4.28e+06 | 3.28e+02 | Magahi | mag | | | | +| 107 | mai_Deva | 6.46e+05 | 1.78e+07 | 9.67e+07 | 2.50e+04 | Maithili | mai | | | | +| 108 | mal_Mlym | 4.80e+07 | 9.74e+08 | 9.49e+09 | 3.10e+06 | Malayalam | mal | | ml | ml | +| 109 | mar_Deva | 3.63e+07 | 9.81e+08 | 6.62e+09 | 2.08e+06 | Marathi | mar | | mr | mr | +| 110 | min_Latn | 6.01e+05 | 1.10e+07 | 7.48e+07 | 2.50e+04 | Minangkabau | min | msa | | ms | +| 111 | mkd_Cyrl | 5.70e+07 | 1.48e+09 | 9.44e+09 | 3.57e+06 | Macedonian | mkd | | mk | mk | +| 112 | mlt_Latn | 8.68e+06 | 1.96e+08 | 1.44e+09 | 3.67e+05 | Maltese | mlt | | mt | mt | +| 113 | mni_Beng | 6.58e+04 | 1.63e+06 | 1.18e+07 | 2.93e+03 | Manipuri | mni | | | | +| 114 | mos_Latn | 1.91e+04 | 8.08e+05 | 3.86e+06 | 9.31e+02 | Mossi | mos | | | | +| 115 | mri_Latn | 2.80e+06 | 8.68e+07 | 4.24e+08 | 1.08e+05 | Maori | mri | | mi | mi | +| 116 | mya_Mymr | 3.05e+07 | 4.53e+08 | 5.82e+09 | 1.37e+06 | Burmese | mya | | my | my | +| 117 | nld_Latn | 3.08e+09 | 7.14e+10 | 4.51e+11 | 1.39e+08 | Dutch | nld | | nl | nl | +| 118 | nno_Latn | 3.46e+07 | 8.60e+08 | 5.40e+09 | 1.42e+06 | Norwegian Nynorsk | nno | nor | nn | nn | +| 119 | nob_Latn | 6.76e+08 | 2.15e+10 | 1.33e+11 | 2.70e+07 | Norwegian Bokmål | nob | nor | nb | nb | +| 120 | npi_Deva | 3.71e+07 | 1.13e+09 | 7.26e+09 | 2.78e+06 | Nepali (individual language) | npi | nep | | ne | +| 121 | nso_Latn | 1.43e+05 | 5.32e+06 | 2.75e+07 | 6.07e+03 | Pedi | nso | | | | +| 122 | nus_Latn | 8.51e+03 | 3.93e+05 | 1.88e+06 | 2.72e+02 | Nuer | nus | | | | +| 123 | nya_Latn | 1.34e+06 | 2.71e+07 | 2.03e+08 | 5.31e+04 | Nyanja | nya | | ny | ny | +| 124 | oci_Latn | 4.20e+06 | 1.03e+08 | 6.35e+08 | 1.90e+05 | Occitan (post 1500) | oci | | oc | oc | +| 125 | ory_Orya | 3.60e+06 | 1.20e+08 | 7.82e+08 | 4.13e+05 | Odia | ory | ori | | or | +| 126 | pag_Latn | 8.58e+04 | 5.66e+06 | 3.35e+07 | 6.90e+03 | Pangasinan | pag | | | | +| 127 | pan_Guru | 1.17e+07 | 3.72e+08 | 1.90e+09 | 5.85e+05 | Panjabi | pan | | pa | pa | +| 128 | pap_Latn | 1.39e+06 | 4.67e+07 | 2.54e+08 | 8.98e+04 | Papiamento | pap | | | | +| 129 | pbt_Arab | 8.46e+06 | 2.79e+08 | 1.30e+09 | 4.66e+05 | Southern Pashto | pbt | pus | | ps | +| 130 | pes_Arab | 3.96e+09 | 8.86e+10 | 4.55e+11 | 9.05e+07 | Iranian Persian | pes | fas | | fa | +| 131 | plt_Latn | 4.74e+06 | 1.17e+08 | 8.10e+08 | 2.08e+05 | Plateau Malagasy | plt | mlg | | mg | +| 132 | pol_Latn | 4.46e+09 | 8.95e+10 | 6.32e+11 | 1.75e+08 | Polish | pol | | pl | pl | +| 133 | por_Latn | 6.12e+09 | 1.46e+11 | 8.96e+11 | 2.38e+08 | Portuguese | por | | pt | pt | +| 134 | prs_Arab | 6.90e+07 | 1.84e+09 | 9.57e+09 | 2.84e+06 | Dari | prs | fas | | fa | +| 135 | quy_Latn | 4.94e+05 | 1.73e+07 | 1.43e+08 | 3.69e+04 | Ayacucho Quechua | quy | que | | qu | +| 136 | ron_Latn | 1.70e+09 | 4.00e+10 | 2.51e+11 | 6.59e+07 | Romanian | ron | | ro | ro | +| 137 | run_Latn | 1.75e+06 | 4.44e+07 | 3.16e+08 | 1.37e+05 | Rundi | run | | rn | rn | +| 138 | rus_Cyrl | 2.63e+10 | 5.41e+11 | 3.91e+12 | 8.85e+08 | Russian | rus | | ru | ru | +| 139 | sag_Latn | 5.19e+04 | 3.61e+06 | 1.67e+07 | 3.16e+03 | Sango | sag | | sg | sg | +| 140 | san_Deva | 3.28e+06 | 4.38e+07 | 3.59e+08 | 5.49e+04 | Sanskrit | san | | sa | sa | +| 141 | sat_Olck | 4.58e+04 | 1.08e+06 | 6.27e+06 | 2.57e+03 | Santali | sat | | | | +| 142 | scn_Latn | 1.65e+06 | 4.24e+07 | 2.52e+08 | 8.20e+04 | Sicilian | scn | | | | +| 143 | shn_Mymr | 9.21e+04 | 1.65e+06 | 2.12e+07 | 6.00e+03 | Shan | shn | | | | +| 144 | sin_Sinh | 3.37e+07 | 7.96e+08 | 4.98e+09 | 1.15e+06 | Sinhala | sin | | si | si | +| 145 | slk_Latn | 4.94e+08 | 1.06e+10 | 7.04e+10 | 2.18e+07 | Slovak | slk | | sk | sk | +| 146 | slv_Latn | 2.39e+08 | 5.44e+09 | 3.53e+10 | 1.03e+07 | Slovenian | slv | | sl | sl | +| 147 | smo_Latn | 1.01e+06 | 3.71e+07 | 1.86e+08 | 4.59e+04 | Samoan | smo | | sm | sm | +| 148 | sna_Latn | 1.20e+06 | 2.39e+07 | 1.93e+08 | 6.11e+04 | Shona | sna | | sn | sn | +| 149 | snd_Arab | 2.83e+06 | 8.95e+07 | 4.29e+08 | 1.00e+05 | Sindhi | snd | | sd | sd | +| 150 | som_Latn | 1.64e+07 | 3.89e+08 | 2.56e+09 | 9.66e+05 | Somali | som | | so | so | +| 151 | sot_Latn | 1.08e+06 | 3.10e+07 | 1.72e+08 | 4.39e+04 | Southern Sotho | sot | | st | st | +| 152 | spa_Latn | 1.21e+10 | 3.22e+11 | 1.95e+12 | 5.03e+08 | Spanish | spa | | es | es | +| 153 | srd_Latn | 9.17e+05 | 2.39e+07 | 1.49e+08 | 5.38e+04 | Sardinian | srd | | sc | sc | +| 154 | srp_Cyrl | 9.38e+07 | 2.52e+09 | 1.62e+10 | 4.12e+06 | Serbian | srp | hbs | sr | sr | +| 155 | ssw_Latn | 6.21e+04 | 9.94e+05 | 8.82e+06 | 2.04e+03 | Swati | ssw | | ss | ss | +| 156 | sun_Latn | 3.24e+06 | 6.96e+07 | 4.75e+08 | 1.15e+05 | Sundanese | sun | | su | su | +| 157 | swe_Latn | 1.76e+09 | 4.01e+10 | 2.51e+11 | 6.68e+07 | Swedish | swe | | sv | sv | +| 158 | swh_Latn | 3.43e+07 | 7.18e+08 | 4.66e+09 | 1.37e+06 | Swahili (individual language) | swh | swa | | sw | +| 159 | szl_Latn | 6.37e+05 | 1.47e+07 | 1.04e+08 | 4.09e+04 | Silesian | szl | | | | +| 160 | tam_Taml | 1.69e+08 | 2.98e+09 | 2.62e+10 | 6.11e+06 | Tamil | tam | | ta | ta | +| 161 | taq_Latn | 1.39e+04 | 1.54e+06 | 8.84e+06 | 1.75e+03 | Tamasheq | taq | tmh | | | +| 162 | tat_Cyrl | 1.34e+07 | 2.97e+08 | 2.16e+09 | 6.31e+05 | Tatar | tat | | tt | tt | +| 163 | tel_Telu | 3.92e+07 | 8.35e+08 | 6.50e+09 | 2.06e+06 | Telugu | tel | | te | te | +| 164 | tgk_Cyrl | 2.48e+07 | 6.25e+08 | 4.59e+09 | 1.26e+06 | Tajik | tgk | | tg | tg | +| 165 | tgl_Latn | 5.29e+07 | 1.35e+09 | 8.13e+09 | 1.87e+06 | Tagalog | tgl | | tl | tl | +| 166 | tha_Thai | 3.39e+08 | 3.51e+09 | 6.00e+10 | 1.77e+07 | Thai | tha | | th | th | +| 167 | tir_Ethi | 1.13e+06 | 3.67e+07 | 1.82e+08 | 6.47e+04 | Tigrinya | tir | | ti | ti | +| 168 | tpi_Latn | 2.82e+05 | 1.25e+07 | 6.45e+07 | 1.40e+04 | Tok Pisin | tpi | | | | +| 169 | tsn_Latn | 1.32e+05 | 5.27e+06 | 2.77e+07 | 6.05e+03 | Tswana | tsn | | tn | tn | +| 170 | tso_Latn | 2.21e+05 | 8.67e+06 | 4.93e+07 | 1.10e+04 | Tsonga | tso | | ts | ts | +| 171 | tuk_Latn | 3.36e+06 | 7.07e+07 | 5.70e+08 | 1.71e+05 | Turkmen | tuk | | tk | tk | +| 172 | tum_Latn | 9.90e+04 | 2.88e+06 | 2.11e+07 | 4.38e+03 | Tumbuka | tum | | | | +| 173 | tur_Latn | 2.58e+09 | 5.17e+10 | 3.90e+11 | 1.17e+08 | Turkish | tur | | tr | tr | +| 174 | twi_Latn | 1.26e+05 | 4.70e+06 | 2.42e+07 | 5.86e+03 | Twi | twi | aka | tw | tw | +| 175 | uig_Arab | 8.98e+06 | 2.24e+08 | 1.75e+09 | 4.42e+05 | Uighur | uig | | ug | ug | +| 176 | ukr_Cyrl | 1.17e+09 | 2.52e+10 | 1.83e+11 | 4.74e+07 | Ukrainian | ukr | | uk | uk | +| 177 | umb_Latn | 5.99e+04 | 2.43e+06 | 1.54e+07 | 2.47e+03 | Umbundu | umb | | | | +| 178 | urd_Arab | 5.06e+07 | 2.13e+09 | 1.00e+10 | 3.19e+06 | Urdu | urd | | ur | ur | +| 179 | uzn_Latn | 1.48e+07 | 3.51e+08 | 2.85e+09 | 7.07e+05 | Northern Uzbek | uzn | uzb | | uz | +| 180 | vec_Latn | 1.58e+06 | 3.53e+07 | 2.18e+08 | 8.48e+04 | Venetian | vec | | | | +| 181 | vie_Latn | 3.02e+09 | 8.32e+10 | 3.80e+11 | 1.01e+08 | Vietnamese | vie | | vi | vi | +| 182 | war_Latn | 2.01e+05 | 5.89e+06 | 3.56e+07 | 1.39e+04 | Waray (Philippines) | war | | | | +| 183 | wol_Latn | 1.62e+05 | 5.46e+06 | 2.75e+07 | 5.68e+03 | Wolof | wol | | wo | wo | +| 184 | xho_Latn | 1.82e+06 | 3.03e+07 | 2.59e+08 | 6.31e+04 | Xhosa | xho | | xh | xh | +| 185 | ydd_Hebr | 2.94e+06 | 7.75e+07 | 4.58e+08 | 1.28e+05 | Eastern Yiddish | ydd | yid | | yi | +| 186 | yor_Latn | 1.47e+06 | 4.28e+07 | 2.18e+08 | 6.61e+04 | Yoruba | yor | | yo | yo | +| 187 | yue_Hant | 1.24e+06 | 3.27e+06 | 7.43e+07 | 6.13e+04 | Yue Chinese | yue | zho | | zh | +| 188 | zho_Hans | 4.24e+10 | 7.40e+10 | 2.35e+12 | 1.25e+09 | Chinese | zho | | zh | zh | +| 189 | zho_Hant | 4.48e+09 | 9.51e+09 | 2.87e+11 | 1.57e+08 | Chinese | zho | | zh | zh | +| 190 | zsm_Latn | 5.80e+08 | 1.15e+10 | 7.84e+10 | 1.84e+07 | Standard Malay | zsm | msa | | ms | +| 191 | zul_Latn | 2.71e+06 | 4.44e+07 | 3.81e+08 | 1.14e+05 | Zulu | zul | | zu | zu |" +mozilla-foundation/common_voice_16_0,"{""pretty_name"": ""Common Voice Corpus 16"", ""annotations_creators"": [""crowdsourced""], ""language_creators"": [""crowdsourced""], ""language"": [""ab"", ""af"", ""am"", ""ar"", ""as"", ""ast"", ""az"", ""ba"", ""bas"", ""be"", ""bg"", ""bn"", ""br"", ""ca"", ""ckb"", ""cnh"", ""cs"", ""cv"", ""cy"", ""da"", ""de"", ""dv"", ""dyu"", ""el"", ""en"", ""eo"", ""es"", ""et"", ""eu"", ""fa"", ""fi"", ""fr"", ""fy"", ""ga"", ""gl"", ""gn"", ""ha"", ""he"", ""hi"", ""hsb"", ""hu"", ""hy"", ""ia"", ""id"", ""ig"", ""is"", ""it"", ""ja"", ""ka"", ""kab"", ""kk"", ""kmr"", ""ko"", ""ky"", ""lg"", ""lij"", ""lo"", ""lt"", ""ltg"", ""lv"", ""mdf"", ""mhr"", ""mk"", ""ml"", ""mn"", ""mr"", ""mrj"", ""mt"", ""myv"", ""nan"", ""ne"", ""nhi"", ""nl"", ""nn"", ""oc"", ""or"", ""os"", ""pa"", ""pl"", ""ps"", ""pt"", ""quy"", ""rm"", ""ro"", ""ru"", ""rw"", ""sah"", ""sat"", ""sc"", ""sk"", ""skr"", ""sl"", ""sq"", ""sr"", ""sv"", ""sw"", ""ta"", ""te"", ""th"", ""ti"", ""tig"", ""tk"", ""tok"", ""tr"", ""tt"", ""tw"", ""ug"", ""uk"", ""ur"", ""uz"", ""vi"", ""vot"", ""yi"", ""yo"", ""yue"", ""zgh"", ""zh""], ""language_bcp47"": [""zh-CN"", ""zh-HK"", ""zh-TW"", ""sv-SE"", ""rm-sursilv"", ""rm-vallader"", ""pa-IN"", ""nn-NO"", ""ne-NP"", ""nan-tw"", ""hy-AM"", ""ga-IE"", ""fy-NL""], ""license"": [""cc0-1.0""], ""multilinguality"": [""multilingual""], ""paperswithcode_id"": ""common-voice"", ""extra_gated_prompt"": ""By clicking on \u201cAccess repository\u201d below, you also agree to not attempt to determine the identity of speakers in the Common Voice dataset.""}","# Dataset Card for Common Voice Corpus 16 + +## Table of Contents +- [Dataset Description](#dataset-description) + - [Dataset Summary](#dataset-summary) + - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) + - [Languages](#languages) +- [Dataset Structure](#dataset-structure) + - [Data Instances](#data-instances) + - [Data Fields](#data-fields) + - [Data Splits](#data-splits) +- [Dataset Creation](#dataset-creation) + - [Curation Rationale](#curation-rationale) + - [Source Data](#source-data) + - [Annotations](#annotations) + - [Personal and Sensitive Information](#personal-and-sensitive-information) +- [Considerations for Using the Data](#considerations-for-using-the-data) + - [Social Impact of Dataset](#social-impact-of-dataset) + - [Discussion of Biases](#discussion-of-biases) + - [Other Known Limitations](#other-known-limitations) +- [Additional Information](#additional-information) + - [Dataset Curators](#dataset-curators) + - [Licensing Information](#licensing-information) + - [Citation Information](#citation-information) + - [Contributions](#contributions) + +## Dataset Description + +- **Homepage:** https://commonvoice.mozilla.org/en/datasets +- **Repository:** https://github.com/common-voice/common-voice +- **Paper:** https://arxiv.org/abs/1912.06670 +- **Leaderboard:** https://paperswithcode.com/dataset/common-voice +- **Point of Contact:** [Vaibhav Srivastav](mailto:vaibhav@huggingface.co) + +### Dataset Summary + +The Common Voice dataset consists of a unique MP3 and corresponding text file. +Many of the 30328 recorded hours in the dataset also include demographic metadata like age, sex, and accent +that can help improve the accuracy of speech recognition engines. + +The dataset currently consists of 19673 validated hours in 120 languages, but more voices and languages are always added. +Take a look at the [Languages](https://commonvoice.mozilla.org/en/languages) page to request a language or start contributing. + +### Languages + +``` +Abkhaz, Afrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Asturian, Azerbaijani, Basaa, Bashkir, Basque, Belarusian, Bengali, Breton, Bulgarian, Cantonese, Catalan, Central Kurdish, Chinese (China), Chinese (Hong Kong), Chinese (Taiwan), Chuvash, Czech, Danish, Dhivehi, Dioula, Dutch, English, Erzya, Esperanto, Estonian, Finnish, French, Frisian, Galician, Georgian, German, Greek, Guarani, Hakha Chin, Hausa, Hebrew, Hill Mari, Hindi, Hungarian, Icelandic, Igbo, Indonesian, Interlingua, Irish, Italian, Japanese, Kabyle, Kazakh, Kinyarwanda, Korean, Kurmanji Kurdish, Kyrgyz, Lao, Latgalian, Latvian, Ligurian, Lithuanian, Luganda, Macedonian, Malayalam, Maltese, Marathi, Meadow Mari, Moksha, Mongolian, Nepali, Norwegian Nynorsk, Occitan, Odia, Ossetian, Pashto, Persian, Polish, Portuguese, Punjabi, Quechua Chanka, Romanian, Romansh Sursilvan, Romansh Vallader, Russian, Sakha, Santali (Ol Chiki), Saraiki, Sardinian, Serbian, Slovak, Slovenian, Sorbian, Upper, Spanish, Swahili, Swedish, Taiwanese (Minnan), Tamazight, Tamil, Tatar, Telugu, Thai, Tigre, Tigrinya, Toki Pona, Turkish, Turkmen, Twi, Ukrainian, Urdu, Uyghur, Uzbek, Vietnamese, Votic, Welsh, Western Sierra Puebla Nahuatl, Yiddish, Yoruba +``` + +## How to use + +The `datasets` library allows you to load and pre-process your dataset in pure Python, at scale. The dataset can be downloaded and prepared in one call to your local drive by using the `load_dataset` function. + +For example, to download the Hindi config, simply specify the corresponding language config name (i.e., ""hi"" for Hindi): +```python +from datasets import load_dataset + +cv_16 = load_dataset(""mozilla-foundation/common_voice_16_0"", ""hi"", split=""train"") +``` + +Using the datasets library, you can also stream the dataset on-the-fly by adding a `streaming=True` argument to the `load_dataset` function call. Loading a dataset in streaming mode loads individual samples of the dataset at a time, rather than downloading the entire dataset to disk. +```python +from datasets import load_dataset + +cv_16 = load_dataset(""mozilla-foundation/common_voice_16_0"", ""hi"", split=""train"", streaming=True) + +print(next(iter(cv_16))) +``` + +*Bonus*: create a [PyTorch dataloader](https://huggingface.co/docs/datasets/use_with_pytorch) directly with your own datasets (local/streamed). + +### Local + +```python +from datasets import load_dataset +from torch.utils.data.sampler import BatchSampler, RandomSampler + +cv_16 = load_dataset(""mozilla-foundation/common_voice_16_0"", ""hi"", split=""train"") + +batch_sampler = BatchSampler(RandomSampler(cv_16), batch_size=32, drop_last=False) +dataloader = DataLoader(cv_16, batch_sampler=batch_sampler) +``` + +### Streaming + +```python +from datasets import load_dataset +from torch.utils.data import DataLoader + +cv_16 = load_dataset(""mozilla-foundation/common_voice_16_0"", ""hi"", split=""train"") +dataloader = DataLoader(cv_16, batch_size=32) +``` + +To find out more about loading and preparing audio datasets, head over to [hf.co/blog/audio-datasets](https://huggingface.co/blog/audio-datasets). + +### Example scripts + +Train your own CTC or Seq2Seq Automatic Speech Recognition models on Common Voice 16 with `transformers` - [here](https://github.com/huggingface/transformers/tree/main/examples/pytorch/speech-recognition). + +## Dataset Structure + +### Data Instances + +A typical data point comprises the `path` to the audio file and its `sentence`. +Additional fields include `accent`, `age`, `client_id`, `up_votes`, `down_votes`, `gender`, `locale` and `segment`. + +```python +{ + 'client_id': 'd59478fbc1ee646a28a3c652a119379939123784d99131b865a89f8b21c81f69276c48bd574b81267d9d1a77b83b43e6d475a6cfc79c232ddbca946ae9c7afc5', + 'path': 'et/clips/common_voice_et_18318995.mp3', + 'audio': { + 'path': 'et/clips/common_voice_et_18318995.mp3', + 'array': array([-0.00048828, -0.00018311, -0.00137329, ..., 0.00079346, 0.00091553, 0.00085449], dtype=float32), + 'sampling_rate': 48000 + }, + 'sentence': 'Tasub kokku saada inimestega, keda tunned juba ammust ajast saati.', + 'up_votes': 2, + 'down_votes': 0, + 'age': 'twenties', + 'gender': 'male', + 'accent': '', + 'locale': 'et', + 'segment': '' +} +``` + +### Data Fields + +`client_id` (`string`): An id for which client (voice) made the recording + +`path` (`string`): The path to the audio file + +`audio` (`dict`): A dictionary containing the path to the downloaded audio file, the decoded audio array, and the sampling rate. Note that when accessing the audio column: `dataset[0][""audio""]` the audio file is automatically decoded and resampled to `dataset.features[""audio""].sampling_rate`. Decoding and resampling of a large number of audio files might take a significant amount of time. Thus it is important to first query the sample index before the `""audio""` column, *i.e.* `dataset[0][""audio""]` should **always** be preferred over `dataset[""audio""][0]`. + +`sentence` (`string`): The sentence the user was prompted to speak + +`up_votes` (`int64`): How many upvotes the audio file has received from reviewers + +`down_votes` (`int64`): How many downvotes the audio file has received from reviewers + +`age` (`string`): The age of the speaker (e.g. `teens`, `twenties`, `fifties`) + +`gender` (`string`): The gender of the speaker + +`accent` (`string`): Accent of the speaker + +`locale` (`string`): The locale of the speaker + +`segment` (`string`): Usually an empty field + +### Data Splits + +The speech material has been subdivided into portions for dev, train, test, validated, invalidated, reported and other. + +The validated data is data that has been validated with reviewers and received upvotes that the data is of high quality. + +The invalidated data is data has been invalidated by reviewers +and received downvotes indicating that the data is of low quality. + +The reported data is data that has been reported, for different reasons. + +The other data is data that has not yet been reviewed. + +The dev, test, train are all data that has been reviewed, deemed of high quality and split into dev, test and train. + +## Data Preprocessing Recommended by Hugging Face + +The following are data preprocessing steps advised by the Hugging Face team. They are accompanied by an example code snippet that shows how to put them to practice. + +Many examples in this dataset have trailing quotations marks, e.g _“the cat sat on the mat.“_. These trailing quotation marks do not change the actual meaning of the sentence, and it is near impossible to infer whether a sentence is a quotation or not a quotation from audio data alone. In these cases, it is advised to strip the quotation marks, leaving: _the cat sat on the mat_. + +In addition, the majority of training sentences end in punctuation ( . or ? or ! ), whereas just a small proportion do not. In the dev set, **almost all** sentences end in punctuation. Thus, it is recommended to append a full-stop ( . ) to the end of the small number of training examples that do not end in punctuation. + +```python +from datasets import load_dataset + +ds = load_dataset(""mozilla-foundation/common_voice_16_0"", ""en"", use_auth_token=True) + +def prepare_dataset(batch): + """"""Function to preprocess the dataset with the .map method"""""" + transcription = batch[""sentence""] + + if transcription.startswith('""') and transcription.endswith('""'): + # we can remove trailing quotation marks as they do not affect the transcription + transcription = transcription[1:-1] + + if transcription[-1] not in [""."", ""?"", ""!""]: + # append a full-stop to sentences that do not end in punctuation + transcription = transcription + ""."" + + batch[""sentence""] = transcription + + return batch + +ds = ds.map(prepare_dataset, desc=""preprocess dataset"") +``` + +## Dataset Creation + +### Curation Rationale + +[Needs More Information] + +### Source Data + +#### Initial Data Collection and Normalization + +[Needs More Information] + +#### Who are the source language producers? + +[Needs More Information] + +### Annotations + +#### Annotation process + +[Needs More Information] + +#### Who are the annotators? + +[Needs More Information] + +### Personal and Sensitive Information + +The dataset consists of people who have donated their voice online. You agree to not attempt to determine the identity of speakers in the Common Voice dataset. + +## Considerations for Using the Data + +### Social Impact of Dataset + +The dataset consists of people who have donated their voice online. You agree to not attempt to determine the identity of speakers in the Common Voice dataset. + +### Discussion of Biases + +[More Information Needed] + +### Other Known Limitations + +[More Information Needed] + +## Additional Information + +### Dataset Curators + +[More Information Needed] + +### Licensing Information + +Public Domain, [CC-0](https://creativecommons.org/share-your-work/public-domain/cc0/) + +### Citation Information + +``` +@inproceedings{commonvoice:2020, + author = {Ardila, R. and Branson, M. and Davis, K. and Henretty, M. and Kohler, M. and Meyer, J. and Morais, R. and Saunders, L. and Tyers, F. M. and Weber, G.}, + title = {Common Voice: A Massively-Multilingual Speech Corpus}, + booktitle = {Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)}, + pages = {4211--4215}, + year = 2020 +} +```" +esdurmus/wiki_lingua,"{""annotations_creators"": [""crowdsourced""], ""language_creators"": [""crowdsourced""], ""language"": [""ar"", ""cs"", ""de"", ""en"", ""es"", ""fr"", ""hi"", ""id"", ""it"", ""ja"", ""ko"", ""nl"", ""pt"", ""ru"", ""th"", ""tr"", ""vi"", ""zh""], ""license"": [""cc-by-3.0""], ""multilinguality"": [""multilingual""], ""size_categories"": [""10K +- **Repository:** +- **Paper:** +- **Leaderboard:** N/A +- **Point of Contact:** Adithya Pratapa + +### Dataset Summary + +XLEL-WD is a multilingual event linking dataset. This dataset repo contains mention references in multilingual Wikipedia/Wikinews articles to event items from Wikidata. + +The descriptions for Wikidata event items were collected from the corresponding Wikipedia articles. Download the event dictionary from [adithya7/xlel_wd_dictionary](https://huggingface.co/datasets/adithya7/xlel_wd_dictionary). + +### Supported Tasks and Leaderboards + +This dataset can be used for the task of event linking. There are two variants of the task, multilingual and crosslingual. + +- Multilingual linking: mention and the event descriptions are in the same language. +- Crosslingual linking: the event descriptions are only available in English. + +### Languages + +This dataset contains text from 44 languages. The language names and their ISO 639-1 codes are listed below. For details on the dataset distribution for each language, refer to the original paper. + +| Language | Code | Language | Code | Language | Code | Language | Code | +| -------- | ---- | -------- | ---- | -------- | ---- | -------- | ---- | +| Afrikaans | af | Arabic | ar | Belarusian | be | Bulgarian | bg | +| Bengali | bn | Catalan | ca | Czech | cs | Danish | da | +| German | de | Greek | el | English | en | Spanish | es | +| Persian | fa | Finnish | fi | French | fr | Hebrew | he | +| Hindi | hi | Hungarian | hu | Indonesian | id | Italian | it | +| Japanese | ja | Korean | ko | Malayalam | ml | Marathi | mr | +| Malay | ms | Dutch | nl | Norwegian | no | Polish | pl | +| Portuguese | pt | Romanian | ro | Russian | ru | Sinhala | si | +| Slovak | sk | Slovene | sl | Serbian | sr | Swedish | sv | +| Swahili | sw | Tamil | ta | Telugu | te | Thai | th | +| Turkish | tr | Ukrainian | uk | Vietnamese | vi | Chinese | zh | + +## Dataset Structure + +### Data Instances + +Each instance in the `train.jsonl`, `dev.jsonl` and `test.jsonl` files follow the below template. + +```json +{ + ""context_left"": ""Minibaev's first major international medal came in the men's synchronized 10 metre platform event at the "", + ""mention"": ""2010 European Championships"", + ""context_right"": ""."", + ""context_lang"": ""en"", + ""label_id"": ""830917"", +} +``` + +### Data Fields + +| Field | Meaning | +| ----- | ------- | +| `mention` | text span of the mention | +| `context_left` | left paragraph context from the document | +| `context_right` | right paragraph context from the document | +| `context_lang` | language of the context (and mention) | +| `context_title` | document title of the mention (only Wikinews subset) | +| `context_date` | document publication date of the mention (only Wikinews subset) | +| `label_id` | Wikidata label ID for the event. E.g. 830917 refers to Q830917 from Wikidata. | + +### Data Splits + +The Wikipedia-based corpus has three splits. This is a zero-shot evaluation setup. + +| | Train | Dev | Test | Total | +| ---- | :-----: | :---: | :----: | :-----: | +| Events | 8653 | 1090 | 1204 | 10947 | +| Event Sequences | 6758 | 844 | 846 | 8448 | +| Mentions | 1.44M | 165K | 190K | 1.8M | +| Languages | 44 | 44 | 44 | 44 | + +The Wikinews-based evaluation set has two variants, one for cross-domain evaluation and another for zero-shot evaluation. + +| | (Cross-domain) Test | (Zero-shot) Test | +| --- | :------------------: | :-----: | +| Events | 802 | 149 | +| Mentions | 2562 | 437 | +| Languages | 27 | 21 | + +## Dataset Creation + +### Curation Rationale + +This dataset helps address the task of event linking. KB linking is extensively studied for entities, but its unclear if the same methodologies can be extended for linking mentions to events from KB. We use Wikidata as our KB, as it allows for linking mentions from multilingual Wikipedia and Wikinews articles. + +### Source Data + +#### Initial Data Collection and Normalization + +First, we utilize spatial & temporal properties from Wikidata to identify event items. Second, we identify corresponding multilingual Wikipedia pages for each Wikidata event item. Third, we pool hyperlinks from multilingual Wikipedia & Wikinews articles to these event items. + +#### Who are the source language producers? + +The documents in XLEL-WD are written by Wikipedia and Wikinews contributors in respective languages. + +### Annotations + +#### Annotation process + +This dataset was originally collected automatically from Wikipedia, Wikinews and Wikidata. It was post-processed to improve data quality. + +#### Who are the annotators? + +The annotations in XLEL-WD (hyperlinks from Wikipedia/Wikinews to Wikidata) are added the original Wiki contributors. + +### Personal and Sensitive Information + +[More Information Needed] + +## Considerations for Using the Data + +### Social Impact of Dataset + +[More Information Needed] + +### Discussion of Biases + +[More Information Needed] + +### Other Known Limitations + +XLEL-WD v1.0.0 mostly caters to eventive nouns from Wikidata. It does not include any links to other event items from Wikidata such as disease outbreak (Q3241045), military offensive (Q2001676) and war (Q198). + +## Additional Information + +### Dataset Curators + +The dataset was curated by Adithya Pratapa, Rishubh Gupta and Teruko Mitamura. The code for collecting the dataset is available at [Github:xlel-wd](https://github.com/adithya7/xlel-wd). + +### Licensing Information + +XLEL-WD dataset is released under [CC-BY-4.0 license](https://creativecommons.org/licenses/by/4.0/). + +### Citation Information + +```bib +@article{pratapa-etal-2022-multilingual, + title = {Multilingual Event Linking to Wikidata}, + author = {Pratapa, Adithya and Gupta, Rishubh and Mitamura, Teruko}, + publisher = {arXiv}, + year = {2022}, + url = {https://arxiv.org/abs/2204.06535}, +} +``` + +### Contributions + +Thanks to [@adithya7](https://github.com/adithya7) for adding this dataset." +Helsinki-NLP/opus_ubuntu,"{""annotations_creators"": [""crowdsourced"", ""expert-generated""], ""language_creators"": [""found""], ""language"": [""ace"", ""af"", ""ak"", ""am"", ""an"", ""ang"", ""ar"", ""ary"", ""as"", ""ast"", ""az"", ""ba"", ""bal"", ""be"", ""bem"", ""ber"", ""bg"", ""bho"", ""bn"", ""bo"", ""br"", ""brx"", ""bs"", ""bua"", ""byn"", ""ca"", ""ce"", ""ceb"", ""chr"", ""ckb"", ""co"", ""crh"", ""cs"", ""csb"", ""cv"", ""cy"", ""da"", ""de"", ""dsb"", ""dv"", ""dz"", ""el"", ""en"", ""eo"", ""es"", ""et"", ""eu"", ""fa"", ""ff"", ""fi"", ""fil"", ""fo"", ""fr"", ""frm"", ""frp"", ""fur"", ""fy"", ""ga"", ""gd"", ""gl"", ""gn"", ""grc"", ""gu"", ""guc"", ""gv"", ""ha"", ""haw"", ""he"", ""hi"", ""hil"", ""hne"", ""hr"", ""hsb"", ""ht"", ""hu"", ""hy"", ""ia"", ""id"", ""ig"", ""io"", ""is"", ""it"", ""iu"", ""ja"", ""jbo"", ""jv"", ""ka"", ""kab"", ""kg"", ""kk"", ""kl"", ""km"", ""kn"", ""ko"", ""kok"", ""ks"", ""ksh"", ""ku"", ""kw"", ""ky"", ""la"", ""lb"", ""lg"", ""li"", ""lij"", ""lld"", ""ln"", ""lo"", ""lt"", ""ltg"", ""lv"", ""mai"", ""mg"", ""mh"", ""mhr"", ""mi"", ""miq"", ""mk"", ""ml"", ""mn"", ""mr"", ""ms"", ""mt"", ""mus"", ""my"", ""nan"", ""nap"", ""nb"", ""nds"", ""ne"", ""nhn"", ""nl"", ""nn"", ""no"", ""nso"", ""ny"", ""oc"", ""om"", ""or"", ""os"", ""pa"", ""pam"", ""pap"", ""pl"", ""pms"", ""pmy"", ""ps"", ""pt"", ""qu"", ""rm"", ""ro"", ""rom"", ""ru"", ""rw"", ""sa"", ""sc"", ""sco"", ""sd"", ""se"", ""shn"", ""shs"", ""si"", ""sk"", ""sl"", ""sm"", ""sml"", ""sn"", ""so"", ""son"", ""sq"", ""sr"", ""st"", ""sv"", ""sw"", ""syr"", ""szl"", ""ta"", ""te"", ""tet"", ""tg"", ""th"", ""ti"", ""tk"", ""tl"", ""tlh"", ""tr"", ""trv"", ""ts"", ""tt"", ""ug"", ""uk"", ""ur"", ""uz"", ""ve"", ""vec"", ""vi"", ""wa"", ""wae"", ""wo"", ""xal"", ""xh"", ""yi"", ""yo"", ""zh"", ""zu"", ""zza""], ""license"": [""bsd-3-clause""], ""multilinguality"": [""multilingual""], ""size_categories"": [""10K1)] + df['chosen'] = df.apply(lambda x:x['text'][np.argmin(x['rank'])],axis=1) + df['rejected'] = df.apply(lambda x:x['text'][np.argmax(x['rank'])],axis=1) + d[split]=Dataset.from_pandas(df[['lang','parent_id','prompt','chosen','rejected']],preserve_index=False) + +DatasetDict(d).push_to_hub('tasksource/oasst1_pairwise_rlhf_reward') +```" +castorini/mr-tydi-corpus,"{""language"": [""ar"", ""bn"", ""en"", ""fi"", ""id"", ""fi"", ""ja"", ""ko"", ""ru"", ""sw"", ""te"", ""th""], ""multilinguality"": [""multilingual""], ""task_categories"": [""text-retrieval""], ""license"": ""apache-2.0""}","# Dataset Summary +Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages. It is designed for monolingual retrieval, specifically to evaluate ranking with learned dense representations. + +This dataset stores documents of Mr. TyDi. To access the queries and judgments, please refer to [castorini/mr-tydi](https://huggingface.co/datasets/castorini/mr-tydi). + +# Dataset Structure +The only configuration here is the `language`. As all three folds (train, dev and test) share the same corpus, there is only one fold 'train' under each language, unlike [castorini/mr-tydi](https://huggingface.co/datasets/castorini/mr-tydi). + +An example of document data entry looks as follows: +``` +{ + 'docid': '25#0', + 'title': 'Autism', + 'text': 'Autism is a developmental disorder characterized by difficulties with social interaction and communication, ...' +} +``` + +# Load Dataset +An example to load the dataset: +``` +language = 'english' +dataset = load_dataset('castorini/mr-tydi-corpus', language, 'train') +``` + +# Citation Information +``` +@article{mrtydi, + title={{Mr. TyDi}: A Multi-lingual Benchmark for Dense Retrieval}, + author={Xinyu Zhang and Xueguang Ma and Peng Shi and Jimmy Lin}, + year={2021}, + journal={arXiv:2108.08787}, +} +```" +Helsinki-NLP/opus_paracrawl,"{""annotations_creators"": [""found""], ""language_creators"": [""found""], ""language"": [""bg"", ""ca"", ""cs"", ""da"", ""de"", ""el"", ""en"", ""es"", ""et"", ""eu"", ""fi"", ""fr"", ""ga"", ""gl"", ""hr"", ""hu"", ""is"", ""it"", ""km"", ""ko"", ""lt"", ""lv"", ""mt"", ""my"", ""nb"", ""ne"", ""nl"", ""nn"", ""pl"", ""pt"", ""ro"", ""ru"", ""si"", ""sk"", ""sl"", ""so"", ""sv"", ""sw"", ""tl"", ""uk"", ""zh""], ""license"": [""cc0-1.0""], ""multilinguality"": [""multilingual""], ""size_categories"": [""100K>> from datasets import load_dataset + +>>> ds = load_dataset(""beomi/KoAlpaca-v1.1a"", split=""train"") +>>> ds +Dataset({ + features: ['instruction', 'input', 'output'], + num_rows: 21155 +}) +``` + + +```python +>>> ds[0] +{'instruction': '양파는 어떤 식물 부위인가요? 그리고 고구마는 뿌리인가요?', + 'output': '양파는 잎이 아닌 식물의 줄기 부분입니다. 고구마는 식물의 뿌리 부분입니다. \n\n식물의 부위의 구분에 대해 궁금해하는 분이라면 분명 이 질문에 대한 답을 찾고 있을 것입니다. 양파는 잎이 아닌 줄기 부분입니다. 고구마는 다른 질문과 답변에서 언급된 것과 같이 뿌리 부분입니다. 따라서, 양파는 식물의 줄기 부분이 되고, 고구마는 식물의 뿌리 부분입니다.\n\n 덧붙이는 답변: 고구마 줄기도 볶아먹을 수 있나요? \n\n고구마 줄기도 식용으로 볶아먹을 수 있습니다. 하지만 줄기 뿐만 아니라, 잎, 씨, 뿌리까지 모든 부위가 식용으로 활용되기도 합니다. 다만, 한국에서는 일반적��로 뿌리 부분인 고구마를 주로 먹습니다.', + 'url': 'https://kin.naver.com/qna/detail.naver?d1id=11&dirId=1116&docId=55320268'} +```" +Helsinki-NLP/opus_gnome,"{""annotations_creators"": [""found""], ""language_creators"": [""found""], ""language"": [""af"", ""am"", ""an"", ""ang"", ""ar"", ""as"", ""ast"", ""az"", ""bal"", ""be"", ""bem"", ""bg"", ""bn"", ""bo"", ""br"", ""brx"", ""bs"", ""ca"", ""crh"", ""cs"", ""csb"", ""cy"", ""da"", ""de"", ""dv"", ""dz"", ""el"", ""en"", ""eo"", ""es"", ""et"", ""eu"", ""fa"", ""fi"", ""fo"", ""fr"", ""fur"", ""fy"", ""ga"", ""gd"", ""gl"", ""gn"", ""gu"", ""gv"", ""ha"", ""he"", ""hi"", ""hr"", ""hu"", ""hy"", ""ia"", ""id"", ""ig"", ""io"", ""is"", ""it"", ""ja"", ""jbo"", ""ka"", ""kg"", ""kk"", ""km"", ""kn"", ""ko"", ""kr"", ""ks"", ""ku"", ""ky"", ""la"", ""lg"", ""li"", ""lo"", ""lt"", ""lv"", ""mai"", ""mg"", ""mi"", ""mk"", ""ml"", ""mn"", ""mr"", ""ms"", ""mt"", ""mus"", ""my"", ""nb"", ""nds"", ""ne"", ""nhn"", ""nl"", ""nn"", ""no"", ""nqo"", ""nr"", ""nso"", ""oc"", ""or"", ""os"", ""pa"", ""pl"", ""ps"", ""pt"", ""quz"", ""ro"", ""ru"", ""rw"", ""si"", ""sk"", ""sl"", ""so"", ""sq"", ""sr"", ""st"", ""sv"", ""sw"", ""szl"", ""ta"", ""te"", ""tg"", ""th"", ""tk"", ""tl"", ""tr"", ""ts"", ""tt"", ""tyj"", ""ug"", ""uk"", ""ur"", ""uz"", ""vi"", ""wa"", ""xh"", ""yi"", ""yo"", ""zh"", ""zu""], ""license"": [""unknown""], ""multilinguality"": [""multilingual""], ""size_categories"": [""10K + + + +## Contact + +- Discord [Open Assistant Discord Server](https://ykilcher.com/open-assistant-discord) +- GitHub: [LAION-AI/Open-Assistant](https://github.com/LAION-AI/Open-Assistant) +- E-Mail: [open-assistant@laion.ai](mailto:open-assistant@laion.ai)" +Babelscape/SREDFM,"{""dataset_info"": [{""config_name"": ""ar"", ""features"": [{""name"": ""docid"", ""dtype"": ""string""}, {""name"": ""title"", ""dtype"": ""string""}, {""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""entities"", ""list"": [{""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""surfaceform"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""start"", ""dtype"": ""int32""}, {""name"": ""end"", ""dtype"": ""int32""}]}, {""name"": ""relations"", ""list"": [{""name"": ""subject"", ""dtype"": ""int32""}, {""name"": ""predicate"", ""dtype"": ""string""}, {""name"": ""object"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 659105981, ""num_examples"": 499568}, {""name"": ""test"", ""num_bytes"": 9015516, ""num_examples"": 4387}, {""name"": ""validation"", ""num_bytes"": 7406509, ""num_examples"": 3783}], ""download_size"": 3651950669, ""dataset_size"": 675528006}, {""config_name"": ""ca"", ""features"": [{""name"": ""docid"", ""dtype"": ""string""}, {""name"": ""title"", ""dtype"": ""string""}, {""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""entities"", ""list"": [{""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""surfaceform"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""start"", ""dtype"": ""int32""}, {""name"": ""end"", ""dtype"": ""int32""}]}, {""name"": ""relations"", ""list"": [{""name"": ""subject"", ""dtype"": ""int32""}, {""name"": ""predicate"", ""dtype"": ""string""}, {""name"": ""object"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 406179567, ""num_examples"": 294856}, {""name"": ""test"", ""num_bytes"": 5378789, ""num_examples"": 2541}, {""name"": ""validation"", ""num_bytes"": 3136722, ""num_examples"": 1532}], ""download_size"": 1513026644, ""dataset_size"": 414695078}, {""config_name"": ""de"", ""features"": [{""name"": ""docid"", ""dtype"": ""string""}, {""name"": ""title"", ""dtype"": ""string""}, {""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""entities"", ""list"": [{""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""surfaceform"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""start"", ""dtype"": ""int32""}, {""name"": ""end"", ""dtype"": ""int32""}]}, {""name"": ""relations"", ""list"": [{""name"": ""subject"", ""dtype"": ""int32""}, {""name"": ""predicate"", ""dtype"": ""string""}, {""name"": ""object"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1288274676, ""num_examples"": 1049967}, {""name"": ""test"", ""num_bytes"": 10773087, ""num_examples"": 5649}, {""name"": ""validation"", ""num_bytes"": 8955886, ""num_examples"": 4994}], ""download_size"": 4521091910, ""dataset_size"": 1308003649}, {""config_name"": ""el"", ""features"": [{""name"": ""docid"", ""dtype"": ""string""}, {""name"": ""title"", ""dtype"": ""string""}, {""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""entities"", ""list"": [{""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""surfaceform"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""start"", ""dtype"": ""int32""}, {""name"": ""end"", ""dtype"": ""int32""}]}, {""name"": ""relations"", ""list"": [{""name"": ""subject"", ""dtype"": ""int32""}, {""name"": ""predicate"", ""dtype"": ""string""}, {""name"": ""object"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 133497910, ""num_examples"": 64221}, {""name"": ""test"", ""num_bytes"": 2364826, ""num_examples"": 861}, {""name"": ""validation"", ""num_bytes"": 1836092, ""num_examples"": 668}], ""download_size"": 579372781, ""dataset_size"": 137698828}, {""config_name"": ""en"", ""features"": [{""name"": ""docid"", ""dtype"": ""string""}, {""name"": ""title"", ""dtype"": ""string""}, {""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""entities"", ""list"": [{""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""surfaceform"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""start"", ""dtype"": ""int32""}, {""name"": ""end"", ""dtype"": ""int32""}]}, {""name"": ""relations"", ""list"": [{""name"": ""subject"", ""dtype"": ""int32""}, {""name"": ""predicate"", ""dtype"": ""string""}, {""name"": ""object"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 3555107736, ""num_examples"": 2701389}, {""name"": ""test"", ""num_bytes"": 13160183, ""num_examples"": 6685}, {""name"": ""validation"", ""num_bytes"": 27692074, ""num_examples"": 13236}], ""download_size"": 11914987368, ""dataset_size"": 3595959993}, {""config_name"": ""es"", ""features"": [{""name"": ""docid"", ""dtype"": ""string""}, {""name"": ""title"", ""dtype"": ""string""}, {""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""entities"", ""list"": [{""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""surfaceform"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""start"", ""dtype"": ""int32""}, {""name"": ""end"", ""dtype"": ""int32""}]}, {""name"": ""relations"", ""list"": [{""name"": ""subject"", ""dtype"": ""int32""}, {""name"": ""predicate"", ""dtype"": ""string""}, {""name"": ""object"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 888914515, ""num_examples"": 702785}, {""name"": ""test"", ""num_bytes"": 16076382, ""num_examples"": 8561}, {""name"": ""validation"", ""num_bytes"": 4621760, ""num_examples"": 2177}], ""download_size"": 3570403740, ""dataset_size"": 909612657}, {""config_name"": ""fr"", ""features"": [{""name"": ""docid"", ""dtype"": ""string""}, {""name"": ""title"", ""dtype"": ""string""}, {""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""entities"", ""list"": [{""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""surfaceform"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""start"", ""dtype"": ""int32""}, {""name"": ""end"", ""dtype"": ""int32""}]}, {""name"": ""relations"", ""list"": [{""name"": ""subject"", ""dtype"": ""int32""}, {""name"": ""predicate"", ""dtype"": ""string""}, {""name"": ""object"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 768697146, ""num_examples"": 870448}, {""name"": ""test"", ""num_bytes"": 5937745, ""num_examples"": 3883}, {""name"": ""validation"", ""num_bytes"": 3233262, ""num_examples"": 2079}], ""download_size"": 3269522484, ""dataset_size"": 777868153}, {""config_name"": ""hi"", ""features"": [{""name"": ""docid"", ""dtype"": ""string""}, {""name"": ""title"", ""dtype"": ""string""}, {""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""entities"", ""list"": [{""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""surfaceform"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""start"", ""dtype"": ""int32""}, {""name"": ""end"", ""dtype"": ""int32""}]}, {""name"": ""relations"", ""list"": [{""name"": ""subject"", ""dtype"": ""int32""}, {""name"": ""predicate"", ""dtype"": ""string""}, {""name"": ""object"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 96926984, ""num_examples"": 51900}, {""name"": ""test"", ""num_bytes"": 1340091, ""num_examples"": 374}, {""name"": ""validation"", ""num_bytes"": 1222098, ""num_examples"": 405}], ""download_size"": 385810623, ""dataset_size"": 99489173}, {""config_name"": ""it"", ""features"": [{""name"": ""docid"", ""dtype"": ""string""}, {""name"": ""title"", ""dtype"": ""string""}, {""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""entities"", ""list"": [{""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""surfaceform"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""start"", ""dtype"": ""int32""}, {""name"": ""end"", ""dtype"": ""int32""}]}, {""name"": ""relations"", ""list"": [{""name"": ""subject"", ""dtype"": ""int32""}, {""name"": ""predicate"", ""dtype"": ""string""}, {""name"": ""object"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 436879977, ""num_examples"": 432076}, {""name"": ""test"", ""num_bytes"": 3798221, ""num_examples"": 2175}, {""name"": ""validation"", ""num_bytes"": 2230995, ""num_examples"": 1276}], ""download_size"": 1685172398, ""dataset_size"": 442909193}, {""config_name"": ""ja"", ""features"": [{""name"": ""docid"", ""dtype"": ""string""}, {""name"": ""title"", ""dtype"": ""string""}, {""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""entities"", ""list"": [{""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""surfaceform"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""start"", ""dtype"": ""int32""}, {""name"": ""end"", ""dtype"": ""int32""}]}, {""name"": ""relations"", ""list"": [{""name"": ""subject"", ""dtype"": ""int32""}, {""name"": ""predicate"", ""dtype"": ""string""}, {""name"": ""object"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 708617436, ""num_examples"": 480785}, {""name"": ""test"", ""num_bytes"": 7802066, ""num_examples"": 3392}, {""name"": ""validation"", ""num_bytes"": 6990637, ""num_examples"": 3106}], ""download_size"": 3186065351, ""dataset_size"": 723410139}, {""config_name"": ""ko"", ""features"": [{""name"": ""docid"", ""dtype"": ""string""}, {""name"": ""title"", ""dtype"": ""string""}, {""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""entities"", ""list"": [{""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""surfaceform"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""start"", ""dtype"": ""int32""}, {""name"": ""end"", ""dtype"": ""int32""}]}, {""name"": ""relations"", ""list"": [{""name"": ""subject"", ""dtype"": ""int32""}, {""name"": ""predicate"", ""dtype"": ""string""}, {""name"": ""object"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 266381416, ""num_examples"": 213659}, {""name"": ""test"", ""num_bytes"": 1736809, ""num_examples"": 803}, {""name"": ""validation"", ""num_bytes"": 1857229, ""num_examples"": 917}], ""download_size"": 1119778167, ""dataset_size"": 269975454}, {""config_name"": ""nl"", ""features"": [{""name"": ""docid"", ""dtype"": ""string""}, {""name"": ""title"", ""dtype"": ""string""}, {""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""entities"", ""list"": [{""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""surfaceform"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""start"", ""dtype"": ""int32""}, {""name"": ""end"", ""dtype"": ""int32""}]}, {""name"": ""relations"", ""list"": [{""name"": ""subject"", ""dtype"": ""int32""}, {""name"": ""predicate"", ""dtype"": ""string""}, {""name"": ""object"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 695855128, ""num_examples"": 648029}, {""name"": ""test"", ""num_bytes"": 5186584, ""num_examples"": 2715}, {""name"": ""validation"", ""num_bytes"": 4188877, ""num_examples"": 2188}], ""download_size"": 2591997126, ""dataset_size"": 705230589}, {""config_name"": ""pl"", ""features"": [{""name"": ""docid"", ""dtype"": ""string""}, {""name"": ""title"", ""dtype"": ""string""}, {""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""entities"", ""list"": [{""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""surfaceform"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""start"", ""dtype"": ""int32""}, {""name"": ""end"", ""dtype"": ""int32""}]}, {""name"": ""relations"", ""list"": [{""name"": ""subject"", ""dtype"": ""int32""}, {""name"": ""predicate"", ""dtype"": ""string""}, {""name"": ""object"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 877441685, ""num_examples"": 675688}, {""name"": ""test"", ""num_bytes"": 11475559, ""num_examples"": 6376}, {""name"": ""validation"", ""num_bytes"": 6618989, ""num_examples"": 3476}], ""download_size"": 3365852789, ""dataset_size"": 895536233}, {""config_name"": ""pt"", ""features"": [{""name"": ""docid"", ""dtype"": ""string""}, {""name"": ""title"", ""dtype"": ""string""}, {""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""entities"", ""list"": [{""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""surfaceform"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""start"", ""dtype"": ""int32""}, {""name"": ""end"", ""dtype"": ""int32""}]}, {""name"": ""relations"", ""list"": [{""name"": ""subject"", ""dtype"": ""int32""}, {""name"": ""predicate"", ""dtype"": ""string""}, {""name"": ""object"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 584986936, ""num_examples"": 469347}, {""name"": ""test"", ""num_bytes"": 8678707, ""num_examples"": 4313}, {""name"": ""validation"", ""num_bytes"": 5807293, ""num_examples"": 2973}], ""download_size"": 2347987926, ""dataset_size"": 599472936}, {""config_name"": ""ru"", ""features"": [{""name"": ""docid"", ""dtype"": ""string""}, {""name"": ""title"", ""dtype"": ""string""}, {""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""entities"", ""list"": [{""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""surfaceform"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""start"", ""dtype"": ""int32""}, {""name"": ""end"", ""dtype"": ""int32""}]}, {""name"": ""relations"", ""list"": [{""name"": ""subject"", ""dtype"": ""int32""}, {""name"": ""predicate"", ""dtype"": ""string""}, {""name"": ""object"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 604993210, ""num_examples"": 339697}, {""name"": ""test"", ""num_bytes"": 5941158, ""num_examples"": 2296}, {""name"": ""validation"", ""num_bytes"": 5352859, ""num_examples"": 2107}], ""download_size"": 2754576893, ""dataset_size"": 616287227}, {""config_name"": ""sv"", ""features"": [{""name"": ""docid"", ""dtype"": ""string""}, {""name"": ""title"", ""dtype"": ""string""}, {""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""entities"", ""list"": [{""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""surfaceform"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""start"", ""dtype"": ""int32""}, {""name"": ""end"", ""dtype"": ""int32""}]}, {""name"": ""relations"", ""list"": [{""name"": ""subject"", ""dtype"": ""int32""}, {""name"": ""predicate"", ""dtype"": ""string""}, {""name"": ""object"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1822863623, ""num_examples"": 1742082}, {""name"": ""test"", ""num_bytes"": 13002356, ""num_examples"": 7531}, {""name"": ""validation"", ""num_bytes"": 5136097, ""num_examples"": 2987}], ""download_size"": 6790489020, ""dataset_size"": 1841002076}, {""config_name"": ""vi"", ""features"": [{""name"": ""docid"", ""dtype"": ""string""}, {""name"": ""title"", ""dtype"": ""string""}, {""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""entities"", ""list"": [{""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""surfaceform"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""start"", ""dtype"": ""int32""}, {""name"": ""end"", ""dtype"": ""int32""}]}, {""name"": ""relations"", ""list"": [{""name"": ""subject"", ""dtype"": ""int32""}, {""name"": ""predicate"", ""dtype"": ""string""}, {""name"": ""object"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 300641174, ""num_examples"": 260010}, {""name"": ""test"", ""num_bytes"": 4304795, ""num_examples"": 1824}, {""name"": ""validation"", ""num_bytes"": 3402120, ""num_examples"": 1461}], ""download_size"": 1301938106, ""dataset_size"": 308348089}, {""config_name"": ""zh"", ""features"": [{""name"": ""docid"", ""dtype"": ""string""}, {""name"": ""title"", ""dtype"": ""string""}, {""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""entities"", ""list"": [{""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""surfaceform"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""start"", ""dtype"": ""int32""}, {""name"": ""end"", ""dtype"": ""int32""}]}, {""name"": ""relations"", ""list"": [{""name"": ""subject"", ""dtype"": ""int32""}, {""name"": ""predicate"", ""dtype"": ""string""}, {""name"": ""object"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 449085696, ""num_examples"": 369249}, {""name"": ""test"", ""num_bytes"": 5260974, ""num_examples"": 2667}, {""name"": ""validation"", ""num_bytes"": 3511103, ""num_examples"": 1816}], ""download_size"": 2440525684, ""dataset_size"": 457857773}, {""config_name"": ""all_languages"", ""features"": [{""name"": ""docid"", ""dtype"": ""string""}, {""name"": ""title"", ""dtype"": ""string""}, {""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""lan"", ""dtype"": ""string""}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""entities"", ""list"": [{""name"": ""uri"", ""dtype"": ""string""}, {""name"": ""surfaceform"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""start"", ""dtype"": ""int32""}, {""name"": ""end"", ""dtype"": ""int32""}]}, {""name"": ""relations"", ""list"": [{""name"": ""subject"", ""dtype"": ""int32""}, {""name"": ""predicate"", ""dtype"": ""string""}, {""name"": ""object"", ""dtype"": ""int32""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 14615645332, ""num_examples"": 11865756}, {""name"": ""test"", ""num_bytes"": 131636046, ""num_examples"": 67033}, {""name"": ""validation"", ""num_bytes"": 103507688, ""num_examples"": 51181}], ""download_size"": 56989165879, ""dataset_size"": 14850789066}], ""task_categories"": [""token-classification""], ""language"": [""ar"", ""ca"", ""de"", ""el"", ""en"", ""es"", ""fr"", ""hi"", ""it"", ""ja"", ""ko"", ""nl"", ""pl"", ""pt"", ""ru"", ""sv"", ""vi"", ""zh""], ""size_categories"": [""10MFM: a Filtered and Multilingual Relation Extraction Dataset + +This is the automatically-filtered dataset from the 2023 ACL paper [RED^{FM}: a Filtered and Multilingual Relation Extraction Dataset](https://arxiv.org/abs/2306.09802). If you use the model, please reference this work in your paper: + + @inproceedings{huguet-cabot-et-al-2023-redfm-dataset, + title = ""RED$^{\rm FM}$: a Filtered and Multilingual Relation Extraction Dataset"", + author = ""Huguet Cabot, Pere-Llu{\'\i}s and Tedeschi, Simone and Ngonga Ngomo, Axel-Cyrille and + Navigli, Roberto"", + booktitle = ""Proc. of the 61st Annual Meeting of the Association for Computational Linguistics: ACL 2023"", + month = jul, + year = ""2023"", + address = ""Toronto, Canada"", + publisher = ""Association for Computational Linguistics"", + url = ""https://arxiv.org/abs/2306.09802"", + } + + +## License + +SREDFM is licensed under the CC BY-SA 4.0 license. The text of the license can be found [here](https://creativecommons.org/licenses/by-sa/4.0/)." +maywell/korean_textbooks,"{""language"": [""ko""], ""license"": ""apache-2.0"", ""size_categories"": [""1M 1) / tmp.shape[0]} + +tokenizer_name = 'mistralai/Mistral-7B-v0.1' +language = 'sk' #Slovak +tokenizer = AutoTokenizer.from_pretrained(tokenizer_name) +ds = load_dataset('occiglot/tokenizer-wiki-bench', name=language, split='clean') + +remove_columns = list(set(ds.column_names) - set([""text""])) +ds = ds.map(lambda x: {'tokens': tokenizer(x['split_text'], add_special_tokens=False)['input_ids']} ,num_proc=256, remove_columns=remove_columns, batched=False) +remove_columns = None#list(set(ds.column_names)) +ds = ds.map(lambda x: calculate_metrics(x['tokens']), num_proc=256, remove_columns=remove_columns, batched=False) +df = ds.to_pandas() + +print('Fertility: ', df.fertility.mean()) +print('Prop. continued words:', df.cont_prop.mean()) +``` + +## Dataset Creation + +We loosely follow the approach of [Rust _et al.](https://arxiv.org/abs/2012.15613) using the fast [UDPipe](https://ufal.mff.cuni.cz/udpipe) to pre-split documents into words and subsequently run the tokenizer over isolated words. For all languages we use the respective November 2023 snapshot from [Wikipedia](wikimedia/wikipedia). Since Wikipedia, by nature, contains significantly more numbers and dates than other text and most tokenizers split those into single digits, we filtered all lone-standing numbers from the documents. Additionally, we removed any documents that still contained non-parsed HTML code (less than 1%). + +## Licensing + +We release our curated benchmark and any associated code under [MIT](https://opensource.org/license/mit) license. However, depending on your use case, the licensing conditions of the original [Wikipedia data](https://huggingface.co/datasets/wikimedia/wikipedia#licensing-information) and [UDPipe](https://github.com/ufal/udpipe/tree/udpipe-2?tab=License-1-ov-file) may apply. + +## Supported Languages +This dataset currently contains pre-processed data for the following languages: + +| Language | Code | +|:-----------|:-------| +| Afrikaans | af | +| Arabic | ar | +| Armenian | hy | +| Basque | eu | +| Bulgarian | bg | +| Catalan | ca | +| Croatian | hr | +| Czech | cs | +| Danish | da | +| Dutch | nl | +| English | en | +| Estonian | et | +| Finnish | fi | +| French | fr | +| German | de | +| Greek | el | +| Hebrew | he | +| Hindi | hi | +| Hungarian | hu | +| Indonesian | id | +| Irish | ga | +| Italian | it | +| Japanese | ja | +| Korean | ko | +| Latvian | lv | +| Lithuanian | lt | +| Marathi | mr | +| Norwegian | no | +| Persian | fa | +| Polish | pl | +| Portuguese | pt | +| Romanian | ro | +| Russian | ru | +| Sanskrit | sa | +| Serbian | sr | +| Slovak | sk | +| Slovenian | sl | +| Spanish | es | +| Swedish | sv | +| Tamil | ta | +| Telugu | te | +| Turkish | tr | +| Ukrainian | uk | +| Urdu | ur | +| Vietnamese | vi |" +taeminlee/Ko-StrategyQA,"{""language"": [""ko""], ""multilinguality"": [""monolingual""], ""size_categories"": [""1K One of the biggest challenges hindering progress in low-resource and multilingual machine translation is the lack of good evaluation benchmarks. Current evaluation benchmarks either lack good coverage of low-resource languages, consider only restricted domains, or are low quality because they are constructed using semi-automatic procedures. In this work, we introduce the FLORES evaluation benchmark, consisting of 3001 sentences extracted from English Wikipedia and covering a variety of different topics and domains. These sentences have been translated in 101 languages by professional translators through a carefully controlled process. The resulting dataset enables better assessment of model quality on the long tail of low-resource languages, including the evaluation of many-to-many multilingual translation systems, as all translations are multilingually aligned. By publicly releasing such a high-quality and high-coverage dataset, we hope to foster progress in the machine translation community and beyond. + +**Disclaimer**: *The Flores-101 dataset is hosted by the Facebook and licensed under the [Creative Commons Attribution-ShareAlike 4.0 International License](https://creativecommons.org/licenses/by-sa/4.0/). + +### Supported Tasks and Leaderboards + +#### Multilingual Machine Translation + +Refer to the [Dynabench leaderboard](https://dynabench.org/flores/Flores%20MT%20Evaluation%20(FULL)) for additional details on model evaluation on FLORES-101 in the context of the WMT2021 shared task on [Large-Scale Multilingual Machine Translation](http://www.statmt.org/wmt21/large-scale-multilingual-translation-task.html). + +### Languages + +The dataset contains parallel sentences for 101 languages, as mentioned in the original [Github](https://github.com/facebookresearch/flores/blob/master/README.md) page for the project. Languages are identified with the ISO 639-3 code (e.g. `eng`, `fra`, `rus`) as in the original dataset. + +**New:** Use the configuration `all` to access the full set of parallel sentences for all the available languages in a single command. + + +## Dataset Structure + +### Data Instances + +A sample from the `dev` split for the Russian language (`rus` config) is provided below. All configurations have the same structure, and all sentences are aligned across configurations and splits. + +```python +{ + 'id': 1, + 'sentence': 'В понедельник ученые из Медицинской школы Стэнфордского университета объявили об изобретении нового диагностического инструмента, который может сортировать клетки по их типу; это маленький чип, который можно напеча��ать, используя стандартный струйный принтер примерно за 1 цент США.', + 'URL': 'https://en.wikinews.org/wiki/Scientists_say_new_medical_diagnostic_chip_can_sort_cells_anywhere_with_an_inkjet', + 'domain': 'wikinews', + 'topic': 'health', + 'has_image': 0, + 'has_hyperlink': 0 +} +``` + +The text is provided as-in the original dataset, without further preprocessing or tokenization. + +### Data Fields + +- `id`: Row number for the data entry, starting at 1. +- `sentence`: The full sentence in the specific language. +- `URL`: The URL for the English article from which the sentence was extracted. +- `domain`: The domain of the sentence. +- `topic`: The topic of the sentence. +- `has_image`: Whether the original article contains an image. +- `has_hyperlink`: Whether the sentence contains a hyperlink. + +### Data Splits + +| config| `dev`| `devtest`| +|-----------------:|-----:|---------:| +|all configurations| 997| 1012:| + +### Dataset Creation + +Please refer to the original article [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://arxiv.org/abs/2106.03193) for additional information on dataset creation. + +## Additional Information + +### Dataset Curators + +The original authors of FLORES-101 are the curators of the original dataset. For problems or updates on this 🤗 Datasets version, please contact [gabriele.sarti996@gmail.com](mailto:gabriele.sarti996@gmail.com). + +### Licensing Information + +Licensed with Creative Commons Attribution Share Alike 4.0. License available [here](https://creativecommons.org/licenses/by-sa/4.0/). + +### Citation Information + +Please cite the authors if you use these corpora in your work: + +```bibtex +@inproceedings{flores101, + title={The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation}, + author={Goyal, Naman and Gao, Cynthia and Chaudhary, Vishrav and Chen, Peng-Jen and Wenzek, Guillaume and Ju, Da and Krishnan, Sanjana and Ranzato, Marc'Aurelio and Guzm\'{a}n, Francisco and Fan, Angela}, + journal={arXiv preprint arXiv:2106.03193}, + year={2021} +} +```" +aiana94/polynews,"{""license"": ""cc-by-nc-4.0"", ""task_categories"": [""fill-mask"", ""text-generation""], ""language"": [""am"", ""ar"", ""ay"", ""bm"", ""bbj"", ""bn"", ""bs"", ""bg"", ""ca"", ""cs"", ""ku"", ""da"", ""el"", ""en"", ""et"", ""ee"", ""fil"", ""fi"", ""fr"", ""fon"", ""gu"", ""guw"", ""ha"", ""he"", ""hi"", ""hu"", ""ig"", ""id"", ""it"", ""ja"", ""kk"", ""km"", ""ko"", ""lv"", ""ln"", ""lt"", ""lg"", ""luo"", ""mk"", ""mos"", ""my"", ""nl"", ""no"", ""ne"", ""om"", ""or"", ""pa"", ""pcm"", ""fa"", ""pl"", ""pt"", ""mg"", ""ro"", ""rn"", ""ru"", ""sn"", ""so"", ""es"", ""sr"", ""sq"", ""sw"", ""sv"", ""ta"", ""tet"", ""ti"", ""th"", ""tn"", ""tr"", ""tw"", ""uk"", ""ur"", ""wo"", ""xh"", ""yo"", ""zh"", ""zu"", ""de""], ""multilinguality"": [""multilingual""], ""pretty_name"": ""PolyNews"", ""size_categories"": [""1K>> from datasets import load_dataset +>>> data = load_dataset('aiana94/polynews', 'ron_Latn') + +# Please, specify the language code, + +# A data point example is below: + +{ +""text"": ""Un public numeros. Este uimitor succesul după doar trei ediții . "", +""provenance"": ""globalvoices"" +} + +``` + +### Data Fields + +- text (string): news text +- provenance (string) : source dataset for the news example + +### Data Splits + +For all languages, there is only the `train` split. + + +## Dataset Creation + +### Curation Rationale + +Multiple multilingual, human-translated, datasets containing news texts have been released in recent years. +However, these datasets are stored in different formats and various websites, and many contain numerous near duplicates. +With PolyNews, we aim to provide an easily-accessible, unified and deduplicated dataset that combines these disparate data sources. +It can be used for domain adaptation of language models, language modeling or text generation in both high-resource and low-resource languages. + +### Source Data + +The source data consists of five multilingual news datasets. + +- [Wikinews](https://www.wikinews.org/) (latest dump available in May 2024) +- [GlobalVoices](https://opus.nlpl.eu/GlobalVoices/corpus/version/GlobalVoices) (v2018q4) +- [WMT-News](https://opus.nlpl.eu/WMT-News/corpus/version/WMT-News) (v2019) +- [MasakhaNews](https://huggingface.co/datasets/masakhane/masakhanews) (`train` split) +- [MAFAND](https://huggingface.co/datasets/masakhane/mafand) (`train` split) + +#### Data Collection and Processing + +We processed the data using a **working script** which covers the entire processing pipeline. It can be found [here](https://github.com/andreeaiana/nase/blob/main/scripts/construct_polynews.sh). + +The data processing pipeline consists of: +1. Downloading the WMT-News and GlobalVoices News from OPUS. +2. Downloading the latest dump from WikiNews. +3. Loading the MasakhaNews and MAFAND datasets from Hugging Face Hub (only the `train` splits). +4. Concatenating, per language, all news texts from the source datasets. +5. Data cleaning (e.g., removal of exact duplicates, short texts, texts in other scripts) +6. [MinHash near-deduplication](https://github.com/bigcode-project/bigcode-dataset/blob/main/near_deduplication/minhash_deduplication.py) per language. + + +### Annotations + +We augment the original samples with the `provenance` annotation which specifies the original data source from which a particular examples stems. + + +#### Personal and Sensitive Information + +The data is sourced from newspaper sources and contains mentions of public figures and individuals. + + +## Considerations for Using the Data + +### Social Impact of Dataset +[More Information Needed] + + +### Discussion of Biases +[More Information Needed] + + +### Other Known Limitations + +Users should keep in mind that the dataset contains short news texts (e.g., mostly titles), which might limit the applicability of the developed systems to other domains. + + +## Additional Information + +### Licensing Information +The dataset is released under the [CC BY-NC Attribution-NonCommercial 4.0 International license](https://creativecommons.org/licenses/by-nc/4.0/). + +### Citation Infomation + +**BibTeX:** + +```bibtex +@misc{iana2024news, + title={News Without Borders: Domain Adaptation of Multilingual Sentence Embeddings for Cross-lingual News Recommendation}, + author={Andreea Iana and Fabian David Schmidt and Goran Glavaš and Heiko Paulheim}, + year={2024}, + eprint={2406.12634}, + archivePrefix={arXiv}, + url={https://arxiv.org/abs/2406.12634} +} +```" +daekeun-ml/naver-news-summarization-ko,"{""license"": ""apache-2.0"", ""task_categories"": [""summarization""], ""language"": [""ko""], ""size_categories"": [""10K 함수해석학은 함수의 공간(특히 무한차원)의 탐구 에 주목한다. 함수해석학의 많은 응용분야 중 하나가 양자역학이다. 많은 문제들이 자연스럽게 양과 그 양의 변화율의 관계로 귀착되고, 이러한 문제들이 미분방정식으로 다루어진다. 자연의 많은 현상들이 동역학계로 기술될 수 있다. 혼돈 이론은 이러한 예측 불가능한 현상을 탐구하는 데 상당한 기여를 한다.', + ""paragraph_answer"": '변화에 대한 이해와 묘사는 자연과학에 있어서 일반적인 주제이며, 미적분학은 변화를 탐구하는 강력한 도구로서 발전되었다. 함수는 변화하는 양을 묘사함에 있어서 중추적인 개념으로써 떠오르게 된다. 실수와 실변수로 구성된 함수의 엄밀한 탐구가 실해석학이라는 분야로 알려지게 되었고, 복소수에 대한 이와 같은 탐구 분야는 복소해석학이라고 한다. 함수해석학은 함수의 공간(특히 무한차원)의 탐구 에 주목한다. 함수해석학의 많은 응용분야 중 하나가 양자역학이다. 많은 문제들이 자연스럽게 양과 그 양의 변화율의 관계로 귀착되고, 이러한 문제들이 미분방정식으로 다루어진다. 자연의 많은 현상들이 동역학계��� 기술될 수 있다. 혼돈 이론은 이러한 예측 불가능한 현상을 탐구하는 데 상당한 기여를 한다.', + ""sentence_answer"": ""함수해석학은 함수의 공간(특히 무한차원)의 탐구 에 주목한다."" +} +``` + +The data fields are the same among all splits. +- `question`: a `string` feature. +- `paragraph`: a `string` feature. +- `answer`: a `string` feature. +- `sentence`: a `string` feature. +- `paragraph_answer`: a `string` feature, which is same as the paragraph but the answer is highlighted by a special token ``. +- `paragraph_sentence`: a `string` feature, which is same as the paragraph but a sentence containing the answer is highlighted by a special token ``. +- `sentence_answer`: a `string` feature, which is same as the sentence but the answer is highlighted by a special token ``. + +Each of `paragraph_answer`, `paragraph_sentence`, and `sentence_answer` feature is assumed to be used to train a question generation model, +but with different information. The `paragraph_answer` and `sentence_answer` features are for answer-aware question generation and +`paragraph_sentence` feature is for sentence-aware question generation. + +## Data Splits + +|train|validation|test | +|----:|---------:|----:| +|54556| 5766 |5766 | + + +## Citation Information + +``` +@inproceedings{ushio-etal-2022-generative, + title = ""{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration: {A} {U}nified {B}enchmark and {E}valuation"", + author = ""Ushio, Asahi and + Alva-Manchego, Fernando and + Camacho-Collados, Jose"", + booktitle = ""Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing"", + month = dec, + year = ""2022"", + address = ""Abu Dhabi, U.A.E."", + publisher = ""Association for Computational Linguistics"", +} +```" +MoritzLaurer/multilingual-NLI-26lang-2mil7,"{""annotations_creators"": [""crowdsourced""], ""language_creators"": [""machinetranslation""], ""size_categories"": [""1MMIMIC-IT Dataset Download\nAgreement\n

S-Lab, Nanyang Technological University (S-Lab) provides access to\nthe MIMIC-IT Dataset (referred to as the Dataset) under the following\nconditions.

\n

By signing, the researcher agrees to the following terms of use:

\n
    \n
  1. S-Lab makes no warranties regarding the Dataset, including but not\nlimited to being up-to-date, correct or complete. S-Lab cannot be held\nliable for providing access to the Dataset or usage of the Dataset.
    2. \n
  2. The Dataset should only be used for scientific or research purposes.\nAny other use is explicitly prohibited.
    3. \n
  3. The researcher agrees to the following terms and conditions of data\nsources of the Dataset:\n
    4. \n
  4. The researcher takes full responsibility for usage of the Dataset at\nany time.
    5. \n
  5. S-Lab reserves the right to terminate the researcher's access to the\nDataset at any time.
    6. \n
  6. The place of jurisdiction is Singapore.
    7. \n
  7. If any part of this agreement is legally invalid, this shall not\naffect the remaining agreement.
    8. \n
\n"", ""extra_gated_fields"": {""Verifiable Name"": ""text"", ""Institution Email"": ""text"", ""Institutional Affiliation"": ""text"", ""I agree with the agreement"": ""checkbox""}, ""dataset_info"": [{""config_name"": ""CGD"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""image""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 26335666892.75, ""num_examples"": 141869}], ""download_size"": 13284595128, ""dataset_size"": 26335666892.75}, {""config_name"": ""CGD_Images"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""image"", ""dtype"": ""image""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 10977030309.125, ""num_examples"": 118287}], ""download_size"": 10976812684, ""dataset_size"": 10977030309.125}, {""config_name"": ""CGD_Instructions"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""string""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 42088070, ""num_examples"": 141869}], ""download_size"": 14266985, ""dataset_size"": 42088070}, {""config_name"": ""DC_Instructions"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""string""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 718166107, ""num_examples"": 226242}], ""download_size"": 50424022, ""dataset_size"": 718166107}, {""config_name"": ""E4D_Instructions"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""string""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 3647794122, ""num_examples"": 2729222}], ""download_size"": 396261870, ""dataset_size"": 3647794122}, {""config_name"": ""LACONV"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""image""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 13374859898.25, ""num_examples"": 256870}], ""download_size"": 3096198512, ""dataset_size"": 13374859898.25}, {""config_name"": ""LACONV_Instructions"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""string""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 119528906, ""num_examples"": 256870}], ""download_size"": 54731579, ""dataset_size"": 119528906}, {""config_name"": ""LACR_I2I"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""image""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 4027892178.625, ""num_examples"": 76643}], ""download_size"": 3988169106, ""dataset_size"": 4027892178.625}, {""config_name"": ""LACR_I2I_Instructions"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""string""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 89534975, ""num_examples"": 76643}], ""download_size"": 42911696, ""dataset_size"": 89534975}, {""config_name"": ""LACR_T2T"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""image""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 4028004669.625, ""num_examples"": 76643}], ""download_size"": 3988281406, ""dataset_size"": 4028004669.625}, {""config_name"": ""LACR_T2T_Instructions"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""string""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 89647466, ""num_examples"": 76643}], ""download_size"": 43136360, ""dataset_size"": 89647466}, {""config_name"": ""LADD"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""image""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1293641342.0, ""num_examples"": 23240}], ""download_size"": 1285923315, ""dataset_size"": 1293641342.0}, {""config_name"": ""LADD_Instructions"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""string""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 16659871, ""num_examples"": 23240}], ""download_size"": 7472431, ""dataset_size"": 16659871}, {""config_name"": ""LA_Images"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""image"", ""dtype"": ""image""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 4191197157.25, ""num_examples"": 81398}], ""download_size"": 4190198358, ""dataset_size"": 4191197157.25}, {""config_name"": ""SD"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""image""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 3098784669.75, ""num_examples"": 15989}], ""download_size"": 1669131271, ""dataset_size"": 3098784669.75}, {""config_name"": ""SD_Images"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""image"", ""dtype"": ""image""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 2523484759.75, ""num_examples"": 26154}], ""download_size"": 2438558263, ""dataset_size"": 2523484759.75}, {""config_name"": ""SD_Instructions"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""string""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 4112174, ""num_examples"": 15989}], ""download_size"": 1237759, ""dataset_size"": 4112174}, {""config_name"": ""SN"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""image""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 7979712053.04, ""num_examples"": 6640}], ""download_size"": 3401191449, ""dataset_size"": 7979712053.04}, {""config_name"": ""SN_Images"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""image"", ""dtype"": ""image""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 859886037.875, ""num_examples"": 11513}], ""download_size"": 859698909, ""dataset_size"": 859886037.875}, {""config_name"": ""SN_Instructions"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""string""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 7230721, ""num_examples"": 6640}], ""download_size"": 1324832, ""dataset_size"": 7230721}, {""config_name"": ""TVC"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""image""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 130408953299.393, ""num_examples"": 137607}], ""download_size"": 79524699480, ""dataset_size"": 130408953299.393}, {""config_name"": ""TVC_Images"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""image"", ""dtype"": ""image""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 13056626872.375, ""num_examples"": 227701}], ""download_size"": 13052443854, ""dataset_size"": 13056626872.375}, {""config_name"": ""TVC_Instructions"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""string""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 161582906, ""num_examples"": 137607}], ""download_size"": 30882217, ""dataset_size"": 161582906}, {""config_name"": ""VST"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""image""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 7093814625.328, ""num_examples"": 32893}], ""download_size"": 4263530868, ""dataset_size"": 7093814625.328}, {""config_name"": ""VST_Images"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""image"", ""dtype"": ""image""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 14529719834.625, ""num_examples"": 144755}], ""download_size"": 14282540973, ""dataset_size"": 14529719834.625}, {""config_name"": ""VST_Instructions"", ""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""images"", ""sequence"": ""string""}, {""name"": ""related instructions"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 30877616, ""num_examples"": 32893}], ""download_size"": 9311504, ""dataset_size"": 30877616}], ""configs"": [{""config_name"": ""CGD"", ""data_files"": [{""split"": ""train"", ""path"": ""CGD/train-*""}]}, {""config_name"": ""CGD_Images"", ""data_files"": [{""split"": ""train"", ""path"": ""CGD_Images/train-*""}]}, {""config_name"": ""CGD_Instructions"", ""data_files"": [{""split"": ""train"", ""path"": ""CGD_Instructions/train-*""}]}, {""config_name"": ""DC_Instructions"", ""data_files"": [{""split"": ""train"", ""path"": ""DC_Instructions/train-*""}]}, {""config_name"": ""E4D_Instructions"", ""data_files"": [{""split"": ""train"", ""path"": ""E4D_Instructions/train-*""}]}, {""config_name"": ""LACONV"", ""data_files"": [{""split"": ""train"", ""path"": ""LACONV/train-*""}]}, {""config_name"": ""LACONV_Instructions"", ""data_files"": [{""split"": ""train"", ""path"": ""LACONV_Instructions/train-*""}]}, {""config_name"": ""LACR_I2I"", ""data_files"": [{""split"": ""train"", ""path"": ""LACR_I2I/train-*""}]}, {""config_name"": ""LACR_I2I_Instructions"", ""data_files"": [{""split"": ""train"", ""path"": ""LACR_I2I_Instructions/train-*""}]}, {""config_name"": ""LACR_T2T"", ""data_files"": [{""split"": ""train"", ""path"": ""LACR_T2T/train-*""}]}, {""config_name"": ""LACR_T2T_Instructions"", ""data_files"": [{""split"": ""train"", ""path"": ""LACR_T2T_Instructions/train-*""}]}, {""config_name"": ""LADD"", ""data_files"": [{""split"": ""train"", ""path"": ""LADD/train-*""}]}, {""config_name"": ""LADD_Instructions"", ""data_files"": [{""split"": ""train"", ""path"": ""LADD_Instructions/train-*""}]}, {""config_name"": ""LA_Images"", ""data_files"": [{""split"": ""train"", ""path"": ""LA_Images/train-*""}]}, {""config_name"": ""SD"", ""data_files"": [{""split"": ""train"", ""path"": ""SD/train-*""}]}, {""config_name"": ""SD_Images"", ""data_files"": [{""split"": ""train"", ""path"": ""SD_Images/train-*""}]}, {""config_name"": ""SD_Instructions"", ""data_files"": [{""split"": ""train"", ""path"": ""SD_Instructions/train-*""}]}, {""config_name"": ""SN"", ""data_files"": [{""split"": ""train"", ""path"": ""SN/train-*""}]}, {""config_name"": ""SN_Images"", ""data_files"": [{""split"": ""train"", ""path"": ""SN_Images/train-*""}]}, {""config_name"": ""SN_Instructions"", ""data_files"": [{""split"": ""train"", ""path"": ""SN_Instructions/train-*""}]}, {""config_name"": ""TVC"", ""data_files"": [{""split"": ""train"", ""path"": ""TVC/train-*""}]}, {""config_name"": ""TVC_Images"", ""data_files"": [{""split"": ""train"", ""path"": ""TVC_Images/train-*""}]}, {""config_name"": ""TVC_Instructions"", ""data_files"": [{""split"": ""train"", ""path"": ""TVC_Instructions/train-*""}]}, {""config_name"": ""VST"", ""data_files"": [{""split"": ""train"", ""path"": ""VST/train-*""}]}, {""config_name"": ""VST_Images"", ""data_files"": [{""split"": ""train"", ""path"": ""VST_Images/train-*""}]}, {""config_name"": ""VST_Instructions"", ""data_files"": [{""split"": ""train"", ""path"": ""VST_Instructions/train-*""}]}]}","

+ +

+ + +
+ +
+
+ 1S-Lab, Nanyang Technological University  + 2Microsoft Research, Redmond +
+ ♠ Co-Project Lead  + * Equal Contribution  + ✉ Corresponding Author + +
+ +## Dataset Description + +- **Homepage: https://otter-ntu.github.io** +- **Repository: https://github.com/Luodian/Otter** +- **Paper: https://arxiv.org/abs/2306.05425** + +**Note 1: To reduce memory consumption during image loading and improve loading speed, we are converting the JSON format of images to the Parquet format. For detailed information, please refer to [this link](https://github.com/Luodian/Otter/blob/main/docs/mimicit_format.md).** + +**Note 2: We are uploading the full version of `DC` and `E4D`, the new files are indicated by the suffix `1207`.** + + +### Dataset Summary + +MIMIC-IT offers a diverse and extensive dataset of 2.8M multimodal instruction-response pairs, designed to enhance the performance of Vision-Language Models (VLMs) in real-life scenarios, enabling VLMs to excel in perception, reasoning, and planning while also catering to a multilingual audience. + +MIMIC-IT enables the application of egocentric visual assistant model that can serve that can answer your questions like **Hey, Do you think I left my keys on the table?**. Harness the power of MIMIC-IT to unlock the full potential of your AI-driven visual assistant and elevate your interactive vision-language tasks to new heights. + +MIMIC-IT provides multilingual instructions, supporting English, Chinese, Korean, Japanese, German, French, Spanish, and Arabic, thereby allowing a larger global audience to altogether enjoy from the convenience brought about by advancements in artificial intelligence. + +

+ +

+ +## Using MIMIC-IT + +We have already upload the `images.parquet` file. You can check [`tools/load.py`](tools/load.py) to learn how to load the dataset (`instruction.json` + `images.parquet`) and check the integrity of the whole dataset. + +You can also use [this code](https://huggingface.co/datasets/pufanyi/MIMICIT/blob/main/tools/convert_to_parquet.py) to convert `image.json` to `parquet` version by yourself. + +You can following the steps to obtain the MIMIC-IT dataset. Each task (e.g. `DC`, `LA`) in MIMIC-IT is composed of three parts, including: +1. `xx.json` file: the images in base64 format. +2. `xx_instructions.json` file: the instruction-response pairs (also includes image ids and related instructions ids for each instruction-response pair) for each task. +3. `xx_train.json` file: the customized related instruction-response pairs for each instruction. + +You can directly download the contents in the `data` folder. The distribution of the `data` folder is as follows: + +```plain +data/ + CGD/ + CGD.json + CGD_images_preview.csv + CGD_instructions.json + ... +``` + +For each `dataset_name`, there are three main files **except for `DC` and `E4D`**: + +1. `{dataset_name}.json`: Stores the image numbers and their corresponding base64 codes in lossless compressed PNG format. + ```json + { + ""image_id_1"": ""base64_code_1"", + ""image_id_2"": ""base64_code_2"", + ... + } + ``` +2. `{dataset_name}_images_preview.csv`: Stores the image numbers and their corresponding base64 codes in lossy compressed JPG format, mainly used for display in the Dataset Card. + ```csv + id, image + ""image_id_1"", ""base64_code_1"" + ""image_id_2"", ""base64_code_2"" + ... + ``` +3. `{dataset_name}_instructions.json`: Stores each instruction and its associated answer. + ```json + { + ""meta"": { + ""version"": current_version, + ""time"": update_time, + ""author"": ""ntu"" + }, + ""data"": { + ""instruction_id_1"": { + ""instruction"": ""instruction_1"", + ""answer"": ""answer_of_instruction_1"", + ""image_ids"": [ + ""image_id_1"", + ""image_id_2"", + ... + ], + ""rel_ins_ids"": [ + ""related_instruction_id_1"", + ""related_instruction_id_2"", + ... + ] + }, + ... + } + } + ``` + +Of course, you can also use `wget` or `curl` for direct downloads. Below is an example. + +Before proceeding with the downloads, you need to set your Hugging Face token. For that, please refer to [this page](https://huggingface.co/docs/hub/security-tokens). + + +```shell +$ # Set Hugging Face Token +$ HF_TOKEN=""YOUR_HUGGING_FACE_TOKEN"" + +$ # Set the dataset you want to download +$ DATASET_NAME=""DATASET_YOU_WANT_TO_DOWNLOAD"" # e.g. CGD + +$ # Download {DATASET_NAME}.json +$ wget --header=""Authorization: Bearer $HF_TOKEN"" ""https://huggingface.co/datasets/pufanyi/MIMICIT/resolve/main/data/${DATASET_NAME}/${DATASET_NAME}.json"" + +$ # Download {DATASET_NAME}_instructions.json +$ wget --header=""Authorization: Bearer $HF_TOKEN"" ""https://huggingface.co/datasets/pufanyi/MIMICIT/resolve/main/data/${DATASET_NAME}/${DATASET_NAME}_instructions.json"" + +$ # Download {DATASET_NAME}_images_preview.csv (usually not necessary) +$ wget --header=""Authorization: Bearer $HF_TOKEN"" ""https://huggingface.co/datasets/pufanyi/MIMICIT/resolve/main/data/${DATASET_NAME}/${DATASET_NAME}_images_preview.csv"" +``` + +Or + +```shell +$ # Set Hugging Face Token +$ HF_TOKEN=""YOUR_HUGGING_FACE_TOKEN"" + +$ # Set the dataset you want to download +$ DATASET_NAME=""DATASET_YOU_WANT_TO_DOWNLOAD"" # e.g. CGD + +$ # Download {DATASET_NAME}.json +$ curl -LJO -H ""Authorization: Bearer $HF_TOKEN"" ""https://huggingface.co/datasets/pufanyi/MIMICIT/resolve/main/data/${DATASET_NAME}/${DATASET_NAME}.json"" + +$ # Download {DATASET_NAME}_instructions.json +$ curl -LJO -H ""Authorization: Bearer $HF_TOKEN"" ""https://huggingface.co/datasets/pufanyi/MIMICIT/resolve/main/data/${DATASET_NAME}/${DATASET_NAME}_instructions.json"" + +$ # Download {DATASET_NAME}_images_preview.csv (usually not necessary) +$ curl -LJO -H ""Authorization: Bearer $HF_TOKEN"" ""https://huggingface.co/datasets/pufanyi/MIMICIT/resolve/main/data/${DATASET_NAME}/${DATASET_NAME}_images_preview.csv"" +``` + +Alternatively, you can use `dataset.load_dataset` for downloading. However, due to Hugging Face's size limitations, all images can only be loaded in JPG format. Below is an example using `CGD` dataset: + + +### CGD_Images + +Download the JPG format images and their corresponding identifiers: + +```python +from datasets import load_dataset +data = load_dataset(""pufanyi/MIMICIT"", ""CGD_Images"") +``` + +The format will be like: + +```json +{ + ""id"": ""CGD_IMG_000000426149"", + ""image"": +} +``` + +It should be noted that, due to size limitations, for `DC` (Dense Captions), this command will only extract a portion of the images from the `DC` collection for downloading. + +### CGD_Instructions + +Download all instructions: + +```python +from datasets import load_dataset +data = load_dataset(""pufanyi/MIMICIT"", ""CGD_Instructions"") +``` + +The format will be like: + +```json +{ + ""id"": ""CGD_INS_000000"", + ""instruction"": ""What is the difference between the two pizzas in these images?"", + ""answer"": ""The pizza in the first image is on a red plate and being held by an old lady, while the pizza in the second image is on a metal counter being prepared by a woman in a blue shirt."", + ""images"": [ + ""CGD_IMG_000000069568"", + ""CGD_IMG_000000328270"" + ], + ""related instructions"": [ + ""CGD_INS_000001"" + ] +} +``` + +### CGD_Preview + +Download all instructions along with their corresponding JPG images: + +```python +from datasets import load_dataset +data = load_dataset(""pufanyi/MIMICIT"", ""CGD_Preview"") +``` + +The format will be like: + +```json +{ + ""id"": ""CGD_INS_000000"", + ""instruction"": ""What is the difference between the two pizzas in these images?"", + ""answer"": ""The pizza in the first image is on a red plate and being held by an old lady, while the pizza in the second image is on a metal counter being prepared by a woman in a blue shirt."", + ""images"": [ + , + + ], + ""related instructions"": [ + ""CGD_INS_000001"" + ] +} +``` + +It should be noted that, due to size limitations, for `DC` (Dense Captions), this command will only extract a portion of the images from the `DC` collection for downloading." +wecover/OPUS_GlobalVoices,{},"--- +configs: +- config_name: default + data_files: + - split: train + path: '*/*/train.parquet' + - split: valid + path: '*/*/valid.parquet' + - split: test + path: '*/*/test.parquet' +- config_name: am + data_files: + - split: train + path: '*/*am*/train.parquet' + - split: test + path: '*/*am*/test.parquet' + - split: valid + path: '*/*am*/valid.parquet' +- config_name: ar + data_files: + - split: train + path: '*/*ar*/train.parquet' + - split: test + path: '*/*ar*/test.parquet' + - split: valid + path: '*/*ar*/valid.parquet' +- config_name: bn + data_files: + - split: train + path: '*/*bn*/train.parquet' + - split: test + path: '*/*bn*/test.parquet' + - split: valid + path: '*/*bn*/valid.parquet' +- config_name: ca + data_files: + - split: train + path: '*/*ca*/train.parquet' + - split: test + path: '*/*ca*/test.parquet' + - split: valid + path: '*/*ca*/valid.parquet' +- config_name: de + data_files: + - split: train + path: '*/*de*/train.parquet' + - split: test + path: '*/*de*/test.parquet' + - split: valid + path: '*/*de*/valid.parquet' +- config_name: el + data_files: + - split: train + path: '*/*el*/train.parquet' + - split: test + path: '*/*el*/test.parquet' + - split: valid + path: '*/*el*/valid.parquet' +- config_name: en + data_files: + - split: train + path: '*/*en*/train.parquet' + - split: test + path: '*/*en*/test.parquet' + - split: valid + path: '*/*en*/valid.parquet' +- config_name: es + data_files: + - split: train + path: '*/*es*/train.parquet' + - split: test + path: '*/*es*/test.parquet' + - split: valid + path: '*/*es*/valid.parquet' +- config_name: fa + data_files: + - split: train + path: '*/*fa*/train.parquet' + - split: test + path: '*/*fa*/test.parquet' + - split: valid + path: '*/*fa*/valid.parquet' +- config_name: fr + data_files: + - split: train + path: '*/*fr*/train.parquet' + - split: test + path: '*/*fr*/test.parquet' + - split: valid + path: '*/*fr*/valid.parquet' +- config_name: hi + data_files: + - split: train + path: '*/*hi*/train.parquet' + - split: test + path: '*/*hi*/test.parquet' + - split: valid + path: '*/*hi*/valid.parquet' +- config_name: hu + data_files: + - split: train + path: '*/*hu*/train.parquet' + - split: test + path: '*/*hu*/test.parquet' + - split: valid + path: '*/*hu*/valid.parquet' +- config_name: id + data_files: + - split: train + path: '*/*id*/train.parquet' + - split: test + path: '*/*id*/test.parquet' + - split: valid + path: '*/*id*/valid.parquet' +- config_name: it + data_files: + - split: train + path: '*/*it*/train.parquet' + - split: test + path: '*/*it*/test.parquet' + - split: valid + path: '*/*it*/valid.parquet' +- config_name: mg + data_files: + - split: train + path: '*/*mg*/train.parquet' + - split: test + path: '*/*mg*/test.parquet' + - split: valid + path: '*/*mg*/valid.parquet' +- config_name: mk + data_files: + - split: train + path: '*/*mk*/train.parquet' + - split: test + path: '*/*mk*/test.parquet' + - split: valid + path: '*/*mk*/valid.parquet' +- config_name: my + data_files: + - split: train + path: '*/*my*/train.parquet' + - split: test + path: '*/*my*/test.parquet' + - split: valid + path: '*/*my*/valid.parquet' +- config_name: nl + data_files: + - split: train + path: '*/*nl*/train.parquet' + - split: test + path: '*/*nl*/test.parquet' + - split: valid + path: '*/*nl*/valid.parquet' +- config_name: pl + data_files: + - split: train + path: '*/*pl*/train.parquet' + - split: test + path: '*/*pl*/test.parquet' + - split: valid + path: '*/*pl*/valid.parquet' +- config_name: pt + data_files: + - split: train + path: '*/*pt*/train.parquet' + - split: test + path: '*/*pt*/test.parquet' + - split: valid + path: '*/*pt*/valid.parquet' +- config_name: ru + data_files: + - split: train + path: '*/*ru*/train.parquet' + - split: test + path: '*/*ru*/test.parquet' + - split: valid + path: '*/*ru*/valid.parquet' +- config_name: sr + data_files: + - split: train + path: '*/*sr*/train.parquet' + - split: test + path: '*/*sr*/test.parquet' + - split: valid + path: '*/*sr*/valid.parquet' +- config_name: sw + data_files: + - split: train + path: '*/*sw*/train.parquet' + - split: test + path: '*/*sw*/test.parquet' + - split: valid + path: '*/*sw*/valid.parquet' +- config_name: tr + data_files: + - split: train + path: '*/*tr*/train.parquet' + - split: test + path: '*/*tr*/test.parquet' + - split: valid + path: '*/*tr*/valid.parquet' +- config_name: ur + data_files: + - split: train + path: '*/*ur*/train.parquet' + - split: test + path: '*/*ur*/test.parquet' + - split: valid + path: '*/*ur*/valid.parquet' +- config_name: zhs + data_files: + - split: train + path: '*/*zhs*/train.parquet' + - split: test + path: '*/*zhs*/test.parquet' + - split: valid + path: '*/*zhs*/valid.parquet' +- config_name: zht + data_files: + - split: train + path: '*/*zht*/train.parquet' + - split: test + path: '*/*zht*/test.parquet' + - split: valid + path: '*/*zht*/valid.parquet' +- config_name: bg + data_files: + - split: train + path: '*/*bg*/train.parquet' + - split: test + path: '*/*bg*/test.parquet' + - split: valid + path: '*/*bg*/valid.parquet' +- config_name: cs + data_files: + - split: train + path: '*/*cs*/train.parquet' + - split: test + path: '*/*cs*/test.parquet' + - split: valid + path: '*/*cs*/valid.parquet' +- config_name: da + data_files: + - split: train + path: '*/*da*/train.parquet' + - split: test + path: '*/*da*/test.parquet' + - split: valid + path: '*/*da*/valid.parquet' +- config_name: eo + data_files: + - split: train + path: '*/*eo*/train.parquet' + - split: test + path: '*/*eo*/test.parquet' + - split: valid + path: '*/*eo*/valid.parquet' +- config_name: he + data_files: + - split: train + path: '*/*he*/train.parquet' + - split: test + path: '*/*he*/test.parquet' + - split: valid + path: '*/*he*/valid.parquet' +- config_name: km + data_files: + - split: train + path: '*/*km*/train.parquet' + - split: test + path: '*/*km*/test.parquet' + - split: valid + path: '*/*km*/valid.parquet' +- config_name: ko + data_files: + - split: train + path: '*/*ko*/train.parquet' + - split: test + path: '*/*ko*/test.parquet' + - split: valid + path: '*/*ko*/valid.parquet' +- config_name: ku + data_files: + - split: train + path: '*/*ku*/train.parquet' + - split: test + path: '*/*ku*/test.parquet' + - split: valid + path: '*/*ku*/valid.parquet' +- config_name: ne + data_files: + - split: train + path: '*/*ne*/train.parquet' + - split: test + path: '*/*ne*/test.parquet' + - split: valid + path: '*/*ne*/valid.parquet' +- config_name: or + data_files: + - split: train + path: '*/*or*/train.parquet' + - split: test + path: '*/*or*/test.parquet' + - split: valid + path: '*/*or*/valid.parquet' +- config_name: pa + data_files: + - split: train + path: '*/*pa*/train.parquet' + - split: test + path: '*/*pa*/test.parquet' + - split: valid + path: '*/*pa*/valid.parquet' +- config_name: ro + data_files: + - split: train + path: '*/*ro*/train.parquet' + - split: test + path: '*/*ro*/test.parquet' + - split: valid + path: '*/*ro*/valid.parquet' +- config_name: sq + data_files: + - split: train + path: '*/*sq*/train.parquet' + - split: test + path: '*/*sq*/test.parquet' + - split: valid + path: '*/*sq*/valid.parquet' +- config_name: sv + data_files: + - split: train + path: '*/*sv*/train.parquet' + - split: test + path: '*/*sv*/test.parquet' + - split: valid + path: '*/*sv*/valid.parquet' +language: +- am +- ar +- bg +- bn +- ca +- cs +- da +- de +- el +- en +- eo +- es +- fa +- fr +- he +- hi +- hu +- id +- it +- km +- ko +- ku +- mg +- mk +- my +- ne +- nl +- or +- pa +- pt +- pl +- ro +- ru +- sq +- sr +- sv +- sw +- tr +- ur +- zh +---" +CohereForAI/Global-MMLU,"{""dataset_info"": [{""config_name"": ""am"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 209505, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 12085768, ""num_examples"": 14042}], ""download_size"": 10260448, ""dataset_size"": 12295273}, {""config_name"": ""ar"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 202343, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 11621977, ""num_examples"": 14042}], ""download_size"": 9817049, ""dataset_size"": 11824320}, {""config_name"": ""bn"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 301875, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 18061158, ""num_examples"": 14042}], ""download_size"": 12524784, ""dataset_size"": 18363033}, {""config_name"": ""cs"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 149807, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 8607308, ""num_examples"": 14042}], ""download_size"": 8640151, ""dataset_size"": 8757115}, {""config_name"": ""de"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 162406, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 9575360, ""num_examples"": 14042}], ""download_size"": 9187953, ""dataset_size"": 9737766}, {""config_name"": ""el"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 254308, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 14502137, ""num_examples"": 14042}], ""download_size"": 12288940, ""dataset_size"": 14756445}, {""config_name"": ""en"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 146364, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 8440632, ""num_examples"": 14042}], ""download_size"": 7912429, ""dataset_size"": 8586996}, {""config_name"": ""es"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 160633, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 9399724, ""num_examples"": 14042}], ""download_size"": 8752720, ""dataset_size"": 9560357}, {""config_name"": ""fa"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 202609, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 11611890, ""num_examples"": 14042}], ""download_size"": 9564082, ""dataset_size"": 11814499}, {""config_name"": ""fil"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 165182, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 9510179, ""num_examples"": 14042}], ""download_size"": 8564879, ""dataset_size"": 9675361}, {""config_name"": ""fr"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 166173, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 9858873, ""num_examples"": 14042}], ""download_size"": 9202595, ""dataset_size"": 10025046}, {""config_name"": ""ha"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 147406, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 8445707, ""num_examples"": 14042}], ""download_size"": 7665529, ""dataset_size"": 8593113}, {""config_name"": ""he"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 178912, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 10248592, ""num_examples"": 14042}], ""download_size"": 8818618, ""dataset_size"": 10427504}, {""config_name"": ""hi"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 308254, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 17970478, ""num_examples"": 14042}], ""download_size"": 12407854, ""dataset_size"": 18278732}, {""config_name"": ""id"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 154692, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 8886643, ""num_examples"": 14042}], ""download_size"": 7793365, ""dataset_size"": 9041335}, {""config_name"": ""ig"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 157376, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 9221405, ""num_examples"": 14042}], ""download_size"": 7644102, ""dataset_size"": 9378781}, {""config_name"": ""it"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 157547, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 9374481, ""num_examples"": 14042}], ""download_size"": 8873034, ""dataset_size"": 9532028}, {""config_name"": ""ja"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 167646, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 9830716, ""num_examples"": 14042}], ""download_size"": 8826164, ""dataset_size"": 9998362}, {""config_name"": ""ko"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 160572, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 9454859, ""num_examples"": 14042}], ""download_size"": 8640457, ""dataset_size"": 9615431}, {""config_name"": ""ky"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 235001, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 13483934, ""num_examples"": 14042}], ""download_size"": 11148813, ""dataset_size"": 13718935}, {""config_name"": ""lt"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 148917, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 8504949, ""num_examples"": 14042}], ""download_size"": 8416467, ""dataset_size"": 8653866}, {""config_name"": ""mg"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 161992, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 9337415, ""num_examples"": 14042}], ""download_size"": 8011427, ""dataset_size"": 9499407}, {""config_name"": ""ms"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 152549, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 8823844, ""num_examples"": 14042}], ""download_size"": 7783581, ""dataset_size"": 8976393}, {""config_name"": ""ne"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 294790, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 16972110, ""num_examples"": 14042}], ""download_size"": 11895818, ""dataset_size"": 17266900}, {""config_name"": ""nl"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 158122, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 9099176, ""num_examples"": 14042}], ""download_size"": 8565959, ""dataset_size"": 9257298}, {""config_name"": ""ny"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 151315, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 8686819, ""num_examples"": 14042}], ""download_size"": 7822699, ""dataset_size"": 8838134}, {""config_name"": ""pl"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 157290, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 8980730, ""num_examples"": 14042}], ""download_size"": 8981270, ""dataset_size"": 9138020}, {""config_name"": ""pt"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 154592, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 8983299, ""num_examples"": 14042}], ""download_size"": 8517588, ""dataset_size"": 9137891}, {""config_name"": ""ro"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 158311, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 9163189, ""num_examples"": 14042}], ""download_size"": 8773232, ""dataset_size"": 9321500}, {""config_name"": ""ru"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 246059, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 14059847, ""num_examples"": 14042}], ""download_size"": 11904365, ""dataset_size"": 14305906}, {""config_name"": ""si"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 297843, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 17374939, ""num_examples"": 14042}], ""download_size"": 12790098, ""dataset_size"": 17672782}, {""config_name"": ""sn"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 147355, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 8507368, ""num_examples"": 14042}], ""download_size"": 7962672, ""dataset_size"": 8654723}, {""config_name"": ""so"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 156282, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 9033243, ""num_examples"": 14042}], ""download_size"": 8706693, ""dataset_size"": 9189525}, {""config_name"": ""sr"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 221580, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 12695546, ""num_examples"": 14042}], ""download_size"": 10748391, ""dataset_size"": 12917126}, {""config_name"": ""sv"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 147893, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 8549708, ""num_examples"": 14042}], ""download_size"": 8181997, ""dataset_size"": 8697601}, {""config_name"": ""sw"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 147069, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 8653210, ""num_examples"": 14042}], ""download_size"": 7932986, ""dataset_size"": 8800279}, {""config_name"": ""te"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 315724, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 18170058, ""num_examples"": 14042}], ""download_size"": 12631358, ""dataset_size"": 18485782}, {""config_name"": ""tr"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 153426, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 8833244, ""num_examples"": 14042}], ""download_size"": 8351339, ""dataset_size"": 8986670}, {""config_name"": ""uk"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 229888, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 13233771, ""num_examples"": 14042}], ""download_size"": 11347842, ""dataset_size"": 13463659}, {""config_name"": ""vi"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 185712, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 10604332, ""num_examples"": 14042}], ""download_size"": 8971266, ""dataset_size"": 10790044}, {""config_name"": ""yo"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 153810, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 10694916, ""num_examples"": 14042}], ""download_size"": 9303668, ""dataset_size"": 10848726}, {""config_name"": ""zh"", ""features"": [{""name"": ""sample_id"", ""dtype"": ""string""}, {""name"": ""subject"", ""dtype"": ""string""}, {""name"": ""subject_category"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""option_a"", ""dtype"": ""string""}, {""name"": ""option_b"", ""dtype"": ""string""}, {""name"": ""option_c"", ""dtype"": ""string""}, {""name"": ""option_d"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""required_knowledge"", ""dtype"": ""string""}, {""name"": ""time_sensitive"", ""dtype"": ""string""}, {""name"": ""reference"", ""dtype"": ""string""}, {""name"": ""culture"", ""dtype"": ""string""}, {""name"": ""region"", ""dtype"": ""string""}, {""name"": ""country"", ""dtype"": ""string""}, {""name"": ""cultural_sensitivity_label"", ""dtype"": ""string""}, {""name"": ""is_annotated"", ""dtype"": ""bool""}], ""splits"": [{""name"": ""dev"", ""num_bytes"": 127577, ""num_examples"": 285}, {""name"": ""test"", ""num_bytes"": 7393764, ""num_examples"": 14042}], ""download_size"": 7322261, ""dataset_size"": 7521341}], ""configs"": [{""config_name"": ""am"", ""data_files"": [{""split"": ""test"", ""path"": ""am/test-*""}, {""split"": ""dev"", ""path"": ""am/dev-*""}]}, {""config_name"": ""ar"", ""data_files"": [{""split"": ""test"", ""path"": ""ar/test-*""}, {""split"": ""dev"", ""path"": ""ar/dev-*""}]}, {""config_name"": ""bn"", ""data_files"": [{""split"": ""test"", ""path"": ""bn/test-*""}, {""split"": ""dev"", ""path"": ""bn/dev-*""}]}, {""config_name"": ""cs"", ""data_files"": [{""split"": ""test"", ""path"": ""cs/test-*""}, {""split"": ""dev"", ""path"": ""cs/dev-*""}]}, {""config_name"": ""de"", ""data_files"": [{""split"": ""test"", ""path"": ""de/test-*""}, {""split"": ""dev"", ""path"": ""de/dev-*""}]}, {""config_name"": ""el"", ""data_files"": [{""split"": ""test"", ""path"": ""el/test-*""}, {""split"": ""dev"", ""path"": ""el/dev-*""}]}, {""config_name"": ""en"", ""data_files"": [{""split"": ""test"", ""path"": ""en/test-*""}, {""split"": ""dev"", ""path"": ""en/dev-*""}]}, {""config_name"": ""es"", ""data_files"": [{""split"": ""test"", ""path"": ""es/test-*""}, {""split"": ""dev"", ""path"": ""es/dev-*""}]}, {""config_name"": ""fa"", ""data_files"": [{""split"": ""test"", ""path"": ""fa/test-*""}, {""split"": ""dev"", ""path"": ""fa/dev-*""}]}, {""config_name"": ""fil"", ""data_files"": [{""split"": ""test"", ""path"": ""fil/test-*""}, {""split"": ""dev"", ""path"": ""fil/dev-*""}]}, {""config_name"": ""fr"", ""data_files"": [{""split"": ""test"", ""path"": ""fr/test-*""}, {""split"": ""dev"", ""path"": ""fr/dev-*""}]}, {""config_name"": ""ha"", ""data_files"": [{""split"": ""test"", ""path"": ""ha/test-*""}, {""split"": ""dev"", ""path"": ""ha/dev-*""}]}, {""config_name"": ""he"", ""data_files"": [{""split"": ""test"", ""path"": ""he/test-*""}, {""split"": ""dev"", ""path"": ""he/dev-*""}]}, {""config_name"": ""hi"", ""data_files"": [{""split"": ""test"", ""path"": ""hi/test-*""}, {""split"": ""dev"", ""path"": ""hi/dev-*""}]}, {""config_name"": ""id"", ""data_files"": [{""split"": ""test"", ""path"": ""id/test-*""}, {""split"": ""dev"", ""path"": ""id/dev-*""}]}, {""config_name"": ""ig"", ""data_files"": [{""split"": ""test"", ""path"": ""ig/test-*""}, {""split"": ""dev"", ""path"": ""ig/dev-*""}]}, {""config_name"": ""it"", ""data_files"": [{""split"": ""test"", ""path"": ""it/test-*""}, {""split"": ""dev"", ""path"": ""it/dev-*""}]}, {""config_name"": ""ja"", ""data_files"": [{""split"": ""test"", ""path"": ""ja/test-*""}, {""split"": ""dev"", ""path"": ""ja/dev-*""}]}, {""config_name"": ""ko"", ""data_files"": [{""split"": ""test"", ""path"": ""ko/test-*""}, {""split"": ""dev"", ""path"": ""ko/dev-*""}]}, {""config_name"": ""ky"", ""data_files"": [{""split"": ""test"", ""path"": ""ky/test-*""}, {""split"": ""dev"", ""path"": ""ky/dev-*""}]}, {""config_name"": ""lt"", ""data_files"": [{""split"": ""test"", ""path"": ""lt/test-*""}, {""split"": ""dev"", ""path"": ""lt/dev-*""}]}, {""config_name"": ""mg"", ""data_files"": [{""split"": ""test"", ""path"": ""mg/test-*""}, {""split"": ""dev"", ""path"": ""mg/dev-*""}]}, {""config_name"": ""ms"", ""data_files"": [{""split"": ""test"", ""path"": ""ms/test-*""}, {""split"": ""dev"", ""path"": ""ms/dev-*""}]}, {""config_name"": ""ne"", ""data_files"": [{""split"": ""test"", ""path"": ""ne/test-*""}, {""split"": ""dev"", ""path"": ""ne/dev-*""}]}, {""config_name"": ""nl"", ""data_files"": [{""split"": ""test"", ""path"": ""nl/test-*""}, {""split"": ""dev"", ""path"": ""nl/dev-*""}]}, {""config_name"": ""ny"", ""data_files"": [{""split"": ""test"", ""path"": ""ny/test-*""}, {""split"": ""dev"", ""path"": ""ny/dev-*""}]}, {""config_name"": ""pl"", ""data_files"": [{""split"": ""test"", ""path"": ""pl/test-*""}, {""split"": ""dev"", ""path"": ""pl/dev-*""}]}, {""config_name"": ""pt"", ""data_files"": [{""split"": ""test"", ""path"": ""pt/test-*""}, {""split"": ""dev"", ""path"": ""pt/dev-*""}]}, {""config_name"": ""ro"", ""data_files"": [{""split"": ""test"", ""path"": ""ro/test-*""}, {""split"": ""dev"", ""path"": ""ro/dev-*""}]}, {""config_name"": ""ru"", ""data_files"": [{""split"": ""test"", ""path"": ""ru/test-*""}, {""split"": ""dev"", ""path"": ""ru/dev-*""}]}, {""config_name"": ""si"", ""data_files"": [{""split"": ""test"", ""path"": ""si/test-*""}, {""split"": ""dev"", ""path"": ""si/dev-*""}]}, {""config_name"": ""sn"", ""data_files"": [{""split"": ""test"", ""path"": ""sn/test-*""}, {""split"": ""dev"", ""path"": ""sn/dev-*""}]}, {""config_name"": ""so"", ""data_files"": [{""split"": ""test"", ""path"": ""so/test-*""}, {""split"": ""dev"", ""path"": ""so/dev-*""}]}, {""config_name"": ""sr"", ""data_files"": [{""split"": ""test"", ""path"": ""sr/test-*""}, {""split"": ""dev"", ""path"": ""sr/dev-*""}]}, {""config_name"": ""sv"", ""data_files"": [{""split"": ""test"", ""path"": ""sv/test-*""}, {""split"": ""dev"", ""path"": ""sv/dev-*""}]}, {""config_name"": ""sw"", ""data_files"": [{""split"": ""test"", ""path"": ""sw/test-*""}, {""split"": ""dev"", ""path"": ""sw/dev-*""}]}, {""config_name"": ""te"", ""data_files"": [{""split"": ""test"", ""path"": ""te/test-*""}, {""split"": ""dev"", ""path"": ""te/dev-*""}]}, {""config_name"": ""tr"", ""data_files"": [{""split"": ""test"", ""path"": ""tr/test-*""}, {""split"": ""dev"", ""path"": ""tr/dev-*""}]}, {""config_name"": ""uk"", ""data_files"": [{""split"": ""test"", ""path"": ""uk/test-*""}, {""split"": ""dev"", ""path"": ""uk/dev-*""}]}, {""config_name"": ""vi"", ""data_files"": [{""split"": ""test"", ""path"": ""vi/test-*""}, {""split"": ""dev"", ""path"": ""vi/dev-*""}]}, {""config_name"": ""yo"", ""data_files"": [{""split"": ""test"", ""path"": ""yo/test-*""}, {""split"": ""dev"", ""path"": ""yo/dev-*""}]}, {""config_name"": ""zh"", ""data_files"": [{""split"": ""test"", ""path"": ""zh/test-*""}, {""split"": ""dev"", ""path"": ""zh/dev-*""}]}], ""tags"": [""argilla""], ""language"": [""en"", ""ar"", ""bn"", ""es"", ""fr"", ""hi"", ""ru"", ""de"", ""id"", ""it"", ""ja"", ""ko"", ""pt"", ""zh"", ""yo"", ""nl"", ""ro"", ""uk"", ""vi"", ""tr"", ""pl"", ""fa"", ""cs"", ""he"", ""el"", ""ms"", ""fil"", ""te"", ""si"", ""ne"", ""ky"", ""sv"", ""lt"", ""sr"", ""mg"", ""so"", ""ha"", ""am"", ""sn"", ""ig"", ""ny"", ""sw""]}","![GlobalMMLU Header](https://huggingface.co/datasets/CohereForAI/Global-MMLU/resolve/main/global_mmlu.jpg) + +# Dataset Summary +[Global-MMLU](https://arxiv.org/abs/2412.03304) 🌍 is a multilingual evaluation set spanning 42 languages, including English. This dataset combines machine translations for [MMLU](https://huggingface.co/datasets/cais/mmlu) questions along with professional translations and crowd-sourced post-edits. +It also includes cultural sensitivity annotations for a subset of the questions (2850 questions per language) and classifies them as *Culturally Sensitive* (CS) 🗽 or *Culturally Agnostic* (CA) ⚖️. These annotations were collected as part of an open science initiative led by Cohere For AI in collaboration with many external collaborators from both industry and academia. + +- **Curated by:** Professional annotators and contributors of [Cohere For AI Community](https://cohere.com/research). +- **Language(s):** 42 languages. +- **License:** [Apache 2.0](https://opensource.org/license/apache-2-0) + +**Note:** We also provide a ""lite"" version of Global MMLU called [""Global-MMLU-Lite""](https://huggingface.co/datasets/CohereForAI/Global-MMLU-Lite). This datatset is more balanced containing 200 samples each for CA and CS subsets for each language. And provides coverage for 15 languages with human translations. + + +### **Global-MMLU Dataset Family:** + + | Name | Explanation | + |------|--------------| + | [Global-MMLU](https://huggingface.co/datasets/CohereForAI/Global-MMLU) | Full Global-MMLU set with translations for all 14K samples including CS and CA subsets| + | [Global-MMLU-Lite](https://huggingface.co/datasets/CohereForAI/Global-MMLU-Lite) | Lite version of Global-MMLU with human translated samples in 15 languages and containing 200 samples each for CS and CA subsets per language.| + + + +## Load with Datasets +To load this dataset with `datasets`, you'll first need to install it using `pip install datasets` and then use the following code: + +```python +from datasets import load_dataset + +# load HF dataset +global_mmlu = load_dataset(""CohereForAI/Global-MMLU"", 'en') + +# can also be used as pandas dataframe +global_mmlu.set_format(""pandas"") +global_mmlu_test = global_mmlu['test'][:] +global_mmlu_dev = global_mmlu['dev'][:] +``` + +
+ additional details + +The columns corresponding to annotations collected from our cultural bias study (i.e. 'required_knowledge', 'time_sensitive', 'reference', 'culture', 'region', 'country') contain a list of values representing annotations from different annotators. +However, to avoid conversion issues to HF dataset, these columns are provided as string in the final dataset. +You can convert these columns back to list of values for easier manipulation as follows: +```python +import ast + +# convert string values to list +global_mmlu_df['required_knowledge'] = global_mmlu_df['required_knowledge'].apply(lamda x: ast.literal_eval(x)) +``` +
+
+ + +## Data Fields + +The data fields are the same among all splits. Brief description of each field is provided below. + +
+ data field description + +- `sample_id`: A unique identifier for the question. +- `subject`: The main topic the question falls under. +- `subject_category`: The high-level category the subject falls under i.e. STEM/Humanities/Social Sciences/Medical/Business/Other. +- `question`: translated question from MMLU +- `option_a`: one of the possible option choices +- `option_b`: one of the possible option choices +- `option_c`: one of the possible option choices +- `option_d`: one of the possible option choices +- `answer': the correct answer (A/B/C/D) +- `required_knowledge`: annotator votes for knowledge needed to answer the question correctly. Possible values include: ""cultural"", ""regional"", ""dialect"" or ""none"" +- `time_sensitive`: annotator votes indicating if the question's answer is time-dependent. Possible values include: Yes/No +- `reference`: annotations for which part of the question contains cultural/regional/dialect references. The different items in the list are annotations from different annotators. +- `culture`: annotations for which culture does the question belong to. The different items in the list correspond to annotations from different annotators. +- `region`: Geographic region the question is relevant to. Each item in the list correspond to annotations from different annotators. +- `country`: Specific country the question pertains to. Each item in the list correspond to annotations from different annotators. +- `cultural_sensitivity_label`: Label to indicate if question is culturally sensitive (CS) or culturally agnostic (CA) based on annotator votes. +- `is_annotated`: True/False flag to indicate if sample contains any annotations from our cultural bias study. + +
+
+ +## Data Splits +The following are the splits of the data: +| Split | No. of instances | Language Coverage | +|-------|------------------|-------------------| +| test | 589,764 | 42 | +| dev | 11,970 | 42 | + + +## Data Instances + +An example from `test` set looks as follows: +```json +{'sample_id': 'world_religions/test/170' + 'subject': 'world_religions', + 'subject_category': 'Humanities', + 'question': ' The numen of Augustus referred to which of the following characteristics?', + 'option_a': 'Divine power', + 'option_b': 'Sexual virility', + 'option_c': 'Military acumen', + 'option_d': 'Philosophical intellect', + 'answer': 'A', + 'required_knowledge': ""['none', 'cultural', 'cultural', 'cultural']"", + 'time_sensitive': ""['No', 'No', 'No', 'No']"", + 'reference': ""['-', '-', {'end': 22, 'label': 'Cultural', 'score': None, 'start': 5}, {'end': 22, 'label': 'Cultural', 'score': None, 'start': 5}]"", + 'culture': ""['Western Culture', 'Western Culture', 'Western Culture']"", + 'region': ""['North America', 'Europe']"", + 'country': ""['Italy']"", + 'cultural_sensitivity_label': 'CS', + 'is_annotated': True, + } +``` + +## Statistics +### Annotation Types +The following is the breakdown of CS🗽, CA⚖️ and MA📝 samples in the final dataset. + +| Type of Annotation | Instances per language | No. of languages | Total instances +|--------------------|------------------------|------------------|----------------| +| Culturally Sensitive 🗽 | 792 | 42 | 33,264 | +| Culturally Agnostic ⚖️ | 2058 |42 | 86,436 | +| MMLU Annotated 📝| 2850 |42 | 119,700 | + +### Languages +The dataset covers 42 languages: 20 high-resource, 9 mid-resource, and 13 low-resource languages. The following is details about the languages included in the dataset. + +
+ Languages Info + +| ISO Code | Language | Resources | +|----------|----------|-----------| +| `am` | Amharic | Low | +| `ar` | Arabic (Standard)| High | +| `bn` | Bengali | Mid | +| `de` | German | High | +| `el` | Greek | Mid | +| `en` | English | High | +| `fil` | Filipino | Mid | +| `fr` | French | High | +| `ha` | Hausa | Low | +| `he` | Hebrew | Mid | +| `hi` | Hindi | High | +| `ig` | Igbo | Low | +| `id` | Indonesian | Mid | +| `it` | Italian | High | +| `ja` | Japanese | High | +| `ky` | Kyrgyz | Low | +| `ko` | Korean | Mid | +| `lt` | Lithuanian | Mid | +| `mg` | Malagasy | Low | +| `ms` | Malay | Mid | +| `ne` | Nepali | Low | +| `nl` | Dutch | High | +| `ny` | Chichewa | Low | +| `fa` | Persian | High | +| `pl` | Polish | High | +| `pt` | Portuguese | High | +| `ru` | Russian | High | +| `si` | Sinhala | Low | +| `sn` | Shona | Low | +| `so` | Somali | Low | +| `es` | Spanish | High | +| `sr` | Serbian | High | +| `sw` | Swahili | Low | +| `sw` | Swedish | High | +| `te` | Telugu | Low | +| `tr` | Turkish | High | +| `uk` | Ukrainian | Mid | +| `vi` | Vietnamese | High | +| `yo` | Yorùbá | Low | +| `zh` | Chinese (Simplified) | High | +
+
+ +# Known Limitations +A brief overview of limitations of this dataset is provided below. +
+ show limitations + +- **Language and dialect coverage:** Global-MMLU focusses on 42 languages. However, this is still only a tiny fraction of the world’s linguistic diversity. Future work is needed to continue to improve evaluations beyond these 42 languages and take into account how technology serves different dialects. +- **Uneven distribution of contributions:** The dataset contains translation post-edits from community volunteers, with a 'long tail' of volunteers making only one or two contributions. Similarly, there is a huge gap between languages with the highest number of contributions and ones with the lowest number of contributions. +- **Toxic or offensive speech:** Our annotation process did not focus on flagging for toxic,harmful, or offensive speech, so it is possible that Global-MMLU contains some data that could be considered harmful. We believe this is of relatively low risk because of the nature of the original MMLU and the focus on examination material. +- **Region Category Assignment:** For the annotation of geographically sensitive questions, we classified regions into six geographic regions (Africa, Asia, Europe, North America, Oceania,and South America). However, based upon discussions we would going forward recommend switching to the taxonomy proposed by the World Bank which is more granular and includes separate designations for Central America and Sub-Saharan Africa. +- **Identifying cultural sensitivity does not guarantee cultural inclusion:** While Global-MMLU highlights important limitations in current datasets by identifying gaps in non-Western cultural representation. Future work must prioritize the integration of diverse culturally grounded knowledge to achieve true inclusivity and fairness in multilingual AI evaluation. + +
+
+ +# Additional Information + +## Provenance +- **Methods Used:** Professional annotations as well as crowd-sourced through volunteer annotations. +- **Methodology Details:** We collected cultural bias annotations as well as post-edits of translations for different mmlu questions. + - [Cultural Sensitivity Annotation Platform](https://huggingface.co/spaces/CohereForAI/MMLU-evaluation) + - [Translation Quality Annotation Platform](https://huggingface.co/spaces/CohereForAI/review-mmlu-translations) + - Dates of Collection: May 2024 - Aug 2024 + + +## Dataset Version and Maintenance +- **Maintenance Status:** Actively Maintained +- **Version Details:** + - *Current version:* 1.0 + - *Last Update:* 12/2024 + - *First Release:* 12/2024 + + +## Authorship +- **Publishing Organization:** [Cohere For AI](https://cohere.com/research) +- **Industry Type:** Not-for-profit - Tech + +## Licensing Information +This dataset can be used for any purpose, under the terms of the [Apache 2.0](https://opensource.org/license/apache-2-0) License. + +## Additional Details +For any additional details, please check our paper, [Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation](https://arxiv.org/abs/2412.03304). + + +## Citation Information +```bibtex +@misc{singh2024globalmmluunderstandingaddressing, + title={Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation}, + author={Shivalika Singh and Angelika Romanou and Clémentine Fourrier and David I. Adelani and Jian Gang Ngui and Daniel Vila-Suero and Peerat Limkonchotiwat and Kelly Marchisio and Wei Qi Leong and Yosephine Susanto and Raymond Ng and Shayne Longpre and Wei-Yin Ko and Madeline Smith and Antoine Bosselut and Alice Oh and Andre F. T. Martins and Leshem Choshen and Daphne Ippolito and Enzo Ferrante and Marzieh Fadaee and Beyza Ermis and Sara Hooker}, + year={2024}, + eprint={2412.03304}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2412.03304}, +} +```" +EunsuKim/CLIcK,"{""task_categories"": [""multiple-choice""], ""language"": [""ko""], ""tags"": [""Culture"", ""Language""], ""size_categories"": [""1K +

CLIcK 🇰🇷🧠

+

A Benchmark Dataset of Cultural and Linguistic Intelligence in Korean

+

+ + +

+
+ + +## Introduction 🎉 + +CLIcK (Cultural and Linguistic Intelligence in Korean) is a comprehensive dataset designed to evaluate cultural and linguistic intelligence in the context of Korean language models. In an era where diverse language models are continually emerging, there is a pressing need for robust evaluation datasets, especially for non-English languages like Korean. CLIcK fills this gap by providing a rich, well-categorized dataset focusing on both cultural and linguistic aspects, enabling a nuanced assessment of Korean language models. + +## News 📰 + +- **[LREC-COLING]** Our paper introducing CLIcK has been accepted to LREC-COLING 2024!🎉 + +## Dataset Description 📊 + +The CLIcK benchmark comprises two broad categories: Culture and Language, which are further divided into 11 fine-grained subcategories. + +### Categories 📂 + +- **Language** 🗣️ + - Textual Knowledge + - Grammatical Knowledge + - Functional Knowledge + +- **Culture** 🌍 + - Korean Society + - Korean Tradition + - Korean Politics + - Korean Economy + - Korean Law + - Korean History + - Korean Geography + - Korean Popular Culture (K-Pop) + + +### Construction 🏗️ + +CLIcK was developed using two human-centric approaches: + +1. Reclassification of **official and well-designed exam data** into our defined categories. +2. Generation of questions using ChatGPT, based on **official educational materials** from the Korean Ministry of Justice, followed by our own validation process. + +### Structure 🏛️ + +The dataset is organized as follows, with each subcategory containing relevant JSON files: + +``` +📦CLIcK + └─ Dataset + ├─ Culture + │ ├─ [Each cultural subcategory with associated JSON files] + └─ Language + ├─ [Each language subcategory with associated JSON files] +``` + +### Exam Code Descriptions 📜 + +- KIIP: Korea Immigration & Integration Program ([Website](www.immigration.go.kr)) +- CSAT: College Scholastic Ability Test for Korean ([Website](https://www.suneung.re.kr/)) +- Kedu: Test of Teaching Korean as a Foreign Language exams ([Website](https://www.q-net.or.kr/man001.do?gSite=L&gId=36)) +- PSE: Public Service Exam for 9th grade +- TOPIK: Test of Proficiency in Korean ([Website](https://www.topik.go.kr/)) +- KHB: Korean History Exam Basic ([Website](https://www.historyexam.go.kr/)) +- PSAT: Public Service Aptitude Test in Korea + +## Results + +| Models | Average Accuracy (Korean Culture) | Average Accuracy (Korean Language) | +|-------------------|-----------------------------------|------------------------------------| +| Polyglot-Ko 1.3B | 32.71% | 22.88% | +| Polyglot-Ko 3.8B | 32.90% | 22.38% | +| Polyglot-Ko 5.8B | 33.14% | 23.27% | +| Polyglot-Ko 12.8B | 33.40% | 22.24% | +| KULLM 5.8B | 33.79% | 23.50% | +| KULLM 12.8B | 33.51% | 23.78% | +| KoAlpaca 5.8B | 32.33% | 23.87% | +| KoAlpaca 12.8B | 33.80% | 22.42% | +| LLaMA-Ko 7B | 33.26% | 25.69% | +| LLaMA 7B | 35.44% | 27.17% | +| LLaMA 13B | **36.22%** | **26.71%** | +| GPT-3.5 | 49.30% | 42.32% | +| Claude2 | **51.72%** | **45.39%** | + + +## Dataset Link 🔗 + +The CLIcK dataset is available on the Hugging Face Hub: [CLIcK Dataset](https://huggingface.co/datasets/your_username/CLIcK) + + +## Citation 📝 + +If you use CLIcK in your research, please cite our paper: + +```bibtex +@misc{kim2024click, + title={CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Korean}, + author={Eunsu Kim and Juyoung Suk and Philhoon Oh and Haneul Yoo and James Thorne and Alice Oh}, + year={2024}, + eprint={2403.06412}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +``` + +## Contact 📧 + +For any questions or inquiries, please contact [kes0317@kaist.ac.kr](mailto:kes0317@kaist.ac.kr)." +wikimedia/wit_base,"{""annotations_creators"": [""machine-generated""], ""language_creators"": [""found""], ""language"": [""af"", ""an"", ""ar"", ""arz"", ""ast"", ""az"", ""azb"", ""ba"", ""bar"", ""be"", ""bg"", ""bn"", ""br"", ""bs"", ""ca"", ""ce"", ""ceb"", ""ckb"", ""cs"", ""cv"", ""cy"", ""da"", ""de"", ""el"", ""en"", ""eo"", ""es"", ""et"", ""eu"", ""fa"", ""fi"", ""fil"", ""fr"", ""fy"", ""ga"", ""gl"", ""hi"", ""hr"", ""hsb"", ""ht"", ""hu"", ""hy"", ""ia"", ""id"", ""io"", ""is"", ""it"", ""iw"", ""ja"", ""jv"", ""ka"", ""kk"", ""kn"", ""ko"", ""la"", ""lah"", ""lb"", ""lmo"", ""lt"", ""lv"", ""mg"", ""mk"", ""ml"", ""mn"", ""mr"", ""ms"", ""my"", ""nan"", ""nds"", ""ne"", ""nl"", ""nn"", ""no"", ""nv"", ""oc"", ""pa"", ""pl"", ""pt"", ""qu"", ""ro"", ""ru"", ""sco"", ""si"", ""sk"", ""sl"", ""sq"", ""sr"", ""sv"", ""sw"", ""ta"", ""te"", ""tg"", ""th"", ""tr"", ""tt"", ""uk"", ""ur"", ""uz"", ""vec"", ""vi"", ""vo"", ""war"", ""xmf"", ""yue"", ""zh""], ""license"": [""cc-by-sa-4.0""], ""multilinguality"": [""multilingual""], ""size_categories"": [""1M The core training data is taken from the Wikipedia Image-Text (WIT) Dataset, a large curated set of more than 37 million image-text associations extracted from Wikipedia articles in 108 languages that was recently released by Google Research. +> +> The WIT dataset offers extremely valuable data about the pieces of text associated with Wikipedia images. However, due to licensing and data volume issues, the Google dataset only provides the image name and corresponding URL for download and not the raw image files. +> +> Getting easy access to the image files is crucial for participants to successfully develop competitive models. Therefore, today, the Wikimedia Research team is releasing its first large image dataset. It contains more than six million image files from Wikipedia articles in 100+ languages, which correspond to almost [1] all captioned images in the WIT dataset. Image files are provided at a 300-px resolution, a size that is suitable for most of the learning frameworks used to classify and analyze images. + +> [1] We are publishing all images having a non-null “reference description” in the WIT dataset. For privacy reasons, we are not publishing images where a person is the primary subject, i.e., where a person’s face covers more than 10% of the image surface. To identify faces and their bounding boxes, we use the RetinaFace detector. In addition, to avoid the inclusion of inappropriate images or images that violate copyright constraints, we have removed all images that are candidate for deletion on Commons from the dataset. + +**Note**: Compared to [Google's version](https://huggingface.co/datasets/google/wit), which has contents of one Wikipedia page per data sample, this version groups contents of all Wikipedia pages available in different languages for the image in one single data sample to avoid duplication of image bytes. + +### Supported Tasks and Leaderboards + +- `image-captioning`: This dataset can be used to train a model for image captioning where the goal is to predict a caption given the image. + +- `text-retrieval`: The goal in this task is to build a model that retrieves the text (`caption_title_and_reference_description`) closest to an image. The leaderboard for this task can be found [here](https://paperswithcode.com/sota/text-image-retrieval-on-wit). This task also has a competition on [Kaggle](https://www.kaggle.com/c/wikipedia-image-caption). + +In these tasks, any combination of the `caption_reference_description`, `caption_attribution_description` and `caption_alt_text_description` fields can be used as the input text/caption. + +### Languages + +The dataset contains examples from all Wikipedia languages. + +## Dataset Structure + +### Data Instances + +Each instance is an image, its representation in bytes, a pre-computed embedding, and the set of captions attached to the image in Wikipedia. + +``` +{ + 'image': , + 'image_url': 'https://upload.wikimedia.org/wikipedia/commons/8/8b/Scolopendra_gigantea.jpg', + 'embedding': [1.4784087, 2.8710432, 0.0, 0.51603067, ..., 10.266883, 0.51142216, 0.0, 2.3464653], + 'metadata_url': 'http://commons.wikimedia.org/wiki/File:Scolopendra_gigantea.jpg', + 'original_height': 3000, + 'original_width': 4000, + 'mime_type': 'image/jpeg', + 'caption_attribution_description': 'English: Puerto Rican Giant Centipede, Scolopendra gigantea; Vieques, Puerto Rico Slovenčina: Stonožka obrovská, Scolopendra gigantea; Vieques, Portoriko', + 'wit_features': { + 'language': ['ro', 'vi', 'sk', ..., 'nl', 'th', 'lv'], + 'page_url': ['https://ro.wikipedia.org/wiki/Scolopendra_gigantea', 'https://vi.wikipedia.org/wiki/Scolopendra_gigantea', 'https://sk.wikipedia.org/wiki/Scolopendra_gigantea', ..., 'https://nl.wikipedia.org/wiki/Scolopendra_gigantea', 'https://th.wikipedia.org/wiki/%E0%B8%95%E0%B8%B0%E0%B8%82%E0%B8%B2%E0%B8%9A%E0%B8%A2%E0%B8%B1%E0%B8%81%E0%B8%A9%E0%B9%8C%E0%B8%82%E0%B8%B2%E0%B9%80%E0%B8%AB%E0%B8%A5%E0%B8%B7%E0%B8%AD%E0%B8%87%E0%B9%80%E0%B8%9B%E0%B8%A3%E0%B8%B9', 'https://lv.wikipedia.org/wiki/Skolopendru_dzimta'], + 'attribution_passes_lang_id': [True, True, True, ..., True, True, True], + 'caption_alt_text_description': [None, None, None, ..., 'Scolopendra gigantea', None, 'Milzu skolopendra (Scolopendra gigantea)'], + 'caption_reference_description': [None, None, None, ..., None, None, 'Milzu skolopendra (Scolopendra gigantea)'], + 'caption_title_and_reference_description': [None, 'Scolopendra gigantea [SEP] ', None, ..., 'Scolopendra gigantea [SEP] ', None, 'Skolopendru dzimta [SEP] Milzu skolopendra (Scolopendra gigantea)'], + 'context_page_description': ['Scolopendra gigantea este un miriapod din clasa Chilopoda, fiind cel mai mare reprezentant al genului Scolopendra. Adultul poate atinge o lungime de 26 cm, uneori depășind 30 cm. Această specie habitează în regiunile de nord și de vest a Americii de Sud, pe insulele Trinidad, insulele Virgine, Jamaica Hispaniola ș.a. Localnicii denumesc scolopendra chilopodul gigant galben și chilopodul gigant amazonian.', 'Scolopendra gigantea là đại diện lớn nhất của chi Scolopendra nói riêng và cả lớp rết nói chung, thường đạt độ dài 26 cm và có thể vượt quá 30 cm. Sinh sống ở khu vực phía bắc và tây của Nam Mỹ và các đảo Trinidad, Puerto Rico, Saint Thomas, U.S. Virgin Islands, Jamaica, và Hispaniola.', 'Scolopendra gigantea, starší slovenský nazov: štípavica veľká, je živočích z rodu Scolopendra, s veľkosťou do 30 cm.', ..., 'Scolopendra gigantea is een tijgerduizendpoot uit Zuid-Amerika. De soort jaagt onder andere op grote geleedpotigen, amfibieën, reptielen en kleine zoogdieren. Het is voor zover bekend de grootste niet uitgestorven duizendpoot ter wereld.', 'ตะขาบยักษ์ขาเหลืองเปรู หรือ ตะขาบยักษ์อเมซอน เป็นตะขาบชนิดที่มีขนาดใหญ่ที่สุดในสกุล Scolopendra โดยปกติเมื่อโตเต็มที่จะยาว 26 เซนติเมตร แต่บางครั้งก็สามารถโตได้ถึง 30 เซนติเมตร ตะขาบชนิดนี้อาศัยอยู่ทางแถบเหนือและตะวันตกของทวีปอเมริกาใต้ และตามเกาะแก่งของประเทศตรินิแดดและจาไมกา เป็นสัตว์กินเนื้อ โดยกินจิ้งจก, กบ, นก, หนู และแม้แต่ค้างคาวเป็นอาหาร และขึ้นชื่อในเรื่องความดุร้าย', 'Skolpendru dzimta pieder pie simtkāju kārtas. Ap 400 dzimtas sugas sastopamas visā pasaulē, īpaši subtropu un tropu apgabalos. Mitinās augsnē, nobirušās lapās, plaisās, spraugās.'], + 'context_section_description': [None, 'Scolopendra gigantea (còn được gọi là Rết chân vàng khổng lồ Peru và Rết khổng lồ Amazon) là đại diện lớn nhất của chi Scolopendra nói riêng và cả lớp rết nói chung, thường đạt độ dài 26\xa0cm (10\xa0in) và có thể vượt quá 30\xa0cm (12\xa0in). Sinh sống ở khu vực phía bắc và tây của Nam Mỹ và các đảo Trinidad, Puerto Rico, Saint Thomas, U.S. Virgin Islands, Jamaica, và Hispaniola.', None, ..., 'Scolopendra gigantea is een tijgerduizendpoot uit Zuid-Amerika. De soort jaagt onder andere op grote geleedpotigen, amfibieën, reptielen en kleine zoogdieren. Het is voor zover bekend de grootste niet uitgestorven duizendpoot ter wereld.', None, 'Skolpendru dzimta (Scolopendridae) pieder pie simtkāju kārtas. Ap 400 dzimtas sugas sastopamas visā pasaulē, īpaši subtropu un tropu apgabalos. Mitinās augsnē, nobirušās lapās, plaisās, spraugās.'], + 'hierarchical_section_title': ['Scolopendra gigantea', 'Scolopendra gigantea', 'Scolopendra gigantea', ..., 'Scolopendra gigantea', 'ตะขาบยักษ์ขาเหลืองเปรู', 'Skolopendru dzimta'], + 'is_main_image': [True, True, True, ..., True, True, True], + 'page_title': ['Scolopendra gigantea', 'Scolopendra gigantea', 'Scolopendra gigantea', ..., 'Scolopendra gigantea', 'ตะขาบยักษ์ขาเหลืองเปรู', 'Skolopendru dzimta'], + 'section_title': [None, None, None, ..., None, None, None] + } +} +``` + +**Note**: The dataset is stored in Parquet for better performance. This dataset was generated from the original files using [this script](wit_base/blob/main/scripts/wit.py). Additionally, 120 examples from the original files have incorrectly formatted one or more of the following fields: `original_height`, `original_width`, `mime_type` and `caption_attribution_description`. The fixed versions of these examples that were used in the generation script can be found [here](wit_base/blob/main/scripts/corrected_examples.py). + +### Data Fields + +- `image`: A `PIL.Image.Image` object containing the image resized to a width of 300-px while preserving its aspect ratio. Note that when accessing the image column: `dataset[0][""image""]` the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the `""image""` column, *i.e.* `dataset[0][""image""]` should **always** be preferred over `dataset[""image""][0]`. +- `image_url`: URL to wikipedia image +- `embedding`: Precomputed image embedding. Each image is described with a 2048-dimensional signature extracted from the second-to-last layer of a [ResNet-50](https://arxiv.org/abs/1512.03385) neural network trained with [Imagenet](https://www.image-net.org/) data. These embeddings contain rich information about the image content and layout, in a compact form +- `metadata_url`: URL to wikimedia page containing the image and the metadata +- `original_height`: Original image height before resizing +- `original_width`: Original image width before resizing +- `mime_type`: Mime type associated to the image +- `caption_attribution_description`: This is the text found on the Wikimedia page of the image. This text is common to all occurrences of that image across all Wikipedias. +- `wit_features`: Sequence of captions for the image with language, page URL, information about the page, caption text, etc. + - `language`: Language code depicting wikipedia language of the page + - `page_url`: URL to wikipedia page + - `attribution_passes_lang_id`: Compared `language` field with the attribution language (written in the prefix of the attribution description. + - `caption_alt_text_description`: This is the “alt” text associated with the image. While not visible in general, it is commonly used for accessibility / screen readers + - `caption_reference_description`: This is the caption that is visible on the wikipedia page directly below the image. + - `caption_title_and_reference_description`: Concatenation of `page_title` and `caption_reference_description`. + - `context_page_description`: Corresponds to the short description of the page. It provides a concise explanation of the scope of the page. + - `context_section_description`: Text within the image's section + - `hierarchical_section_title`: Hierarchical section's title + - `is_main_image`: Flag determining if the image is the first image of the page. Usually displayed on the top-right part of the page when using web browsers. + - `page_changed_recently`: [More Information Needed] + - `page_title`: Wikipedia page's title + - `section_title`: Section's title + +

+
+Figure: WIT annotation example. +

+ +Details on the field content can be found directly in the [paper, figure 5 and table 12.](https://arxiv.org/abs/2103.01913) + +### Data Splits + +All data is held in `train` split, with a total of 6477255 examples. + +## Dataset Creation + +### Curation Rationale + +From the [official blog post](https://techblog.wikimedia.org/2021/09/09/the-wikipedia-image-caption-matching-challenge-and-a-huge-release-of-image-data-for-research/): + +> The WIT dataset offers extremely valuable data about the pieces of text associated with Wikipedia images. + +> Getting easy access to the image files is crucial for participants to successfully develop competitive models. + +> With this large release of visual data, we aim to help the competition participants—as well as researchers and practitioners who are interested in working with Wikipedia images—find and download the large number of image files associated with the challenge, in a compact form. + +### Source Data + +#### Initial Data Collection and Normalization + +From the [paper, section 3.1](https://arxiv.org/abs/2103.01913): + +> We started with all Wikipedia content pages (i.e., ignoring other +pages that have discussions, comments and such). These number about ~124M pages across 279 languages. + +#### Who are the source language producers? + +Text was extracted from Wikipedia. + +### Annotations + +#### Annotation process + +WIT was constructed using an automatic process. However it was human-validated. + +From the [paper, section 3.7](https://arxiv.org/abs/2103.01913): + +> To further verify the quality of the WIT dataset we performed a +study using (crowd-sourced) human annotators. As seen in Fig. 3, +we asked raters to answer 3 questions. Given an image and the page +title, raters first evaluate the quality of the attribution description +and reference description in the first two questions (order randomized). The third question understands the contextual quality of these +text descriptions given the page description and caption. Each response is on a 3-point scale: ""Yes"" if the text perfectly describes +the image, ""Maybe"" if it is sufficiently explanatory and ""No"" if it is +irrelevant or the image is inappropriate. + +#### Who are the annotators? + +[More Information Needed] + +### Personal and Sensitive Information + +From the [official blog post](https://techblog.wikimedia.org/2021/09/09/the-wikipedia-image-caption-matching-challenge-and-a-huge-release-of-image-data-for-research/#FN1): + +> For privacy reasons, we are not publishing images where a person is the primary subject, i.e., where a person’s face covers more than 10% of the image surface. To identify faces and their bounding boxes, we use the [RetinaFace](https://arxiv.org/abs/1905.00641) detector. In addition, to avoid the inclusion of inappropriate images or images that violate copyright constraints, we have removed all images that are [candidate for deletion](https://commons.wikimedia.org/wiki/Commons:Deletion_requests) on Commons from the dataset. + +## Considerations for Using the Data + +### Social Impact of Dataset + +[More Information Needed] + +### Discussion of Biases + +From the [paper, section 3.4](https://arxiv.org/abs/2103.01913): + +> Lastly we found that certain image-text pairs occurred very +frequently. These were often generic images that did not have +much to do with the main article page. Common examples +included flags, logos, maps, insignia and such. To prevent +biasing the data, we heavily under-sampled all such images + +### Other Known Limitations + +[More Information Needed] + +## Additional Information + +### Dataset Curators + +Miriam Redi, Fabian Kaelin and Tiziano Piccardi. + +### Licensing Information + +[CC BY-SA 4.0 international license](https://creativecommons.org/licenses/by-sa/4.0/) + +### Citation Information + +```bibtex +@article{srinivasan2021wit, + title={WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning}, + author={Srinivasan, Krishna and Raman, Karthik and Chen, Jiecao and Bendersky, Michael and Najork, Marc}, + journal={arXiv preprint arXiv:2103.01913}, + year={2021} +} +``` + +### Contributions + +Thanks to [@nateraw](https://github.com/nateraw), [yjernite](https://github.com/yjernite) and [mariosasko](https://github.com/mariosasko) for adding this dataset." +cis-lmu/GlotCC-V1,"{""license"": ""cc0-1.0"", ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/*/*.parquet""}]}, {""config_name"": ""eng-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/eng-Latn/*.parquet""}]}, {""config_name"": ""rus-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rus-Cyrl/*.parquet""}]}, {""config_name"": ""fra-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fra-Latn/*.parquet""}]}, {""config_name"": ""spa-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/spa-Latn/*.parquet""}]}, {""config_name"": ""deu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/deu-Latn/*.parquet""}]}, {""config_name"": ""pol-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pol-Latn/*.parquet""}]}, {""config_name"": ""vie-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/vie-Latn/*.parquet""}]}, {""config_name"": ""ita-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ita-Latn/*.parquet""}]}, {""config_name"": ""nld-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nld-Latn/*.parquet""}]}, {""config_name"": ""por-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/por-Latn/*.parquet""}]}, {""config_name"": ""ces-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ces-Latn/*.parquet""}]}, {""config_name"": ""fas-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fas-Arab/*.parquet""}]}, {""config_name"": ""tur-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tur-Latn/*.parquet""}]}, {""config_name"": ""tha-Thai"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tha-Thai/*.parquet""}]}, {""config_name"": ""ind-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ind-Latn/*.parquet""}]}, {""config_name"": ""cmn-Hani"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cmn-Hani/*.parquet""}]}, {""config_name"": ""hun-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hun-Latn/*.parquet""}]}, {""config_name"": ""ell-Grek"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ell-Grek/*.parquet""}]}, {""config_name"": ""swe-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/swe-Latn/*.parquet""}]}, {""config_name"": ""ron-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ron-Latn/*.parquet""}]}, {""config_name"": ""kor-Hang"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kor-Hang/*.parquet""}]}, {""config_name"": ""ukr-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ukr-Cyrl/*.parquet""}]}, {""config_name"": ""arb-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/arb-Arab/*.parquet""}]}, {""config_name"": ""fin-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fin-Latn/*.parquet""}]}, {""config_name"": ""slk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/slk-Latn/*.parquet""}]}, {""config_name"": ""bul-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bul-Cyrl/*.parquet""}]}, {""config_name"": ""dan-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dan-Latn/*.parquet""}]}, {""config_name"": ""heb-Hebr"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/heb-Hebr/*.parquet""}]}, {""config_name"": ""nob-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nob-Latn/*.parquet""}]}, {""config_name"": ""cat-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cat-Latn/*.parquet""}]}, {""config_name"": ""lit-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lit-Latn/*.parquet""}]}, {""config_name"": ""ben-Beng"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ben-Beng/*.parquet""}]}, {""config_name"": ""slv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/slv-Latn/*.parquet""}]}, {""config_name"": ""azj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/azj-Latn/*.parquet""}]}, {""config_name"": ""ekk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ekk-Latn/*.parquet""}]}, {""config_name"": ""lvs-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lvs-Latn/*.parquet""}]}, {""config_name"": ""hrv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hrv-Latn/*.parquet""}]}, {""config_name"": ""jpn-Jpan"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/jpn-Jpan/*.parquet""}]}, {""config_name"": ""tam-Taml"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tam-Taml/*.parquet""}]}, {""config_name"": ""srp-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/srp-Cyrl/*.parquet""}]}, {""config_name"": ""npi-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/npi-Deva/*.parquet""}]}, {""config_name"": ""kat-Geor"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kat-Geor/*.parquet""}]}, {""config_name"": ""hin-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hin-Deva/*.parquet""}]}, {""config_name"": ""hye-Armn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hye-Armn/*.parquet""}]}, {""config_name"": ""zsm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zsm-Latn/*.parquet""}]}, {""config_name"": ""als-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/als-Latn/*.parquet""}]}, {""config_name"": ""mkd-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mkd-Cyrl/*.parquet""}]}, {""config_name"": ""mal-Mlym"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mal-Mlym/*.parquet""}]}, {""config_name"": ""kiu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kiu-Latn/*.parquet""}]}, {""config_name"": ""urd-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/urd-Arab/*.parquet""}]}, {""config_name"": ""mya-Mymr"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mya-Mymr/*.parquet""}]}, {""config_name"": ""glg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/glg-Latn/*.parquet""}]}, {""config_name"": ""isl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/isl-Latn/*.parquet""}]}, {""config_name"": ""mar-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mar-Deva/*.parquet""}]}, {""config_name"": ""eus-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/eus-Latn/*.parquet""}]}, {""config_name"": ""kaz-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kaz-Cyrl/*.parquet""}]}, {""config_name"": ""tel-Telu"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tel-Telu/*.parquet""}]}, {""config_name"": ""lat-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lat-Latn/*.parquet""}]}, {""config_name"": ""khk-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/khk-Cyrl/*.parquet""}]}, {""config_name"": ""khm-Khmr"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/khm-Khmr/*.parquet""}]}, {""config_name"": ""bel-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bel-Cyrl/*.parquet""}]}, {""config_name"": ""kan-Knda"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kan-Knda/*.parquet""}]}, {""config_name"": ""bos-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bos-Latn/*.parquet""}]}, {""config_name"": ""guj-Gujr"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/guj-Gujr/*.parquet""}]}, {""config_name"": ""sin-Sinh"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sin-Sinh/*.parquet""}]}, {""config_name"": ""uzn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/uzn-Latn/*.parquet""}]}, {""config_name"": ""uzn-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/uzn-Cyrl/*.parquet""}]}, {""config_name"": ""fil-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fil-Latn/*.parquet""}]}, {""config_name"": ""pan-Guru"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pan-Guru/*.parquet""}]}, {""config_name"": ""nno-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nno-Latn/*.parquet""}]}, {""config_name"": ""cym-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cym-Latn/*.parquet""}]}, {""config_name"": ""afr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/afr-Latn/*.parquet""}]}, {""config_name"": ""kir-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kir-Cyrl/*.parquet""}]}, {""config_name"": ""tgk-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tgk-Cyrl/*.parquet""}]}, {""config_name"": ""swh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/swh-Latn/*.parquet""}]}, {""config_name"": ""epo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/epo-Latn/*.parquet""}]}, {""config_name"": ""pbt-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pbt-Arab/*.parquet""}]}, {""config_name"": ""gle-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gle-Latn/*.parquet""}]}, {""config_name"": ""tat-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tat-Cyrl/*.parquet""}]}, {""config_name"": ""anp-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/anp-Deva/*.parquet""}]}, {""config_name"": ""ory-Orya"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ory-Orya/*.parquet""}]}, {""config_name"": ""uig-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/uig-Arab/*.parquet""}]}, {""config_name"": ""ary-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ary-Arab/*.parquet""}]}, {""config_name"": ""lao-Laoo"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lao-Laoo/*.parquet""}]}, {""config_name"": ""mlt-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mlt-Latn/*.parquet""}]}, {""config_name"": ""amh-Ethi"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/amh-Ethi/*.parquet""}]}, {""config_name"": ""asm-Beng"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/asm-Beng/*.parquet""}]}, {""config_name"": ""bak-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bak-Cyrl/*.parquet""}]}, {""config_name"": ""div-Thaa"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/div-Thaa/*.parquet""}]}, {""config_name"": ""fao-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fao-Latn/*.parquet""}]}, {""config_name"": ""bod-Tibt"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bod-Tibt/*.parquet""}]}, {""config_name"": ""som-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/som-Latn/*.parquet""}]}, {""config_name"": ""ydd-Hebr"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ydd-Hebr/*.parquet""}]}, {""config_name"": ""ckb-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ckb-Arab/*.parquet""}]}, {""config_name"": ""fry-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fry-Latn/*.parquet""}]}, {""config_name"": ""kmr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kmr-Latn/*.parquet""}]}, {""config_name"": ""snd-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/snd-Arab/*.parquet""}]}, {""config_name"": ""ast-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ast-Latn/*.parquet""}]}, {""config_name"": ""gla-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gla-Latn/*.parquet""}]}, {""config_name"": ""oci-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/oci-Latn/*.parquet""}]}, {""config_name"": ""hau-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hau-Latn/*.parquet""}]}, {""config_name"": ""plt-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/plt-Latn/*.parquet""}]}, {""config_name"": ""tuk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tuk-Latn/*.parquet""}]}, {""config_name"": ""ltz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ltz-Latn/*.parquet""}]}, {""config_name"": ""arz-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/arz-Arab/*.parquet""}]}, {""config_name"": ""hyw-Armn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hyw-Armn/*.parquet""}]}, {""config_name"": ""san-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/san-Deva/*.parquet""}]}, {""config_name"": ""grc-Grek"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/grc-Grek/*.parquet""}]}, {""config_name"": ""cos-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cos-Latn/*.parquet""}]}, {""config_name"": ""hat-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hat-Latn/*.parquet""}]}, {""config_name"": ""mww-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mww-Latn/*.parquet""}]}, {""config_name"": ""jav-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/jav-Latn/*.parquet""}]}, {""config_name"": ""sun-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sun-Latn/*.parquet""}]}, {""config_name"": ""bew-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bew-Latn/*.parquet""}]}, {""config_name"": ""fro-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fro-Latn/*.parquet""}]}, {""config_name"": ""und-Mong"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/und-Mong/*.parquet""}]}, {""config_name"": ""mri-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mri-Latn/*.parquet""}]}, {""config_name"": ""kin-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kin-Latn/*.parquet""}]}, {""config_name"": ""xho-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/xho-Latn/*.parquet""}]}, {""config_name"": ""ibo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ibo-Latn/*.parquet""}]}, {""config_name"": ""kal-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kal-Latn/*.parquet""}]}, {""config_name"": ""bre-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bre-Latn/*.parquet""}]}, {""config_name"": ""yor-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yor-Latn/*.parquet""}]}, {""config_name"": ""ceb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ceb-Latn/*.parquet""}]}, {""config_name"": ""smo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/smo-Latn/*.parquet""}]}, {""config_name"": ""tir-Ethi"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tir-Ethi/*.parquet""}]}, {""config_name"": ""crh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/crh-Latn/*.parquet""}]}, {""config_name"": ""lim-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lim-Latn/*.parquet""}]}, {""config_name"": ""haw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/haw-Latn/*.parquet""}]}, {""config_name"": ""sot-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sot-Latn/*.parquet""}]}, {""config_name"": ""glk-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/glk-Arab/*.parquet""}]}, {""config_name"": ""gsw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gsw-Latn/*.parquet""}]}, {""config_name"": ""sna-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sna-Latn/*.parquet""}]}, {""config_name"": ""nya-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nya-Latn/*.parquet""}]}, {""config_name"": ""zul-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zul-Latn/*.parquet""}]}, {""config_name"": ""pnb-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pnb-Arab/*.parquet""}]}, {""config_name"": ""tyv-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tyv-Cyrl/*.parquet""}]}, {""config_name"": ""nds-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nds-Latn/*.parquet""}]}, {""config_name"": ""srd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/srd-Latn/*.parquet""}]}, {""config_name"": ""sme-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sme-Latn/*.parquet""}]}, {""config_name"": ""san-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/san-Latn/*.parquet""}]}, {""config_name"": ""arg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/arg-Latn/*.parquet""}]}, {""config_name"": ""pap-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pap-Latn/*.parquet""}]}, {""config_name"": ""mhr-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mhr-Cyrl/*.parquet""}]}, {""config_name"": ""srp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/srp-Latn/*.parquet""}]}, {""config_name"": ""hsb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hsb-Latn/*.parquet""}]}, {""config_name"": ""chv-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/chv-Cyrl/*.parquet""}]}, {""config_name"": ""vec-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/vec-Latn/*.parquet""}]}, {""config_name"": ""roh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/roh-Latn/*.parquet""}]}, {""config_name"": ""gaz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gaz-Latn/*.parquet""}]}, {""config_name"": ""che-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/che-Cyrl/*.parquet""}]}, {""config_name"": ""sah-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sah-Cyrl/*.parquet""}]}, {""config_name"": ""uig-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/uig-Cyrl/*.parquet""}]}, {""config_name"": ""sdh-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sdh-Arab/*.parquet""}]}, {""config_name"": ""azb-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/azb-Arab/*.parquet""}]}, {""config_name"": ""lus-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lus-Latn/*.parquet""}]}, {""config_name"": ""wln-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wln-Latn/*.parquet""}]}, {""config_name"": ""orv-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/orv-Cyrl/*.parquet""}]}, {""config_name"": ""sco-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sco-Latn/*.parquet""}]}, {""config_name"": ""scn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/scn-Latn/*.parquet""}]}, {""config_name"": ""cnh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cnh-Latn/*.parquet""}]}, {""config_name"": ""crh-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/crh-Cyrl/*.parquet""}]}, {""config_name"": ""mai-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mai-Deva/*.parquet""}]}, {""config_name"": ""syc-Syrc"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/syc-Syrc/*.parquet""}]}, {""config_name"": ""run-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/run-Latn/*.parquet""}]}, {""config_name"": ""bar-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bar-Latn/*.parquet""}]}, {""config_name"": ""rue-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rue-Cyrl/*.parquet""}]}, {""config_name"": ""gom-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gom-Deva/*.parquet""}]}, {""config_name"": ""bpy-Beng"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bpy-Beng/*.parquet""}]}, {""config_name"": ""nrm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nrm-Latn/*.parquet""}]}, {""config_name"": ""uig-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/uig-Latn/*.parquet""}]}, {""config_name"": ""urd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/urd-Latn/*.parquet""}]}, {""config_name"": ""bxr-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bxr-Cyrl/*.parquet""}]}, {""config_name"": ""nap-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nap-Latn/*.parquet""}]}, {""config_name"": ""hbo-Hebr"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hbo-Hebr/*.parquet""}]}, {""config_name"": ""ina-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ina-Latn/*.parquet""}]}, {""config_name"": ""ars-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ars-Arab/*.parquet""}]}, {""config_name"": ""pcm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pcm-Latn/*.parquet""}]}, {""config_name"": ""dag-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dag-Latn/*.parquet""}]}, {""config_name"": ""vls-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/vls-Latn/*.parquet""}]}, {""config_name"": ""kbd-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kbd-Cyrl/*.parquet""}]}, {""config_name"": ""vro-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/vro-Latn/*.parquet""}]}, {""config_name"": ""mni-Beng"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mni-Beng/*.parquet""}]}, {""config_name"": ""new-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/new-Deva/*.parquet""}]}, {""config_name"": ""ike-Cans"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ike-Cans/*.parquet""}]}, {""config_name"": ""gmh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gmh-Latn/*.parquet""}]}, {""config_name"": ""gug-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gug-Latn/*.parquet""}]}, {""config_name"": ""bcl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bcl-Latn/*.parquet""}]}, {""config_name"": ""tcy-Knda"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tcy-Knda/*.parquet""}]}, {""config_name"": ""shn-Mymr"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/shn-Mymr/*.parquet""}]}, {""config_name"": ""xmf-Geor"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/xmf-Geor/*.parquet""}]}, {""config_name"": ""frp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/frp-Latn/*.parquet""}]}, {""config_name"": ""fur-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fur-Latn/*.parquet""}]}, {""config_name"": ""ilo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ilo-Latn/*.parquet""}]}, {""config_name"": ""eml-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/eml-Latn/*.parquet""}]}, {""config_name"": ""kha-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kha-Latn/*.parquet""}]}, {""config_name"": ""lmo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lmo-Latn/*.parquet""}]}, {""config_name"": ""udm-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/udm-Cyrl/*.parquet""}]}, {""config_name"": ""min-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/min-Latn/*.parquet""}]}, {""config_name"": ""abk-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/abk-Cyrl/*.parquet""}]}, {""config_name"": ""bho-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bho-Deva/*.parquet""}]}, {""config_name"": ""bbc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bbc-Latn/*.parquet""}]}, {""config_name"": ""zea-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zea-Latn/*.parquet""}]}, {""config_name"": ""lij-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lij-Latn/*.parquet""}]}, {""config_name"": ""smj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/smj-Latn/*.parquet""}]}, {""config_name"": ""lfn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lfn-Latn/*.parquet""}]}, {""config_name"": ""yua-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yua-Latn/*.parquet""}]}, {""config_name"": ""ctd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ctd-Latn/*.parquet""}]}, {""config_name"": ""ido-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ido-Latn/*.parquet""}]}, {""config_name"": ""cnr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cnr-Latn/*.parquet""}]}, {""config_name"": ""sma-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sma-Latn/*.parquet""}]}, {""config_name"": ""szl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/szl-Latn/*.parquet""}]}, {""config_name"": ""kum-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kum-Cyrl/*.parquet""}]}, {""config_name"": ""ksh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ksh-Latn/*.parquet""}]}, {""config_name"": ""war-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/war-Latn/*.parquet""}]}, {""config_name"": ""mag-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mag-Deva/*.parquet""}]}, {""config_name"": ""lug-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lug-Latn/*.parquet""}]}, {""config_name"": ""ile-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ile-Latn/*.parquet""}]}, {""config_name"": ""krc-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/krc-Cyrl/*.parquet""}]}, {""config_name"": ""ava-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ava-Cyrl/*.parquet""}]}, {""config_name"": ""diq-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/diq-Latn/*.parquet""}]}, {""config_name"": ""rmy-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rmy-Cyrl/*.parquet""}]}, {""config_name"": ""kbp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kbp-Latn/*.parquet""}]}, {""config_name"": ""lad-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lad-Latn/*.parquet""}]}, {""config_name"": ""kab-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kab-Latn/*.parquet""}]}, {""config_name"": ""tzm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tzm-Latn/*.parquet""}]}, {""config_name"": ""hin-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hin-Latn/*.parquet""}]}, {""config_name"": ""sgs-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sgs-Latn/*.parquet""}]}, {""config_name"": ""cor-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cor-Latn/*.parquet""}]}, {""config_name"": ""tcz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tcz-Latn/*.parquet""}]}, {""config_name"": ""pms-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pms-Latn/*.parquet""}]}, {""config_name"": ""ace-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ace-Latn/*.parquet""}]}, {""config_name"": ""csb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/csb-Latn/*.parquet""}]}, {""config_name"": ""tah-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tah-Latn/*.parquet""}]}, {""config_name"": ""tsn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tsn-Latn/*.parquet""}]}, {""config_name"": ""cuk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cuk-Latn/*.parquet""}]}, {""config_name"": ""dzo-Tibt"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dzo-Tibt/*.parquet""}]}, {""config_name"": ""vep-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/vep-Latn/*.parquet""}]}, {""config_name"": ""kaa-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kaa-Cyrl/*.parquet""}]}, {""config_name"": ""mwl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mwl-Latn/*.parquet""}]}, {""config_name"": ""bal-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bal-Arab/*.parquet""}]}, {""config_name"": ""gcr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gcr-Latn/*.parquet""}]}, {""config_name"": ""cfm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cfm-Latn/*.parquet""}]}, {""config_name"": ""nan-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nan-Latn/*.parquet""}]}, {""config_name"": ""dsb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dsb-Latn/*.parquet""}]}, {""config_name"": ""frr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/frr-Latn/*.parquet""}]}, {""config_name"": ""tpi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tpi-Latn/*.parquet""}]}, {""config_name"": ""pjt-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pjt-Latn/*.parquet""}]}, {""config_name"": ""fij-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fij-Latn/*.parquet""}]}, {""config_name"": ""olo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/olo-Latn/*.parquet""}]}, {""config_name"": ""hac-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hac-Arab/*.parquet""}]}, {""config_name"": ""lez-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lez-Cyrl/*.parquet""}]}, {""config_name"": ""smn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/smn-Latn/*.parquet""}]}, {""config_name"": ""ban-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ban-Latn/*.parquet""}]}, {""config_name"": ""bam-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bam-Latn/*.parquet""}]}, {""config_name"": ""bjn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bjn-Latn/*.parquet""}]}, {""config_name"": ""tzm-Tfng"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tzm-Tfng/*.parquet""}]}, {""config_name"": ""ewe-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ewe-Latn/*.parquet""}]}, {""config_name"": ""pdc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pdc-Latn/*.parquet""}]}, {""config_name"": ""ltg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ltg-Latn/*.parquet""}]}, {""config_name"": ""kpv-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kpv-Cyrl/*.parquet""}]}, {""config_name"": ""lin-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lin-Latn/*.parquet""}]}, {""config_name"": ""pfl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pfl-Latn/*.parquet""}]}, {""config_name"": ""yue-Hani"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yue-Hani/*.parquet""}]}, {""config_name"": ""nqo-Nkoo"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nqo-Nkoo/*.parquet""}]}, {""config_name"": ""iso-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/iso-Latn/*.parquet""}]}, {""config_name"": ""dyu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dyu-Latn/*.parquet""}]}, {""config_name"": ""rup-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rup-Latn/*.parquet""}]}, {""config_name"": ""aeb-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/aeb-Arab/*.parquet""}]}, {""config_name"": ""iba-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/iba-Latn/*.parquet""}]}, {""config_name"": ""gos-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gos-Latn/*.parquet""}]}, {""config_name"": ""nde-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nde-Latn/*.parquet""}]}, {""config_name"": ""tso-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tso-Latn/*.parquet""}]}, {""config_name"": ""uzs-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/uzs-Arab/*.parquet""}]}, {""config_name"": ""krl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/krl-Latn/*.parquet""}]}, {""config_name"": ""mzn-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mzn-Arab/*.parquet""}]}, {""config_name"": ""stq-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/stq-Latn/*.parquet""}]}, {""config_name"": ""rmy-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rmy-Latn/*.parquet""}]}, {""config_name"": ""avk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/avk-Latn/*.parquet""}]}, {""config_name"": ""tok-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tok-Latn/*.parquet""}]}, {""config_name"": ""inh-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/inh-Cyrl/*.parquet""}]}, {""config_name"": ""wol-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wol-Latn/*.parquet""}]}, {""config_name"": ""ext-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ext-Latn/*.parquet""}]}, {""config_name"": ""tat-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tat-Latn/*.parquet""}]}, {""config_name"": ""lld-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lld-Latn/*.parquet""}]}, {""config_name"": ""wuu-Hani"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wuu-Hani/*.parquet""}]}, {""config_name"": ""aly-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/aly-Latn/*.parquet""}]}, {""config_name"": ""myv-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/myv-Cyrl/*.parquet""}]}, {""config_name"": ""tel-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tel-Latn/*.parquet""}]}, {""config_name"": ""fit-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fit-Latn/*.parquet""}]}, {""config_name"": ""mrw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mrw-Latn/*.parquet""}]}, {""config_name"": ""sms-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sms-Latn/*.parquet""}]}, {""config_name"": ""nav-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nav-Latn/*.parquet""}]}, {""config_name"": ""gil-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gil-Latn/*.parquet""}]}, {""config_name"": ""ayr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ayr-Latn/*.parquet""}]}, {""config_name"": ""goh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/goh-Latn/*.parquet""}]}, {""config_name"": ""hne-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hne-Deva/*.parquet""}]}, {""config_name"": ""jbo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/jbo-Latn/*.parquet""}]}, {""config_name"": ""ckm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ckm-Latn/*.parquet""}]}, {""config_name"": ""hil-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hil-Latn/*.parquet""}]}, {""config_name"": ""pon-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pon-Latn/*.parquet""}]}, {""config_name"": ""jam-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/jam-Latn/*.parquet""}]}, {""config_name"": ""bts-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bts-Latn/*.parquet""}]}, {""config_name"": ""azj-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/azj-Cyrl/*.parquet""}]}, {""config_name"": ""mah-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mah-Latn/*.parquet""}]}, {""config_name"": ""ubu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ubu-Latn/*.parquet""}]}, {""config_name"": ""sat-Olck"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sat-Olck/*.parquet""}]}, {""config_name"": ""oss-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/oss-Cyrl/*.parquet""}]}, {""config_name"": ""hui-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hui-Latn/*.parquet""}]}, {""config_name"": ""doi-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/doi-Deva/*.parquet""}]}, {""config_name"": ""swg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/swg-Latn/*.parquet""}]}, {""config_name"": ""tuc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tuc-Latn/*.parquet""}]}, {""config_name"": ""nso-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nso-Latn/*.parquet""}]}, {""config_name"": ""kjh-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kjh-Cyrl/*.parquet""}]}, {""config_name"": ""awa-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/awa-Deva/*.parquet""}]}, {""config_name"": ""mnw-Mymr"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mnw-Mymr/*.parquet""}]}, {""config_name"": ""jra-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/jra-Latn/*.parquet""}]}, {""config_name"": ""srn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/srn-Latn/*.parquet""}]}, {""config_name"": ""twi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/twi-Latn/*.parquet""}]}, {""config_name"": ""quc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/quc-Latn/*.parquet""}]}, {""config_name"": ""pam-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pam-Latn/*.parquet""}]}, {""config_name"": ""apc-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/apc-Arab/*.parquet""}]}, {""config_name"": ""pma-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pma-Latn/*.parquet""}]}, {""config_name"": ""ven-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ven-Latn/*.parquet""}]}, {""config_name"": ""hif-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hif-Latn/*.parquet""}]}, {""config_name"": ""kng-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kng-Latn/*.parquet""}]}, {""config_name"": ""acm-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/acm-Arab/*.parquet""}]}, {""config_name"": ""mrj-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mrj-Cyrl/*.parquet""}]}, {""config_name"": ""tvl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tvl-Latn/*.parquet""}]}, {""config_name"": ""brx-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/brx-Deva/*.parquet""}]}, {""config_name"": ""aaz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/aaz-Latn/*.parquet""}]}, {""config_name"": ""ton-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ton-Latn/*.parquet""}]}, {""config_name"": ""ndo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ndo-Latn/*.parquet""}]}, {""config_name"": ""cbk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cbk-Latn/*.parquet""}]}, {""config_name"": ""gom-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gom-Latn/*.parquet""}]}, {""config_name"": ""und-Newa"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/und-Newa/*.parquet""}]}, {""config_name"": ""yao-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yao-Latn/*.parquet""}]}, {""config_name"": ""pan-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pan-Latn/*.parquet""}]}, {""config_name"": ""aln-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/aln-Latn/*.parquet""}]}, {""config_name"": ""kpg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kpg-Latn/*.parquet""}]}, {""config_name"": ""non-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/non-Latn/*.parquet""}]}, {""config_name"": ""ksw-Mymr"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ksw-Mymr/*.parquet""}]}, {""config_name"": ""vol-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/vol-Latn/*.parquet""}]}, {""config_name"": ""rmc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rmc-Latn/*.parquet""}]}, {""config_name"": ""bru-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bru-Latn/*.parquet""}]}, {""config_name"": ""kas-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kas-Arab/*.parquet""}]}, {""config_name"": ""tog-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tog-Latn/*.parquet""}]}, {""config_name"": ""rmn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rmn-Latn/*.parquet""}]}, {""config_name"": ""pcd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pcd-Latn/*.parquet""}]}, {""config_name"": ""pis-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pis-Latn/*.parquet""}]}, {""config_name"": ""nsn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nsn-Latn/*.parquet""}]}, {""config_name"": ""cmo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cmo-Latn/*.parquet""}]}, {""config_name"": ""blk-Mymr"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/blk-Mymr/*.parquet""}]}, {""config_name"": ""gnn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gnn-Latn/*.parquet""}]}, {""config_name"": ""pck-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pck-Latn/*.parquet""}]}, {""config_name"": ""iou-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/iou-Latn/*.parquet""}]}, {""config_name"": ""und-Sylo"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/und-Sylo/*.parquet""}]}, {""config_name"": ""yml-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yml-Latn/*.parquet""}]}, {""config_name"": ""atj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/atj-Latn/*.parquet""}]}, {""config_name"": ""nia-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nia-Latn/*.parquet""}]}, {""config_name"": ""glv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/glv-Latn/*.parquet""}]}, {""config_name"": ""ium-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ium-Latn/*.parquet""}]}, {""config_name"": ""hnj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hnj-Latn/*.parquet""}]}, {""config_name"": ""fue-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fue-Latn/*.parquet""}]}, {""config_name"": ""ron-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ron-Cyrl/*.parquet""}]}, {""config_name"": ""seh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/seh-Latn/*.parquet""}]}, {""config_name"": ""gul-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gul-Latn/*.parquet""}]}, {""config_name"": ""luo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/luo-Latn/*.parquet""}]}, {""config_name"": ""etr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/etr-Latn/*.parquet""}]}, {""config_name"": ""mfe-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mfe-Latn/*.parquet""}]}, {""config_name"": ""und-Hung"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/und-Hung/*.parquet""}]}, {""config_name"": ""und-Dsrt"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/und-Dsrt/*.parquet""}]}, {""config_name"": ""tam-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tam-Latn/*.parquet""}]}, {""config_name"": ""swb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/swb-Latn/*.parquet""}]}, {""config_name"": ""agd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/agd-Latn/*.parquet""}]}, {""config_name"": ""crs-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/crs-Latn/*.parquet""}]}, {""config_name"": ""kac-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kac-Latn/*.parquet""}]}, {""config_name"": ""aoj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/aoj-Latn/*.parquet""}]}, {""config_name"": ""enm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/enm-Latn/*.parquet""}]}, {""config_name"": ""her-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/her-Latn/*.parquet""}]}, {""config_name"": ""yap-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yap-Latn/*.parquet""}]}, {""config_name"": ""quz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/quz-Latn/*.parquet""}]}, {""config_name"": ""gcf-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gcf-Latn/*.parquet""}]}, {""config_name"": ""fkv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fkv-Latn/*.parquet""}]}, {""config_name"": ""tly-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tly-Latn/*.parquet""}]}, {""config_name"": ""szy-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/szy-Latn/*.parquet""}]}, {""config_name"": ""rad-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rad-Latn/*.parquet""}]}, {""config_name"": ""umb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/umb-Latn/*.parquet""}]}, {""config_name"": ""hwc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hwc-Latn/*.parquet""}]}, {""config_name"": ""wmw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wmw-Latn/*.parquet""}]}, {""config_name"": ""knv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/knv-Latn/*.parquet""}]}, {""config_name"": ""bxh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bxh-Latn/*.parquet""}]}, {""config_name"": ""mui-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mui-Latn/*.parquet""}]}, {""config_name"": ""mdf-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mdf-Cyrl/*.parquet""}]}, {""config_name"": ""cnk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cnk-Latn/*.parquet""}]}, {""config_name"": ""nbl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nbl-Latn/*.parquet""}]}, {""config_name"": ""llg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/llg-Latn/*.parquet""}]}, {""config_name"": ""spl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/spl-Latn/*.parquet""}]}, {""config_name"": ""abq-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/abq-Cyrl/*.parquet""}]}, {""config_name"": ""mns-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mns-Cyrl/*.parquet""}]}, {""config_name"": ""kyc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kyc-Latn/*.parquet""}]}, {""config_name"": ""tnk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tnk-Latn/*.parquet""}]}, {""config_name"": ""ssd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ssd-Latn/*.parquet""}]}, {""config_name"": ""rug-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rug-Latn/*.parquet""}]}, {""config_name"": ""und-Syrc"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/und-Syrc/*.parquet""}]}, {""config_name"": ""alt-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/alt-Cyrl/*.parquet""}]}, {""config_name"": ""quy-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/quy-Latn/*.parquet""}]}, {""config_name"": ""lif-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lif-Deva/*.parquet""}]}, {""config_name"": ""nah-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nah-Latn/*.parquet""}]}, {""config_name"": ""nwi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nwi-Latn/*.parquet""}]}, {""config_name"": ""wnu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wnu-Latn/*.parquet""}]}, {""config_name"": ""gfk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gfk-Latn/*.parquet""}]}, {""config_name"": ""iws-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/iws-Latn/*.parquet""}]}, {""config_name"": ""hot-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hot-Latn/*.parquet""}]}, {""config_name"": ""ang-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ang-Latn/*.parquet""}]}, {""config_name"": ""nyy-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nyy-Latn/*.parquet""}]}, {""config_name"": ""dob-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dob-Latn/*.parquet""}]}, {""config_name"": ""kpw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kpw-Latn/*.parquet""}]}, {""config_name"": ""kua-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kua-Latn/*.parquet""}]}, {""config_name"": ""nch-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nch-Latn/*.parquet""}]}, {""config_name"": ""row-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/row-Latn/*.parquet""}]}, {""config_name"": ""trp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/trp-Latn/*.parquet""}]}, {""config_name"": ""koi-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/koi-Cyrl/*.parquet""}]}, {""config_name"": ""for-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/for-Latn/*.parquet""}]}, {""config_name"": ""mal-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mal-Latn/*.parquet""}]}, {""config_name"": ""toi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/toi-Latn/*.parquet""}]}, {""config_name"": ""dng-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dng-Cyrl/*.parquet""}]}, {""config_name"": ""nhg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nhg-Latn/*.parquet""}]}, {""config_name"": ""lue-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lue-Latn/*.parquet""}]}, {""config_name"": ""thl-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/thl-Deva/*.parquet""}]}, {""config_name"": ""sny-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sny-Latn/*.parquet""}]}, {""config_name"": ""soq-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/soq-Latn/*.parquet""}]}, {""config_name"": ""mpp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mpp-Latn/*.parquet""}]}, {""config_name"": ""rwo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rwo-Latn/*.parquet""}]}, {""config_name"": ""roo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/roo-Latn/*.parquet""}]}, {""config_name"": ""gaa-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gaa-Latn/*.parquet""}]}, {""config_name"": ""ngl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ngl-Latn/*.parquet""}]}, {""config_name"": ""bis-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bis-Latn/*.parquet""}]}, {""config_name"": ""tkl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tkl-Latn/*.parquet""}]}, {""config_name"": ""poi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/poi-Latn/*.parquet""}]}, {""config_name"": ""dad-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dad-Latn/*.parquet""}]}, {""config_name"": ""msy-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/msy-Latn/*.parquet""}]}, {""config_name"": ""asm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/asm-Latn/*.parquet""}]}, {""config_name"": ""fuf-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fuf-Latn/*.parquet""}]}, {""config_name"": ""rar-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rar-Latn/*.parquet""}]}, {""config_name"": ""tnn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tnn-Latn/*.parquet""}]}, {""config_name"": ""wsk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wsk-Latn/*.parquet""}]}, {""config_name"": ""xal-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/xal-Cyrl/*.parquet""}]}, {""config_name"": ""arl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/arl-Latn/*.parquet""}]}, {""config_name"": ""jac-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/jac-Latn/*.parquet""}]}, {""config_name"": ""zyb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zyb-Latn/*.parquet""}]}, {""config_name"": ""guw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/guw-Latn/*.parquet""}]}, {""config_name"": ""mmx-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mmx-Latn/*.parquet""}]}, {""config_name"": ""huu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/huu-Latn/*.parquet""}]}, {""config_name"": ""emi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/emi-Latn/*.parquet""}]}, {""config_name"": ""qxo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/qxo-Latn/*.parquet""}]}, {""config_name"": ""yuj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yuj-Latn/*.parquet""}]}, {""config_name"": ""enq-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/enq-Latn/*.parquet""}]}, {""config_name"": ""mni-Mtei"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mni-Mtei/*.parquet""}]}, {""config_name"": ""aii-Syrc"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/aii-Syrc/*.parquet""}]}, {""config_name"": ""bon-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bon-Latn/*.parquet""}]}, {""config_name"": ""boa-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/boa-Latn/*.parquet""}]}, {""config_name"": ""gah-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gah-Latn/*.parquet""}]}, {""config_name"": ""sus-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sus-Latn/*.parquet""}]}, {""config_name"": ""kyu-Kali"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kyu-Kali/*.parquet""}]}, {""config_name"": ""bch-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bch-Latn/*.parquet""}]}, {""config_name"": ""mhw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mhw-Latn/*.parquet""}]}, {""config_name"": ""apb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/apb-Latn/*.parquet""}]}, {""config_name"": ""zat-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zat-Latn/*.parquet""}]}, {""config_name"": ""acu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/acu-Latn/*.parquet""}]}, {""config_name"": ""ipi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ipi-Latn/*.parquet""}]}, {""config_name"": ""kze-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kze-Latn/*.parquet""}]}, {""config_name"": ""ikt-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ikt-Latn/*.parquet""}]}, {""config_name"": ""ong-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ong-Latn/*.parquet""}]}, {""config_name"": ""bci-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bci-Latn/*.parquet""}]}, {""config_name"": ""mps-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mps-Latn/*.parquet""}]}, {""config_name"": ""ssw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ssw-Latn/*.parquet""}]}, {""config_name"": ""ben-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ben-Latn/*.parquet""}]}, {""config_name"": ""gor-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gor-Latn/*.parquet""}]}, {""config_name"": ""bmu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bmu-Latn/*.parquet""}]}, {""config_name"": ""mur-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mur-Latn/*.parquet""}]}, {""config_name"": ""yle-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yle-Latn/*.parquet""}]}, {""config_name"": ""mgh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mgh-Latn/*.parquet""}]}, {""config_name"": ""hmr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hmr-Latn/*.parquet""}]}, {""config_name"": ""cak-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cak-Latn/*.parquet""}]}, {""config_name"": ""avt-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/avt-Latn/*.parquet""}]}, {""config_name"": ""kri-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kri-Latn/*.parquet""}]}, {""config_name"": ""yss-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yss-Latn/*.parquet""}]}, {""config_name"": ""ubr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ubr-Latn/*.parquet""}]}, {""config_name"": ""snn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/snn-Latn/*.parquet""}]}, {""config_name"": ""brh-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/brh-Arab/*.parquet""}]}, {""config_name"": ""rop-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rop-Latn/*.parquet""}]}, {""config_name"": ""btx-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/btx-Latn/*.parquet""}]}, {""config_name"": ""fon-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fon-Latn/*.parquet""}]}, {""config_name"": ""bjp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bjp-Latn/*.parquet""}]}, {""config_name"": ""tum-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tum-Latn/*.parquet""}]}, {""config_name"": ""aau-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/aau-Latn/*.parquet""}]}, {""config_name"": ""opm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/opm-Latn/*.parquet""}]}, {""config_name"": ""efi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/efi-Latn/*.parquet""}]}, {""config_name"": ""chu-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/chu-Cyrl/*.parquet""}]}, {""config_name"": ""mnk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mnk-Latn/*.parquet""}]}, {""config_name"": ""tnp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tnp-Latn/*.parquet""}]}, {""config_name"": ""cop-Copt"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cop-Copt/*.parquet""}]}, {""config_name"": ""sbe-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sbe-Latn/*.parquet""}]}, {""config_name"": ""kaq-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kaq-Latn/*.parquet""}]}, {""config_name"": ""lww-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lww-Latn/*.parquet""}]}, {""config_name"": ""aoi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/aoi-Latn/*.parquet""}]}, {""config_name"": ""apz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/apz-Latn/*.parquet""}]}, {""config_name"": ""ffm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ffm-Latn/*.parquet""}]}, {""config_name"": ""wes-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wes-Latn/*.parquet""}]}, {""config_name"": ""dar-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dar-Cyrl/*.parquet""}]}, {""config_name"": ""tke-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tke-Latn/*.parquet""}]}, {""config_name"": ""tgp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tgp-Latn/*.parquet""}]}, {""config_name"": ""got-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/got-Latn/*.parquet""}]}, {""config_name"": ""gag-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gag-Latn/*.parquet""}]}, {""config_name"": ""att-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/att-Latn/*.parquet""}]}, {""config_name"": ""arb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/arb-Latn/*.parquet""}]}, {""config_name"": ""ify-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ify-Latn/*.parquet""}]}, {""config_name"": ""kbh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kbh-Latn/*.parquet""}]}, {""config_name"": ""gaw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gaw-Latn/*.parquet""}]}, {""config_name"": ""rcf-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rcf-Latn/*.parquet""}]}, {""config_name"": ""rro-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rro-Latn/*.parquet""}]}, {""config_name"": ""mcq-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mcq-Latn/*.parquet""}]}, {""config_name"": ""loz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/loz-Latn/*.parquet""}]}, {""config_name"": ""cbu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cbu-Latn/*.parquet""}]}, {""config_name"": ""niu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/niu-Latn/*.parquet""}]}, {""config_name"": ""tvk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tvk-Latn/*.parquet""}]}, {""config_name"": ""qup-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/qup-Latn/*.parquet""}]}, {""config_name"": ""kij-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kij-Latn/*.parquet""}]}, {""config_name"": ""tlh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tlh-Latn/*.parquet""}]}, {""config_name"": ""cpc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cpc-Latn/*.parquet""}]}, {""config_name"": ""kqc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kqc-Latn/*.parquet""}]}, {""config_name"": ""kvg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kvg-Latn/*.parquet""}]}, {""config_name"": ""nov-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nov-Latn/*.parquet""}]}, {""config_name"": ""bba-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bba-Latn/*.parquet""}]}, {""config_name"": ""teo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/teo-Latn/*.parquet""}]}, {""config_name"": ""pdt-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pdt-Latn/*.parquet""}]}, {""config_name"": ""mux-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mux-Latn/*.parquet""}]}, {""config_name"": ""geb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/geb-Latn/*.parquet""}]}, {""config_name"": ""byr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/byr-Latn/*.parquet""}]}, {""config_name"": ""dao-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dao-Latn/*.parquet""}]}, {""config_name"": ""lbj-Tibt"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lbj-Tibt/*.parquet""}]}, {""config_name"": ""kos-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kos-Latn/*.parquet""}]}, {""config_name"": ""zom-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zom-Latn/*.parquet""}]}, {""config_name"": ""nzi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nzi-Latn/*.parquet""}]}, {""config_name"": ""ann-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ann-Latn/*.parquet""}]}, {""config_name"": ""nvm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nvm-Latn/*.parquet""}]}, {""config_name"": ""guz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/guz-Latn/*.parquet""}]}, {""config_name"": ""liv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/liv-Latn/*.parquet""}]}, {""config_name"": ""mkn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mkn-Latn/*.parquet""}]}, {""config_name"": ""kik-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kik-Latn/*.parquet""}]}, {""config_name"": ""nog-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nog-Cyrl/*.parquet""}]}, {""config_name"": ""ady-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ady-Cyrl/*.parquet""}]}, {""config_name"": ""mic-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mic-Latn/*.parquet""}]}, {""config_name"": ""shi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/shi-Latn/*.parquet""}]}, {""config_name"": ""nop-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nop-Latn/*.parquet""}]}, {""config_name"": ""pui-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pui-Latn/*.parquet""}]}, {""config_name"": ""kdl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kdl-Latn/*.parquet""}]}, {""config_name"": ""agm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/agm-Latn/*.parquet""}]}, {""config_name"": ""mna-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mna-Latn/*.parquet""}]}, {""config_name"": ""mar-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mar-Latn/*.parquet""}]}, {""config_name"": ""smk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/smk-Latn/*.parquet""}]}, {""config_name"": ""chk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/chk-Latn/*.parquet""}]}, {""config_name"": ""myy-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/myy-Latn/*.parquet""}]}, {""config_name"": ""kca-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kca-Cyrl/*.parquet""}]}, {""config_name"": ""snp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/snp-Latn/*.parquet""}]}, {""config_name"": ""mti-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mti-Latn/*.parquet""}]}, {""config_name"": ""chd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/chd-Latn/*.parquet""}]}, {""config_name"": ""tzo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tzo-Latn/*.parquet""}]}, {""config_name"": ""nnh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nnh-Latn/*.parquet""}]}, {""config_name"": ""klv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/klv-Latn/*.parquet""}]}, {""config_name"": ""myk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/myk-Latn/*.parquet""}]}, {""config_name"": ""gdn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gdn-Latn/*.parquet""}]}, {""config_name"": ""pao-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pao-Latn/*.parquet""}]}, {""config_name"": ""kea-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kea-Latn/*.parquet""}]}, {""config_name"": ""mni-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mni-Latn/*.parquet""}]}, {""config_name"": ""meu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/meu-Latn/*.parquet""}]}, {""config_name"": ""ata-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ata-Latn/*.parquet""}]}, {""config_name"": ""mam-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mam-Latn/*.parquet""}]}, {""config_name"": ""lub-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lub-Latn/*.parquet""}]}, {""config_name"": ""cni-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cni-Latn/*.parquet""}]}, {""config_name"": ""cjv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cjv-Latn/*.parquet""}]}, {""config_name"": ""fuh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fuh-Latn/*.parquet""}]}, {""config_name"": ""prg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/prg-Latn/*.parquet""}]}, {""config_name"": ""suk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/suk-Latn/*.parquet""}]}, {""config_name"": ""hak-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hak-Latn/*.parquet""}]}, {""config_name"": ""tet-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tet-Latn/*.parquet""}]}, {""config_name"": ""ghs-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ghs-Latn/*.parquet""}]}, {""config_name"": ""gng-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gng-Latn/*.parquet""}]}, {""config_name"": ""crn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/crn-Latn/*.parquet""}]}, {""config_name"": ""mdy-Ethi"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mdy-Ethi/*.parquet""}]}, {""config_name"": ""hns-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hns-Latn/*.parquet""}]}, {""config_name"": ""skr-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/skr-Arab/*.parquet""}]}, {""config_name"": ""zas-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zas-Latn/*.parquet""}]}, {""config_name"": ""arn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/arn-Latn/*.parquet""}]}, {""config_name"": ""ami-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ami-Latn/*.parquet""}]}, {""config_name"": ""gam-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gam-Latn/*.parquet""}]}, {""config_name"": ""bug-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bug-Latn/*.parquet""}]}, {""config_name"": ""cut-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cut-Latn/*.parquet""}]}, {""config_name"": ""crk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/crk-Latn/*.parquet""}]}, {""config_name"": ""fuv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fuv-Latn/*.parquet""}]}, {""config_name"": ""pag-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pag-Latn/*.parquet""}]}, {""config_name"": ""wrs-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wrs-Latn/*.parquet""}]}, {""config_name"": ""moh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/moh-Latn/*.parquet""}]}, {""config_name"": ""cao-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cao-Latn/*.parquet""}]}, {""config_name"": ""nlg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nlg-Latn/*.parquet""}]}, {""config_name"": ""hmo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hmo-Latn/*.parquet""}]}, {""config_name"": ""pwn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pwn-Latn/*.parquet""}]}, {""config_name"": ""vmy-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/vmy-Latn/*.parquet""}]}, {""config_name"": ""heg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/heg-Latn/*.parquet""}]}, {""config_name"": ""spm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/spm-Latn/*.parquet""}]}, {""config_name"": ""gwi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gwi-Latn/*.parquet""}]}, {""config_name"": ""syb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/syb-Latn/*.parquet""}]}, {""config_name"": ""ian-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ian-Latn/*.parquet""}]}, {""config_name"": ""ppk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ppk-Latn/*.parquet""}]}, {""config_name"": ""akb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/akb-Latn/*.parquet""}]}, {""config_name"": ""raw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/raw-Latn/*.parquet""}]}, {""config_name"": ""nhr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nhr-Latn/*.parquet""}]}, {""config_name"": ""chw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/chw-Latn/*.parquet""}]}, {""config_name"": ""nas-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nas-Latn/*.parquet""}]}, {""config_name"": ""cot-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cot-Latn/*.parquet""}]}, {""config_name"": ""npi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/npi-Latn/*.parquet""}]}, {""config_name"": ""nhe-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nhe-Latn/*.parquet""}]}, {""config_name"": ""dik-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dik-Latn/*.parquet""}]}, {""config_name"": ""kwj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kwj-Latn/*.parquet""}]}, {""config_name"": ""bkd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bkd-Latn/*.parquet""}]}, {""config_name"": ""tku-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tku-Latn/*.parquet""}]}, {""config_name"": ""quh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/quh-Latn/*.parquet""}]}, {""config_name"": ""agr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/agr-Latn/*.parquet""}]}, {""config_name"": ""pau-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pau-Latn/*.parquet""}]}, {""config_name"": ""lam-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lam-Latn/*.parquet""}]}, {""config_name"": ""kmu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kmu-Latn/*.parquet""}]}, {""config_name"": ""mad-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mad-Latn/*.parquet""}]}, {""config_name"": ""cpy-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cpy-Latn/*.parquet""}]}, {""config_name"": ""snc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/snc-Latn/*.parquet""}]}, {""config_name"": ""avu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/avu-Latn/*.parquet""}]}, {""config_name"": ""nbu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nbu-Latn/*.parquet""}]}, {""config_name"": ""yut-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yut-Latn/*.parquet""}]}, {""config_name"": ""vun-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/vun-Latn/*.parquet""}]}, {""config_name"": ""zac-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zac-Latn/*.parquet""}]}, {""config_name"": ""gdg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gdg-Latn/*.parquet""}]}, {""config_name"": ""buk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/buk-Latn/*.parquet""}]}, {""config_name"": ""ota-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ota-Arab/*.parquet""}]}, {""config_name"": ""qub-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/qub-Latn/*.parquet""}]}, {""config_name"": ""dwr-Ethi"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dwr-Ethi/*.parquet""}]}, {""config_name"": ""sue-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sue-Latn/*.parquet""}]}, {""config_name"": ""ksd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ksd-Latn/*.parquet""}]}, {""config_name"": ""mak-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mak-Latn/*.parquet""}]}, {""config_name"": ""bmh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bmh-Latn/*.parquet""}]}, {""config_name"": ""kto-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kto-Latn/*.parquet""}]}, {""config_name"": ""azg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/azg-Latn/*.parquet""}]}, {""config_name"": ""kaa-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kaa-Latn/*.parquet""}]}, {""config_name"": ""amf-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/amf-Latn/*.parquet""}]}, {""config_name"": ""nfa-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nfa-Latn/*.parquet""}]}, {""config_name"": ""abs-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/abs-Latn/*.parquet""}]}, {""config_name"": ""trq-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/trq-Latn/*.parquet""}]}, {""config_name"": ""fub-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fub-Latn/*.parquet""}]}, {""config_name"": ""bhg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bhg-Latn/*.parquet""}]}, {""config_name"": ""uvh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/uvh-Latn/*.parquet""}]}, {""config_name"": ""qxl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/qxl-Latn/*.parquet""}]}, {""config_name"": ""nss-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nss-Latn/*.parquet""}]}, {""config_name"": ""ndc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ndc-Latn/*.parquet""}]}, {""config_name"": ""mup-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mup-Deva/*.parquet""}]}, {""config_name"": ""zia-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zia-Latn/*.parquet""}]}, {""config_name"": ""bem-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bem-Latn/*.parquet""}]}, {""config_name"": ""bvr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bvr-Latn/*.parquet""}]}, {""config_name"": ""aoz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/aoz-Latn/*.parquet""}]}, {""config_name"": ""yal-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yal-Latn/*.parquet""}]}, {""config_name"": ""ixl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ixl-Latn/*.parquet""}]}, {""config_name"": ""ach-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ach-Latn/*.parquet""}]}, {""config_name"": ""lbk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lbk-Latn/*.parquet""}]}, {""config_name"": ""bnp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bnp-Latn/*.parquet""}]}, {""config_name"": ""lbb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lbb-Latn/*.parquet""}]}, {""config_name"": ""cac-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cac-Latn/*.parquet""}]}, {""config_name"": ""otw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/otw-Latn/*.parquet""}]}, {""config_name"": ""tbo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tbo-Latn/*.parquet""}]}, {""config_name"": ""nhi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nhi-Latn/*.parquet""}]}, {""config_name"": ""naq-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/naq-Latn/*.parquet""}]}, {""config_name"": ""tzj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tzj-Latn/*.parquet""}]}, {""config_name"": ""mmo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mmo-Latn/*.parquet""}]}, {""config_name"": ""dgz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dgz-Latn/*.parquet""}]}, {""config_name"": ""bbr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bbr-Latn/*.parquet""}]}, {""config_name"": ""nin-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nin-Latn/*.parquet""}]}, {""config_name"": ""taq-Tfng"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/taq-Tfng/*.parquet""}]}, {""config_name"": ""cgc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cgc-Latn/*.parquet""}]}, {""config_name"": ""dak-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dak-Latn/*.parquet""}]}, {""config_name"": ""okv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/okv-Latn/*.parquet""}]}, {""config_name"": ""mxv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mxv-Latn/*.parquet""}]}, {""config_name"": ""mos-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mos-Latn/*.parquet""}]}, {""config_name"": ""aom-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/aom-Latn/*.parquet""}]}, {""config_name"": ""wlx-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wlx-Latn/*.parquet""}]}, {""config_name"": ""car-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/car-Latn/*.parquet""}]}, {""config_name"": ""jvn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/jvn-Latn/*.parquet""}]}, {""config_name"": ""yrk-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yrk-Cyrl/*.parquet""}]}, {""config_name"": ""mvn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mvn-Latn/*.parquet""}]}, {""config_name"": ""tmd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tmd-Latn/*.parquet""}]}, {""config_name"": ""omw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/omw-Latn/*.parquet""}]}, {""config_name"": ""kyz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kyz-Latn/*.parquet""}]}, {""config_name"": ""suc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/suc-Latn/*.parquet""}]}, {""config_name"": ""lgl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lgl-Latn/*.parquet""}]}, {""config_name"": ""zpt-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zpt-Latn/*.parquet""}]}, {""config_name"": ""zao-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zao-Latn/*.parquet""}]}, {""config_name"": ""nyn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nyn-Latn/*.parquet""}]}, {""config_name"": ""rmn-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rmn-Cyrl/*.parquet""}]}, {""config_name"": ""kkc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kkc-Latn/*.parquet""}]}, {""config_name"": ""kpr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kpr-Latn/*.parquet""}]}, {""config_name"": ""wos-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wos-Latn/*.parquet""}]}, {""config_name"": ""mbb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mbb-Latn/*.parquet""}]}, {""config_name"": ""kbm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kbm-Latn/*.parquet""}]}, {""config_name"": ""ajp-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ajp-Arab/*.parquet""}]}, {""config_name"": ""caa-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/caa-Latn/*.parquet""}]}, {""config_name"": ""dgc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dgc-Latn/*.parquet""}]}, {""config_name"": ""leu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/leu-Latn/*.parquet""}]}, {""config_name"": ""upv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/upv-Latn/*.parquet""}]}, {""config_name"": ""qvc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/qvc-Latn/*.parquet""}]}, {""config_name"": ""njn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/njn-Latn/*.parquet""}]}, {""config_name"": ""tab-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tab-Cyrl/*.parquet""}]}, {""config_name"": ""faa-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/faa-Latn/*.parquet""}]}, {""config_name"": ""ape-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ape-Latn/*.parquet""}]}, {""config_name"": ""apt-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/apt-Latn/*.parquet""}]}, {""config_name"": ""kmh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kmh-Latn/*.parquet""}]}, {""config_name"": ""lmk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lmk-Latn/*.parquet""}]}, {""config_name"": ""kne-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kne-Latn/*.parquet""}]}, {""config_name"": ""tay-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tay-Latn/*.parquet""}]}, {""config_name"": ""lua-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lua-Latn/*.parquet""}]}, {""config_name"": ""und-Shaw"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/und-Shaw/*.parquet""}]}, {""config_name"": ""dtp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dtp-Latn/*.parquet""}]}, {""config_name"": ""mas-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mas-Latn/*.parquet""}]}, {""config_name"": ""tbg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tbg-Latn/*.parquet""}]}, {""config_name"": ""ckt-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ckt-Cyrl/*.parquet""}]}, {""config_name"": ""wal-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wal-Latn/*.parquet""}]}, {""config_name"": ""gyr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gyr-Latn/*.parquet""}]}, {""config_name"": ""bdd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bdd-Latn/*.parquet""}]}, {""config_name"": ""sid-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sid-Latn/*.parquet""}]}, {""config_name"": ""yka-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yka-Latn/*.parquet""}]}, {""config_name"": ""kan-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kan-Latn/*.parquet""}]}, {""config_name"": ""jiv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/jiv-Latn/*.parquet""}]}, {""config_name"": ""sil-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sil-Latn/*.parquet""}]}, {""config_name"": ""trv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/trv-Latn/*.parquet""}]}, {""config_name"": ""wls-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wls-Latn/*.parquet""}]}, {""config_name"": ""mlh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mlh-Latn/*.parquet""}]}, {""config_name"": ""suz-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/suz-Deva/*.parquet""}]}, {""config_name"": ""tca-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tca-Latn/*.parquet""}]}, {""config_name"": ""eve-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/eve-Cyrl/*.parquet""}]}, {""config_name"": ""dga-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dga-Latn/*.parquet""}]}, {""config_name"": ""kmg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kmg-Latn/*.parquet""}]}, {""config_name"": ""enl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/enl-Latn/*.parquet""}]}, {""config_name"": ""czt-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/czt-Latn/*.parquet""}]}, {""config_name"": ""kew-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kew-Latn/*.parquet""}]}, {""config_name"": ""mpx-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mpx-Latn/*.parquet""}]}, {""config_name"": ""pnt-Grek"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pnt-Grek/*.parquet""}]}, {""config_name"": ""med-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/med-Latn/*.parquet""}]}, {""config_name"": ""ory-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ory-Latn/*.parquet""}]}, {""config_name"": ""jae-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/jae-Latn/*.parquet""}]}, {""config_name"": ""pad-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pad-Latn/*.parquet""}]}, {""config_name"": ""ppo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ppo-Latn/*.parquet""}]}, {""config_name"": ""bus-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bus-Latn/*.parquet""}]}, {""config_name"": ""wuv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wuv-Latn/*.parquet""}]}, {""config_name"": ""bbb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bbb-Latn/*.parquet""}]}, {""config_name"": ""lex-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lex-Latn/*.parquet""}]}, {""config_name"": ""dah-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dah-Latn/*.parquet""}]}, {""config_name"": ""guj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/guj-Latn/*.parquet""}]}, {""config_name"": ""mog-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mog-Latn/*.parquet""}]}, {""config_name"": ""khz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/khz-Latn/*.parquet""}]}, {""config_name"": ""ncj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ncj-Latn/*.parquet""}]}, {""config_name"": ""uvl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/uvl-Latn/*.parquet""}]}, {""config_name"": ""adi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/adi-Latn/*.parquet""}]}, {""config_name"": ""msb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/msb-Latn/*.parquet""}]}, {""config_name"": ""pib-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pib-Latn/*.parquet""}]}, {""config_name"": ""abt-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/abt-Latn/*.parquet""}]}, {""config_name"": ""kdc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kdc-Latn/*.parquet""}]}, {""config_name"": ""sda-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sda-Latn/*.parquet""}]}, {""config_name"": ""nca-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nca-Latn/*.parquet""}]}, {""config_name"": ""csw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/csw-Latn/*.parquet""}]}, {""config_name"": ""tte-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tte-Latn/*.parquet""}]}, {""config_name"": ""mxt-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mxt-Latn/*.parquet""}]}, {""config_name"": ""sag-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sag-Latn/*.parquet""}]}, {""config_name"": ""top-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/top-Latn/*.parquet""}]}, {""config_name"": ""zpo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zpo-Latn/*.parquet""}]}, {""config_name"": ""clu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/clu-Latn/*.parquet""}]}, {""config_name"": ""bgs-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bgs-Latn/*.parquet""}]}, {""config_name"": ""guc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/guc-Latn/*.parquet""}]}, {""config_name"": ""nak-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nak-Latn/*.parquet""}]}, {""config_name"": ""yom-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yom-Latn/*.parquet""}]}, {""config_name"": ""ada-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ada-Latn/*.parquet""}]}, {""config_name"": ""cub-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cub-Latn/*.parquet""}]}, {""config_name"": ""mph-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mph-Latn/*.parquet""}]}, {""config_name"": ""und-Gran"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/und-Gran/*.parquet""}]}, {""config_name"": ""sdc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sdc-Latn/*.parquet""}]}, {""config_name"": ""tap-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tap-Latn/*.parquet""}]}, {""config_name"": ""maa-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/maa-Latn/*.parquet""}]}, {""config_name"": ""bjr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bjr-Latn/*.parquet""}]}, {""config_name"": ""sus-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sus-Arab/*.parquet""}]}, {""config_name"": ""hch-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hch-Latn/*.parquet""}]}, {""config_name"": ""ino-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ino-Latn/*.parquet""}]}, {""config_name"": ""adz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/adz-Latn/*.parquet""}]}, {""config_name"": ""taj-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/taj-Deva/*.parquet""}]}, {""config_name"": ""zai-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zai-Latn/*.parquet""}]}, {""config_name"": ""rjs-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rjs-Deva/*.parquet""}]}, {""config_name"": ""aso-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/aso-Latn/*.parquet""}]}, {""config_name"": ""dhm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dhm-Latn/*.parquet""}]}, {""config_name"": ""lki-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lki-Arab/*.parquet""}]}, {""config_name"": ""lun-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lun-Latn/*.parquet""}]}, {""config_name"": ""mvp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mvp-Latn/*.parquet""}]}, {""config_name"": ""dop-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dop-Latn/*.parquet""}]}, {""config_name"": ""snf-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/snf-Latn/*.parquet""}]}, {""config_name"": ""ojb-Cans"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ojb-Cans/*.parquet""}]}, {""config_name"": ""mwv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mwv-Latn/*.parquet""}]}, {""config_name"": ""ttc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ttc-Latn/*.parquet""}]}, {""config_name"": ""emp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/emp-Latn/*.parquet""}]}, {""config_name"": ""lfn-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lfn-Cyrl/*.parquet""}]}, {""config_name"": ""cab-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cab-Latn/*.parquet""}]}, {""config_name"": ""pwg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pwg-Latn/*.parquet""}]}, {""config_name"": ""kmr-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kmr-Cyrl/*.parquet""}]}, {""config_name"": ""mek-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mek-Latn/*.parquet""}]}, {""config_name"": ""mbh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mbh-Latn/*.parquet""}]}, {""config_name"": ""ttq-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ttq-Latn/*.parquet""}]}, {""config_name"": ""swc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/swc-Latn/*.parquet""}]}, {""config_name"": ""nhw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nhw-Latn/*.parquet""}]}, {""config_name"": ""tsg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tsg-Latn/*.parquet""}]}, {""config_name"": ""aim-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/aim-Latn/*.parquet""}]}, {""config_name"": ""bzi-Thai"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bzi-Thai/*.parquet""}]}, {""config_name"": ""ote-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ote-Latn/*.parquet""}]}, {""config_name"": ""djk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/djk-Latn/*.parquet""}]}, {""config_name"": ""ots-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ots-Latn/*.parquet""}]}, {""config_name"": ""tuf-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tuf-Latn/*.parquet""}]}, {""config_name"": ""crl-Cans"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/crl-Cans/*.parquet""}]}, {""config_name"": ""kek-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kek-Latn/*.parquet""}]}, {""config_name"": ""shp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/shp-Latn/*.parquet""}]}, {""config_name"": ""npy-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/npy-Latn/*.parquet""}]}, {""config_name"": ""kwn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kwn-Latn/*.parquet""}]}, {""config_name"": ""kzj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kzj-Latn/*.parquet""}]}, {""config_name"": ""mza-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mza-Latn/*.parquet""}]}, {""config_name"": ""ngu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ngu-Latn/*.parquet""}]}, {""config_name"": ""ssx-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ssx-Latn/*.parquet""}]}, {""config_name"": ""cta-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cta-Latn/*.parquet""}]}, {""config_name"": ""msk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/msk-Latn/*.parquet""}]}, {""config_name"": ""sab-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sab-Latn/*.parquet""}]}, {""config_name"": ""klt-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/klt-Latn/*.parquet""}]}, {""config_name"": ""tuk-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tuk-Cyrl/*.parquet""}]}, {""config_name"": ""mjc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mjc-Latn/*.parquet""}]}, {""config_name"": ""qxn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/qxn-Latn/*.parquet""}]}, {""config_name"": ""wbp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wbp-Latn/*.parquet""}]}, {""config_name"": ""kjb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kjb-Latn/*.parquet""}]}, {""config_name"": ""laj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/laj-Latn/*.parquet""}]}, {""config_name"": ""tll-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tll-Latn/*.parquet""}]}, {""config_name"": ""ded-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ded-Latn/*.parquet""}]}, {""config_name"": ""msc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/msc-Latn/*.parquet""}]}, {""config_name"": ""nif-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nif-Latn/*.parquet""}]}, {""config_name"": ""hvn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hvn-Latn/*.parquet""}]}, {""config_name"": ""bhl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bhl-Latn/*.parquet""}]}, {""config_name"": ""gvn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gvn-Latn/*.parquet""}]}, {""config_name"": ""knc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/knc-Latn/*.parquet""}]}, {""config_name"": ""kpx-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kpx-Latn/*.parquet""}]}, {""config_name"": ""nho-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nho-Latn/*.parquet""}]}, {""config_name"": ""rmq-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rmq-Latn/*.parquet""}]}, {""config_name"": ""crx-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/crx-Latn/*.parquet""}]}, {""config_name"": ""sml-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sml-Latn/*.parquet""}]}, {""config_name"": ""xtn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/xtn-Latn/*.parquet""}]}, {""config_name"": ""sxb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sxb-Latn/*.parquet""}]}, {""config_name"": ""adj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/adj-Latn/*.parquet""}]}, {""config_name"": ""sop-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sop-Latn/*.parquet""}]}, {""config_name"": ""kup-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kup-Latn/*.parquet""}]}, {""config_name"": ""tod-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tod-Latn/*.parquet""}]}, {""config_name"": ""apr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/apr-Latn/*.parquet""}]}, {""config_name"": ""akh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/akh-Latn/*.parquet""}]}, {""config_name"": ""zyp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zyp-Latn/*.parquet""}]}, {""config_name"": ""sxn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sxn-Latn/*.parquet""}]}, {""config_name"": ""lbe-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lbe-Cyrl/*.parquet""}]}, {""config_name"": ""acf-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/acf-Latn/*.parquet""}]}, {""config_name"": ""big-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/big-Latn/*.parquet""}]}, {""config_name"": ""kzf-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kzf-Latn/*.parquet""}]}, {""config_name"": ""cbr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cbr-Latn/*.parquet""}]}, {""config_name"": ""esk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/esk-Latn/*.parquet""}]}, {""config_name"": ""kpf-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kpf-Latn/*.parquet""}]}, {""config_name"": ""blz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/blz-Latn/*.parquet""}]}, {""config_name"": ""naf-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/naf-Latn/*.parquet""}]}, {""config_name"": ""mif-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mif-Latn/*.parquet""}]}, {""config_name"": ""alp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/alp-Latn/*.parquet""}]}, {""config_name"": ""ish-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ish-Latn/*.parquet""}]}, {""config_name"": ""ibg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ibg-Latn/*.parquet""}]}, {""config_name"": ""cax-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cax-Latn/*.parquet""}]}, {""config_name"": ""sim-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sim-Latn/*.parquet""}]}, {""config_name"": ""kam-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kam-Latn/*.parquet""}]}, {""config_name"": ""zdj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zdj-Latn/*.parquet""}]}, {""config_name"": ""fai-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fai-Latn/*.parquet""}]}, {""config_name"": ""kqf-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kqf-Latn/*.parquet""}]}, {""config_name"": ""awx-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/awx-Latn/*.parquet""}]}, {""config_name"": ""rtm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rtm-Latn/*.parquet""}]}, {""config_name"": ""taq-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/taq-Latn/*.parquet""}]}, {""config_name"": ""syl-Beng"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/syl-Beng/*.parquet""}]}, {""config_name"": ""yva-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yva-Latn/*.parquet""}]}, {""config_name"": ""tkr-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tkr-Cyrl/*.parquet""}]}, {""config_name"": ""maz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/maz-Latn/*.parquet""}]}, {""config_name"": ""nus-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nus-Latn/*.parquet""}]}, {""config_name"": ""nii-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nii-Latn/*.parquet""}]}, {""config_name"": ""bjn-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bjn-Arab/*.parquet""}]}, {""config_name"": ""swp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/swp-Latn/*.parquet""}]}, {""config_name"": ""atb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/atb-Latn/*.parquet""}]}, {""config_name"": ""esu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/esu-Latn/*.parquet""}]}, {""config_name"": ""gjn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gjn-Latn/*.parquet""}]}, {""config_name"": ""qvh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/qvh-Latn/*.parquet""}]}, {""config_name"": ""mip-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mip-Latn/*.parquet""}]}, {""config_name"": ""kpe-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kpe-Latn/*.parquet""}]}, {""config_name"": ""hus-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hus-Latn/*.parquet""}]}, {""config_name"": ""amu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/amu-Latn/*.parquet""}]}, {""config_name"": ""mfq-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mfq-Latn/*.parquet""}]}, {""config_name"": ""sgc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sgc-Latn/*.parquet""}]}, {""config_name"": ""abx-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/abx-Latn/*.parquet""}]}, {""config_name"": ""yli-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yli-Latn/*.parquet""}]}, {""config_name"": ""isd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/isd-Latn/*.parquet""}]}, {""config_name"": ""eri-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/eri-Latn/*.parquet""}]}, {""config_name"": ""bin-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bin-Latn/*.parquet""}]}, {""config_name"": ""gmv-Ethi"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gmv-Ethi/*.parquet""}]}, {""config_name"": ""snw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/snw-Latn/*.parquet""}]}, {""config_name"": ""acr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/acr-Latn/*.parquet""}]}, {""config_name"": ""dhg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dhg-Latn/*.parquet""}]}, {""config_name"": ""taw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/taw-Latn/*.parquet""}]}, {""config_name"": ""eko-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/eko-Latn/*.parquet""}]}, {""config_name"": ""qvn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/qvn-Latn/*.parquet""}]}, {""config_name"": ""mxx-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mxx-Latn/*.parquet""}]}, {""config_name"": ""mva-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mva-Latn/*.parquet""}]}, {""config_name"": ""mge-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mge-Latn/*.parquet""}]}, {""config_name"": ""kyg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kyg-Latn/*.parquet""}]}, {""config_name"": ""arq-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/arq-Arab/*.parquet""}]}, {""config_name"": ""kms-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kms-Latn/*.parquet""}]}, {""config_name"": ""gum-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gum-Latn/*.parquet""}]}, {""config_name"": ""wnc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wnc-Latn/*.parquet""}]}, {""config_name"": ""qvw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/qvw-Latn/*.parquet""}]}, {""config_name"": ""kbo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kbo-Latn/*.parquet""}]}, {""config_name"": ""kmk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kmk-Latn/*.parquet""}]}, {""config_name"": ""tar-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tar-Latn/*.parquet""}]}, {""config_name"": ""zpm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zpm-Latn/*.parquet""}]}, {""config_name"": ""kbq-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kbq-Latn/*.parquet""}]}, {""config_name"": ""ptu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ptu-Latn/*.parquet""}]}, {""config_name"": ""bno-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bno-Latn/*.parquet""}]}, {""config_name"": ""kmb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kmb-Latn/*.parquet""}]}, {""config_name"": ""not-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/not-Latn/*.parquet""}]}, {""config_name"": ""mfy-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mfy-Latn/*.parquet""}]}, {""config_name"": ""ntu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ntu-Latn/*.parquet""}]}, {""config_name"": ""cbt-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cbt-Latn/*.parquet""}]}, {""config_name"": ""men-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/men-Latn/*.parquet""}]}, {""config_name"": ""xmm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/xmm-Latn/*.parquet""}]}, {""config_name"": ""tby-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tby-Latn/*.parquet""}]}, {""config_name"": ""mpm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mpm-Latn/*.parquet""}]}, {""config_name"": ""bgr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bgr-Latn/*.parquet""}]}, {""config_name"": ""cho-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cho-Latn/*.parquet""}]}, {""config_name"": ""dru-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dru-Latn/*.parquet""}]}, {""config_name"": ""btd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/btd-Latn/*.parquet""}]}, {""config_name"": ""sgw-Ethi"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sgw-Ethi/*.parquet""}]}, {""config_name"": ""nuj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nuj-Latn/*.parquet""}]}, {""config_name"": ""dje-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dje-Latn/*.parquet""}]}, {""config_name"": ""tlf-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tlf-Latn/*.parquet""}]}, {""config_name"": ""yuw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yuw-Latn/*.parquet""}]}, {""config_name"": ""kas-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kas-Latn/*.parquet""}]}, {""config_name"": ""lzh-Hani"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lzh-Hani/*.parquet""}]}, {""config_name"": ""miq-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/miq-Latn/*.parquet""}]}, {""config_name"": ""lrc-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lrc-Arab/*.parquet""}]}, {""config_name"": ""mhx-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mhx-Latn/*.parquet""}]}, {""config_name"": ""xog-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/xog-Latn/*.parquet""}]}, {""config_name"": ""myw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/myw-Latn/*.parquet""}]}, {""config_name"": ""ktu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ktu-Latn/*.parquet""}]}, {""config_name"": ""shu-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/shu-Arab/*.parquet""}]}, {""config_name"": ""syl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/syl-Latn/*.parquet""}]}, {""config_name"": ""sxw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sxw-Latn/*.parquet""}]}, {""config_name"": ""shk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/shk-Latn/*.parquet""}]}, {""config_name"": ""dyo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dyo-Latn/*.parquet""}]}, {""config_name"": ""tiv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tiv-Latn/*.parquet""}]}, {""config_name"": ""mbt-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mbt-Latn/*.parquet""}]}, {""config_name"": ""zam-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zam-Latn/*.parquet""}]}, {""config_name"": ""bzj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bzj-Latn/*.parquet""}]}, {""config_name"": ""lia-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lia-Latn/*.parquet""}]}, {""config_name"": ""kqn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kqn-Latn/*.parquet""}]}, {""config_name"": ""csy-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/csy-Latn/*.parquet""}]}, {""config_name"": ""tif-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tif-Latn/*.parquet""}]}, {""config_name"": ""twu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/twu-Latn/*.parquet""}]}, {""config_name"": ""ojb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ojb-Latn/*.parquet""}]}, {""config_name"": ""pmx-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pmx-Latn/*.parquet""}]}, {""config_name"": ""mqy-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mqy-Latn/*.parquet""}]}, {""config_name"": ""srr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/srr-Latn/*.parquet""}]}, {""config_name"": ""gbi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gbi-Latn/*.parquet""}]}, {""config_name"": ""rkb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rkb-Latn/*.parquet""}]}, {""config_name"": ""xsr-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/xsr-Deva/*.parquet""}]}, {""config_name"": ""ktm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ktm-Latn/*.parquet""}]}, {""config_name"": ""mej-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mej-Latn/*.parquet""}]}, {""config_name"": ""txu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/txu-Latn/*.parquet""}]}, {""config_name"": ""tcs-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tcs-Latn/*.parquet""}]}, {""config_name"": ""blw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/blw-Latn/*.parquet""}]}, {""config_name"": ""pmf-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pmf-Latn/*.parquet""}]}, {""config_name"": ""aui-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/aui-Latn/*.parquet""}]}, {""config_name"": ""kix-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kix-Latn/*.parquet""}]}, {""config_name"": ""sps-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sps-Latn/*.parquet""}]}, {""config_name"": ""kru-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kru-Deva/*.parquet""}]}, {""config_name"": ""kqw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kqw-Latn/*.parquet""}]}, {""config_name"": ""nbc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nbc-Latn/*.parquet""}]}, {""config_name"": ""lsi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lsi-Latn/*.parquet""}]}, {""config_name"": ""fud-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fud-Latn/*.parquet""}]}, {""config_name"": ""ewo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ewo-Latn/*.parquet""}]}, {""config_name"": ""ain-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ain-Latn/*.parquet""}]}, {""config_name"": ""gai-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gai-Latn/*.parquet""}]}, {""config_name"": ""bdq-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bdq-Latn/*.parquet""}]}, {""config_name"": ""snd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/snd-Latn/*.parquet""}]}, {""config_name"": ""bsp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bsp-Latn/*.parquet""}]}, {""config_name"": ""snd-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/snd-Deva/*.parquet""}]}, {""config_name"": ""sas-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sas-Latn/*.parquet""}]}, {""config_name"": ""boj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/boj-Latn/*.parquet""}]}, {""config_name"": ""xbi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/xbi-Latn/*.parquet""}]}, {""config_name"": ""lud-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lud-Latn/*.parquet""}]}, {""config_name"": ""auy-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/auy-Latn/*.parquet""}]}, {""config_name"": ""nzm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nzm-Latn/*.parquet""}]}, {""config_name"": ""kbc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kbc-Latn/*.parquet""}]}, {""config_name"": ""gnb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gnb-Latn/*.parquet""}]}, {""config_name"": ""tzh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tzh-Latn/*.parquet""}]}, {""config_name"": ""lew-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lew-Latn/*.parquet""}]}, {""config_name"": ""icr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/icr-Latn/*.parquet""}]}, {""config_name"": ""yby-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yby-Latn/*.parquet""}]}, {""config_name"": ""mtg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mtg-Latn/*.parquet""}]}, {""config_name"": ""gwr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gwr-Latn/*.parquet""}]}, {""config_name"": ""agt-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/agt-Latn/*.parquet""}]}, {""config_name"": ""hla-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hla-Latn/*.parquet""}]}, {""config_name"": ""kwy-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kwy-Latn/*.parquet""}]}, {""config_name"": ""bkl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bkl-Latn/*.parquet""}]}, {""config_name"": ""quw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/quw-Latn/*.parquet""}]}, {""config_name"": ""cpb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cpb-Latn/*.parquet""}]}, {""config_name"": ""too-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/too-Latn/*.parquet""}]}, {""config_name"": ""tig-Ethi"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tig-Ethi/*.parquet""}]}, {""config_name"": ""kgr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kgr-Latn/*.parquet""}]}, {""config_name"": ""agn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/agn-Latn/*.parquet""}]}, {""config_name"": ""cwt-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cwt-Latn/*.parquet""}]}, {""config_name"": ""obo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/obo-Latn/*.parquet""}]}, {""config_name"": ""tos-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tos-Latn/*.parquet""}]}, {""config_name"": ""yrl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yrl-Latn/*.parquet""}]}, {""config_name"": ""rgu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rgu-Latn/*.parquet""}]}, {""config_name"": ""ctu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ctu-Latn/*.parquet""}]}, {""config_name"": ""tih-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tih-Latn/*.parquet""}]}, {""config_name"": ""bum-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bum-Latn/*.parquet""}]}, {""config_name"": ""pot-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pot-Latn/*.parquet""}]}, {""config_name"": ""bdh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bdh-Latn/*.parquet""}]}, {""config_name"": ""mbf-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mbf-Latn/*.parquet""}]}, {""config_name"": ""wat-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wat-Latn/*.parquet""}]}, {""config_name"": ""tdx-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tdx-Latn/*.parquet""}]}, {""config_name"": ""poh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/poh-Latn/*.parquet""}]}, {""config_name"": ""ruf-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ruf-Latn/*.parquet""}]}, {""config_name"": ""lhi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lhi-Latn/*.parquet""}]}, {""config_name"": ""qul-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/qul-Latn/*.parquet""}]}, {""config_name"": ""muh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/muh-Latn/*.parquet""}]}, {""config_name"": ""sll-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sll-Latn/*.parquet""}]}, {""config_name"": ""ntp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ntp-Latn/*.parquet""}]}, {""config_name"": ""nsu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nsu-Latn/*.parquet""}]}, {""config_name"": ""cya-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cya-Latn/*.parquet""}]}, {""config_name"": ""kas-Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kas-Deva/*.parquet""}]}, {""config_name"": ""nbe-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nbe-Latn/*.parquet""}]}, {""config_name"": ""mwp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mwp-Latn/*.parquet""}]}, {""config_name"": ""dhv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dhv-Latn/*.parquet""}]}, {""config_name"": ""gux-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gux-Latn/*.parquet""}]}, {""config_name"": ""kck-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kck-Latn/*.parquet""}]}, {""config_name"": ""aey-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/aey-Latn/*.parquet""}]}, {""config_name"": ""mcd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mcd-Latn/*.parquet""}]}, {""config_name"": ""lnd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lnd-Latn/*.parquet""}]}, {""config_name"": ""fat-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/fat-Latn/*.parquet""}]}, {""config_name"": ""spp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/spp-Latn/*.parquet""}]}, {""config_name"": ""tlb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tlb-Latn/*.parquet""}]}, {""config_name"": ""bim-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bim-Latn/*.parquet""}]}, {""config_name"": ""sat-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sat-Latn/*.parquet""}]}, {""config_name"": ""xmv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/xmv-Latn/*.parquet""}]}, {""config_name"": ""way-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/way-Latn/*.parquet""}]}, {""config_name"": ""ljp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ljp-Latn/*.parquet""}]}, {""config_name"": ""moc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/moc-Latn/*.parquet""}]}, {""config_name"": ""gym-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gym-Latn/*.parquet""}]}, {""config_name"": ""zos-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zos-Latn/*.parquet""}]}, {""config_name"": ""hto-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hto-Latn/*.parquet""}]}, {""config_name"": ""kby-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kby-Latn/*.parquet""}]}, {""config_name"": ""bef-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bef-Latn/*.parquet""}]}, {""config_name"": ""ikw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ikw-Latn/*.parquet""}]}, {""config_name"": ""ria-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ria-Latn/*.parquet""}]}, {""config_name"": ""bzd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bzd-Latn/*.parquet""}]}, {""config_name"": ""lid-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lid-Latn/*.parquet""}]}, {""config_name"": ""yaa-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yaa-Latn/*.parquet""}]}, {""config_name"": ""kdi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kdi-Latn/*.parquet""}]}, {""config_name"": ""myu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/myu-Latn/*.parquet""}]}, {""config_name"": ""tsz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tsz-Latn/*.parquet""}]}, {""config_name"": ""skg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/skg-Latn/*.parquet""}]}, {""config_name"": ""nmz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nmz-Latn/*.parquet""}]}, {""config_name"": ""ptp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ptp-Latn/*.parquet""}]}, {""config_name"": ""njz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/njz-Latn/*.parquet""}]}, {""config_name"": ""poe-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/poe-Latn/*.parquet""}]}, {""config_name"": ""njm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/njm-Latn/*.parquet""}]}, {""config_name"": ""ivb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ivb-Latn/*.parquet""}]}, {""config_name"": ""mwc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mwc-Latn/*.parquet""}]}, {""config_name"": ""dis-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dis-Latn/*.parquet""}]}, {""config_name"": ""myb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/myb-Latn/*.parquet""}]}, {""config_name"": ""waj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/waj-Latn/*.parquet""}]}, {""config_name"": ""bps-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bps-Latn/*.parquet""}]}, {""config_name"": ""dua-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dua-Latn/*.parquet""}]}, {""config_name"": ""bas-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bas-Latn/*.parquet""}]}, {""config_name"": ""nyu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nyu-Latn/*.parquet""}]}, {""config_name"": ""nmf-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nmf-Latn/*.parquet""}]}, {""config_name"": ""tfr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tfr-Latn/*.parquet""}]}, {""config_name"": ""bqc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bqc-Latn/*.parquet""}]}, {""config_name"": ""ajz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ajz-Latn/*.parquet""}]}, {""config_name"": ""got-Goth"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/got-Goth/*.parquet""}]}, {""config_name"": ""tgo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tgo-Latn/*.parquet""}]}, {""config_name"": ""wbm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wbm-Latn/*.parquet""}]}, {""config_name"": ""kyq-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kyq-Latn/*.parquet""}]}, {""config_name"": ""aby-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/aby-Latn/*.parquet""}]}, {""config_name"": ""rej-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rej-Latn/*.parquet""}]}, {""config_name"": ""amm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/amm-Latn/*.parquet""}]}, {""config_name"": ""nnw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nnw-Latn/*.parquet""}]}, {""config_name"": ""crk-Cans"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/crk-Cans/*.parquet""}]}, {""config_name"": ""cmr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cmr-Latn/*.parquet""}]}, {""config_name"": ""hub-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hub-Latn/*.parquet""}]}, {""config_name"": ""nij-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nij-Latn/*.parquet""}]}, {""config_name"": ""srm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/srm-Latn/*.parquet""}]}, {""config_name"": ""tnc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tnc-Latn/*.parquet""}]}, {""config_name"": ""plu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/plu-Latn/*.parquet""}]}, {""config_name"": ""atq-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/atq-Latn/*.parquet""}]}, {""config_name"": ""xla-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/xla-Latn/*.parquet""}]}, {""config_name"": ""mjw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mjw-Latn/*.parquet""}]}, {""config_name"": ""qug-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/qug-Latn/*.parquet""}]}, {""config_name"": ""vid-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/vid-Latn/*.parquet""}]}, {""config_name"": ""did-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/did-Latn/*.parquet""}]}, {""config_name"": ""mxb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mxb-Latn/*.parquet""}]}, {""config_name"": ""mwn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mwn-Latn/*.parquet""}]}, {""config_name"": ""lis-Lisu"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lis-Lisu/*.parquet""}]}, {""config_name"": ""cha-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cha-Latn/*.parquet""}]}, {""config_name"": ""idu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/idu-Latn/*.parquet""}]}, {""config_name"": ""mqj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mqj-Latn/*.parquet""}]}, {""config_name"": ""trc-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/trc-Latn/*.parquet""}]}, {""config_name"": ""sgb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sgb-Latn/*.parquet""}]}, {""config_name"": ""xtd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/xtd-Latn/*.parquet""}]}, {""config_name"": ""zgh-Tfng"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zgh-Tfng/*.parquet""}]}, {""config_name"": ""rif-Tfng"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rif-Tfng/*.parquet""}]}, {""config_name"": ""rif-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rif-Latn/*.parquet""}]}, {""config_name"": ""mnb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mnb-Latn/*.parquet""}]}, {""config_name"": ""wsg-Telu"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wsg-Telu/*.parquet""}]}, {""config_name"": ""ncx-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ncx-Latn/*.parquet""}]}, {""config_name"": ""ccp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ccp-Latn/*.parquet""}]}, {""config_name"": ""nuy-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nuy-Latn/*.parquet""}]}, {""config_name"": ""usa-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/usa-Latn/*.parquet""}]}, {""config_name"": ""wlv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wlv-Latn/*.parquet""}]}, {""config_name"": ""qvs-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/qvs-Latn/*.parquet""}]}, {""config_name"": ""mhi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mhi-Latn/*.parquet""}]}, {""config_name"": ""atd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/atd-Latn/*.parquet""}]}, {""config_name"": ""sgh-Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sgh-Cyrl/*.parquet""}]}, {""config_name"": ""tbw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tbw-Latn/*.parquet""}]}, {""config_name"": ""plw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/plw-Latn/*.parquet""}]}, {""config_name"": ""tnr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tnr-Latn/*.parquet""}]}, {""config_name"": ""bwd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bwd-Latn/*.parquet""}]}, {""config_name"": ""nhx-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nhx-Latn/*.parquet""}]}, {""config_name"": ""aer-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/aer-Latn/*.parquet""}]}, {""config_name"": ""gub-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gub-Latn/*.parquet""}]}, {""config_name"": ""quf-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/quf-Latn/*.parquet""}]}, {""config_name"": ""dyi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dyi-Latn/*.parquet""}]}, {""config_name"": ""tob-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tob-Latn/*.parquet""}]}, {""config_name"": ""kwf-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kwf-Latn/*.parquet""}]}, {""config_name"": ""xtm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/xtm-Latn/*.parquet""}]}, {""config_name"": ""dww-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dww-Latn/*.parquet""}]}, {""config_name"": ""mwf-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mwf-Latn/*.parquet""}]}, {""config_name"": ""kak-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kak-Latn/*.parquet""}]}, {""config_name"": ""omb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/omb-Latn/*.parquet""}]}, {""config_name"": ""mbs-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mbs-Latn/*.parquet""}]}, {""config_name"": ""mwm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mwm-Latn/*.parquet""}]}, {""config_name"": ""bpr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bpr-Latn/*.parquet""}]}, {""config_name"": ""gnw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gnw-Latn/*.parquet""}]}, {""config_name"": ""cjk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cjk-Latn/*.parquet""}]}, {""config_name"": ""nnp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nnp-Latn/*.parquet""}]}, {""config_name"": ""agw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/agw-Latn/*.parquet""}]}, {""config_name"": ""rml-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rml-Latn/*.parquet""}]}, {""config_name"": ""kkl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kkl-Latn/*.parquet""}]}, {""config_name"": ""ksr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ksr-Latn/*.parquet""}]}, {""config_name"": ""kpj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kpj-Latn/*.parquet""}]}, {""config_name"": ""zpu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zpu-Latn/*.parquet""}]}, {""config_name"": ""itv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/itv-Latn/*.parquet""}]}, {""config_name"": ""cbs-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cbs-Latn/*.parquet""}]}, {""config_name"": ""con-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/con-Latn/*.parquet""}]}, {""config_name"": ""eza-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/eza-Latn/*.parquet""}]}, {""config_name"": ""vap-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/vap-Latn/*.parquet""}]}, {""config_name"": ""bom-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bom-Latn/*.parquet""}]}, {""config_name"": ""biu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/biu-Latn/*.parquet""}]}, {""config_name"": ""iqw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/iqw-Latn/*.parquet""}]}, {""config_name"": ""hra-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hra-Latn/*.parquet""}]}, {""config_name"": ""nst-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nst-Latn/*.parquet""}]}, {""config_name"": ""bgz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bgz-Latn/*.parquet""}]}, {""config_name"": ""bhw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bhw-Latn/*.parquet""}]}, {""config_name"": ""tui-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tui-Latn/*.parquet""}]}, {""config_name"": ""nyk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nyk-Latn/*.parquet""}]}, {""config_name"": ""cbi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cbi-Latn/*.parquet""}]}, {""config_name"": ""mck-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mck-Latn/*.parquet""}]}, {""config_name"": ""cwe-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cwe-Latn/*.parquet""}]}, {""config_name"": ""mzh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mzh-Latn/*.parquet""}]}, {""config_name"": ""yon-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/yon-Latn/*.parquet""}]}, {""config_name"": ""agu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/agu-Latn/*.parquet""}]}, {""config_name"": ""qvi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/qvi-Latn/*.parquet""}]}, {""config_name"": ""cnw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cnw-Latn/*.parquet""}]}, {""config_name"": ""mau-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mau-Latn/*.parquet""}]}, {""config_name"": ""gur-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/gur-Latn/*.parquet""}]}, {""config_name"": ""sbd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/sbd-Latn/*.parquet""}]}, {""config_name"": ""ikk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ikk-Latn/*.parquet""}]}, {""config_name"": ""tbz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tbz-Latn/*.parquet""}]}, {""config_name"": ""rnl-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rnl-Latn/*.parquet""}]}, {""config_name"": ""bqj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/bqj-Latn/*.parquet""}]}, {""config_name"": ""inb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/inb-Latn/*.parquet""}]}, {""config_name"": ""maw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/maw-Latn/*.parquet""}]}, {""config_name"": ""guj-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/guj-Arab/*.parquet""}]}, {""config_name"": ""hag-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/hag-Latn/*.parquet""}]}, {""config_name"": ""acn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/acn-Latn/*.parquet""}]}, {""config_name"": ""nph-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nph-Latn/*.parquet""}]}, {""config_name"": ""lwg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lwg-Latn/*.parquet""}]}, {""config_name"": ""kog-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kog-Latn/*.parquet""}]}, {""config_name"": ""djr-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/djr-Latn/*.parquet""}]}, {""config_name"": ""urh-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/urh-Latn/*.parquet""}]}, {""config_name"": ""cag-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/cag-Latn/*.parquet""}]}, {""config_name"": ""kcg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kcg-Latn/*.parquet""}]}, {""config_name"": ""dts-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/dts-Latn/*.parquet""}]}, {""config_name"": ""nsa-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nsa-Latn/*.parquet""}]}, {""config_name"": ""xon-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/xon-Latn/*.parquet""}]}, {""config_name"": ""lif-Limb"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lif-Limb/*.parquet""}]}, {""config_name"": ""tuk-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/tuk-Arab/*.parquet""}]}, {""config_name"": ""kmm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kmm-Latn/*.parquet""}]}, {""config_name"": ""plg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/plg-Latn/*.parquet""}]}, {""config_name"": ""kmy-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kmy-Latn/*.parquet""}]}, {""config_name"": ""rmo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rmo-Latn/*.parquet""}]}, {""config_name"": ""lcm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lcm-Latn/*.parquet""}]}, {""config_name"": ""nnb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/nnb-Latn/*.parquet""}]}, {""config_name"": ""kgk-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kgk-Latn/*.parquet""}]}, {""config_name"": ""vmw-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/vmw-Latn/*.parquet""}]}, {""config_name"": ""kjs-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kjs-Latn/*.parquet""}]}, {""config_name"": ""met-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/met-Latn/*.parquet""}]}, {""config_name"": ""trn-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/trn-Latn/*.parquet""}]}, {""config_name"": ""ivv-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ivv-Latn/*.parquet""}]}, {""config_name"": ""ktz-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ktz-Latn/*.parquet""}]}, {""config_name"": ""kpo-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kpo-Latn/*.parquet""}]}, {""config_name"": ""pbb-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pbb-Latn/*.parquet""}]}, {""config_name"": ""wed-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/wed-Latn/*.parquet""}]}, {""config_name"": ""zsm-Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/zsm-Arab/*.parquet""}]}, {""config_name"": ""alq-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/alq-Latn/*.parquet""}]}, {""config_name"": ""ssg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ssg-Latn/*.parquet""}]}, {""config_name"": ""mie-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mie-Latn/*.parquet""}]}, {""config_name"": ""ddg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ddg-Latn/*.parquet""}]}, {""config_name"": ""ses-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/ses-Latn/*.parquet""}]}, {""config_name"": ""toj-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/toj-Latn/*.parquet""}]}, {""config_name"": ""pls-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pls-Latn/*.parquet""}]}, {""config_name"": ""kyu-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kyu-Latn/*.parquet""}]}, {""config_name"": ""otd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/otd-Latn/*.parquet""}]}, {""config_name"": ""mfi-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/mfi-Latn/*.parquet""}]}, {""config_name"": ""kmd-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kmd-Latn/*.parquet""}]}, {""config_name"": ""rap-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rap-Latn/*.parquet""}]}, {""config_name"": ""kde-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/kde-Latn/*.parquet""}]}, {""config_name"": ""any-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/any-Latn/*.parquet""}]}, {""config_name"": ""pps-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/pps-Latn/*.parquet""}]}, {""config_name"": ""rhg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/rhg-Latn/*.parquet""}]}, {""config_name"": ""lgg-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/lgg-Latn/*.parquet""}]}, {""config_name"": ""xsm-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/xsm-Latn/*.parquet""}]}, {""config_name"": ""usp-Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""v1.0/usp-Latn/*.parquet""}]}], ""multilinguality"": [""multilingual""], ""pinned"": true, ""tags"": [""multilingual""], ""language"": [""aau"", ""aaz"", ""ab"", ""abk"", ""abq"", ""abs"", ""abt"", ""abx"", ""aby"", ""ace"", ""acf"", ""ach"", ""acm"", ""acn"", ""acr"", ""acu"", ""ada"", ""adi"", ""adj"", ""ady"", ""adz"", ""aeb"", ""aer"", ""aey"", ""af"", ""afr"", ""agd"", ""agm"", ""agn"", ""agr"", ""agt"", ""agu"", ""agw"", ""aii"", ""aim"", ""ain"", ""ajp"", ""ajz"", ""aka"", ""akb"", ""akh"", ""aln"", ""alp"", ""alq"", ""als"", ""alt"", ""aly"", ""am"", ""amf"", ""amh"", ""ami"", ""amm"", ""amu"", ""an"", ""ang"", ""ann"", ""anp"", ""any"", ""aoi"", ""aoj"", ""aom"", ""aoz"", ""apb"", ""apc"", ""ape"", ""apr"", ""apt"", ""apz"", ""ara"", ""arb"", ""arg"", ""arl"", ""arn"", ""arq"", ""ars"", ""ary"", ""arz"", ""as"", ""asm"", ""aso"", ""ast"", ""ata"", ""atb"", ""atd"", ""atj"", ""atq"", ""att"", ""aui"", ""auy"", ""av"", ""ava"", ""avk"", ""avt"", ""avu"", ""awa"", ""awx"", ""aym"", ""ayr"", ""azb"", ""aze"", ""azg"", ""azj"", ""ba"", ""bak"", ""bal"", ""bam"", ""ban"", ""bar"", ""bas"", ""bba"", ""bbb"", ""bbc"", ""bbr"", ""bcc"", ""bch"", ""bci"", ""bcl"", ""bdd"", ""bdh"", ""bdq"", ""be"", ""bef"", ""bel"", ""bem"", ""ben"", ""bew"", ""bg"", ""bgr"", ""bgs"", ""bgz"", ""bhg"", ""bhl"", ""bho"", ""bhw"", ""bi"", ""big"", ""bik"", ""bim"", ""bin"", ""bis"", ""biu"", ""bjn"", ""bjp"", ""bjr"", ""bkd"", ""bkl"", ""blk"", ""blw"", ""blz"", ""bm"", ""bmh"", ""bmu"", ""bn"", ""bnc"", ""bno"", ""bnp"", ""bo"", ""boa"", ""bod"", ""boj"", ""bom"", ""bon"", ""bos"", ""bpr"", ""bps"", ""bpy"", ""bqc"", ""bqj"", ""br"", ""bre"", ""brh"", ""bru"", ""brx"", ""bs"", ""bsp"", ""btd"", ""bts"", ""btx"", ""bua"", ""bug"", ""buk"", ""bul"", ""bum"", ""bus"", ""bvr"", ""bwd"", ""bxh"", ""bxr"", ""byr"", ""bzd"", ""bzi"", ""bzj"", ""ca"", ""caa"", ""cab"", ""cac"", ""cag"", ""cak"", ""cao"", ""car"", ""cat"", ""cax"", ""cbi"", ""cbk"", ""cbr"", ""cbs"", ""cbt"", ""cbu"", ""ccp"", ""ce"", ""ceb"", ""ces"", ""cfm"", ""cgc"", ""ch"", ""cha"", ""chd"", ""che"", ""chk"", ""chm"", ""cho"", ""chu"", ""chv"", ""chw"", ""cjk"", ""cjv"", ""ckb"", ""ckm"", ""ckt"", ""clu"", ""cmn"", ""cmo"", ""cmr"", ""cnh"", ""cni"", ""cnk"", ""cnr"", ""cnw"", ""co"", ""con"", ""cop"", ""cor"", ""cos"", ""cot"", ""cpb"", ""cpc"", ""cpy"", ""cre"", ""crh"", ""crk"", ""crl"", ""crn"", ""crs"", ""crx"", ""cs"", ""csb"", ""csw"", ""csy"", ""cta"", ""ctd"", ""ctu"", ""cu"", ""cub"", ""cuk"", ""cut"", ""cv"", ""cwe"", ""cwt"", ""cy"", ""cya"", ""cym"", ""czt"", ""da"", ""dad"", ""dag"", ""dah"", ""dak"", ""dan"", ""dao"", ""dar"", ""ddg"", ""de"", ""ded"", ""deu"", ""dga"", ""dgc"", ""dgz"", ""dhg"", ""dhm"", ""dhv"", ""did"", ""dik"", ""din"", ""diq"", ""dis"", ""div"", ""dje"", ""djk"", ""djr"", ""dng"", ""dob"", ""doi"", ""dop"", ""dru"", ""dsb"", ""dtp"", ""dts"", ""dua"", ""dv"", ""dwr"", ""dww"", ""dyi"", ""dyo"", ""dyu"", ""dz"", ""dzo"", ""ee"", ""efi"", ""ekk"", ""eko"", ""el"", ""ell"", ""emi"", ""eml"", ""emp"", ""en"", ""eng"", ""enl"", ""enm"", ""enq"", ""eo"", ""epo"", ""eri"", ""es"", ""esk"", ""est"", ""esu"", ""etr"", ""eu"", ""eus"", ""eve"", ""ewe"", ""ewo"", ""ext"", ""eza"", ""fa"", ""faa"", ""fai"", ""fao"", ""fas"", ""fat"", ""ffm"", ""fi"", ""fij"", ""fil"", ""fin"", ""fit"", ""fj"", ""fkv"", ""fo"", ""fon"", ""for"", ""fr"", ""fra"", ""fro"", ""frp"", ""frr"", ""fry"", ""fub"", ""fud"", ""fue"", ""fuf"", ""fuh"", ""ful"", ""fur"", ""fuv"", ""fy"", ""ga"", ""gaa"", ""gag"", ""gah"", ""gai"", ""gam"", ""gaw"", ""gaz"", ""gbi"", ""gcf"", ""gcr"", ""gd"", ""gdg"", ""gdn"", ""geb"", ""gfk"", ""ghs"", ""gil"", ""gjn"", ""gl"", ""gla"", ""gle"", ""glg"", ""glk"", ""glv"", ""gmh"", ""gmv"", ""gnb"", ""gng"", ""gnn"", ""gnw"", ""goh"", ""gom"", ""gon"", ""gor"", ""gos"", ""got"", ""grc"", ""grn"", ""gsw"", ""gu"", ""gub"", ""guc"", ""gug"", ""guj"", ""gul"", ""gum"", ""gur"", ""guw"", ""gux"", ""guz"", ""gv"", ""gvn"", ""gwi"", ""gwr"", ""gym"", ""gyr"", ""ha"", ""hac"", ""hag"", ""hak"", ""hat"", ""hau"", ""haw"", ""hbo"", ""hbs"", ""hch"", ""he"", ""heb"", ""heg"", ""her"", ""hi"", ""hif"", ""hil"", ""hin"", ""hla"", ""hmn"", ""hmo"", ""hmr"", ""hne"", ""hnj"", ""hns"", ""ho"", ""hot"", ""hr"", ""hra"", ""hrv"", ""hsb"", ""ht"", ""hto"", ""hu"", ""hub"", ""hui"", ""hun"", ""hus"", ""huu"", ""hvn"", ""hwc"", ""hy"", ""hye"", ""hyw"", ""hz"", ""ia"", ""ian"", ""iba"", ""ibg"", ""ibo"", ""icr"", ""id"", ""ido"", ""idu"", ""ie"", ""ify"", ""ig"", ""ike"", ""ikk"", ""ikt"", ""iku"", ""ikw"", ""ile"", ""ilo"", ""ina"", ""inb"", ""ind"", ""inh"", ""ino"", ""io"", ""iou"", ""ipi"", ""ipk"", ""iqw"", ""is"", ""isd"", ""ish"", ""isl"", ""iso"", ""it"", ""ita"", ""itv"", ""ium"", ""ivb"", ""ivv"", ""iws"", ""ixl"", ""ja"", ""jac"", ""jae"", ""jam"", ""jav"", ""jbo"", ""jiv"", ""jpn"", ""jra"", ""jrb"", ""jv"", ""jvn"", ""ka"", ""kaa"", ""kab"", ""kac"", ""kak"", ""kal"", ""kam"", ""kan"", ""kaq"", ""kas"", ""kat"", ""kau"", ""kaz"", ""kbc"", ""kbd"", ""kbh"", ""kbm"", ""kbo"", ""kbp"", ""kbq"", ""kby"", ""kca"", ""kcg"", ""kck"", ""kdc"", ""kde"", ""kdi"", ""kdl"", ""kea"", ""kek"", ""kew"", ""kgk"", ""kgr"", ""kha"", ""khk"", ""khm"", ""khz"", ""ki"", ""kij"", ""kik"", ""kin"", ""kir"", ""kiu"", ""kix"", ""kj"", ""kjb"", ""kjh"", ""kjs"", ""kk"", ""kkc"", ""kkl"", ""kl"", ""kln"", ""klt"", ""klv"", ""km"", ""kmb"", ""kmd"", ""kmg"", ""kmh"", ""kmk"", ""kmm"", ""kmr"", ""kms"", ""kmu"", ""kmy"", ""kn"", ""knc"", ""kne"", ""kng"", ""knv"", ""ko"", ""kog"", ""koi"", ""kok"", ""kom"", ""kon"", ""kor"", ""kos"", ""kpe"", ""kpf"", ""kpg"", ""kpj"", ""kpo"", ""kpr"", ""kpv"", ""kpw"", ""kpx"", ""kqc"", ""kqf"", ""kqn"", ""kqw"", ""krc"", ""kri"", ""krl"", ""kru"", ""ks"", ""ksd"", ""ksh"", ""ksr"", ""ksw"", ""ktm"", ""kto"", ""ktu"", ""ktz"", ""kua"", ""kum"", ""kup"", ""kur"", ""kvg"", ""kw"", ""kwf"", ""kwj"", ""kwn"", ""kwy"", ""ky"", ""kyc"", ""kyg"", ""kyq"", ""kyu"", ""kyz"", ""kze"", ""kzf"", ""kzj"", ""la"", ""lad"", ""lah"", ""laj"", ""lam"", ""lao"", ""lat"", ""lav"", ""lb"", ""lbb"", ""lbe"", ""lbj"", ""lbk"", ""lcm"", ""leu"", ""lew"", ""lex"", ""lez"", ""lfn"", ""lg"", ""lgg"", ""lgl"", ""lhi"", ""li"", ""lia"", ""lid"", ""lif"", ""lij"", ""lim"", ""lin"", ""lis"", ""lit"", ""liv"", ""ljp"", ""lki"", ""lld"", ""llg"", ""lmk"", ""lmo"", ""ln"", ""lnd"", ""lo"", ""loz"", ""lrc"", ""lsi"", ""lt"", ""ltg"", ""ltz"", ""lu"", ""lua"", ""lub"", ""lud"", ""lue"", ""lug"", ""lun"", ""luo"", ""lus"", ""luy"", ""lvs"", ""lwg"", ""lww"", ""lzh"", ""maa"", ""mad"", ""mag"", ""mah"", ""mai"", ""mak"", ""mal"", ""mam"", ""man"", ""mar"", ""mas"", ""mau"", ""maw"", ""maz"", ""mbb"", ""mbf"", ""mbh"", ""mbs"", ""mbt"", ""mcd"", ""mck"", ""mcq"", ""mdf"", ""mdy"", ""med"", ""mej"", ""mek"", ""men"", ""met"", ""meu"", ""mfe"", ""mfi"", ""mfq"", ""mfy"", ""mge"", ""mgh"", ""mh"", ""mhi"", ""mhr"", ""mhw"", ""mhx"", ""mi"", ""mic"", ""mie"", ""mif"", ""min"", ""mip"", ""miq"", ""mjc"", ""mjw"", ""mk"", ""mkd"", ""mkn"", ""ml"", ""mlg"", ""mlh"", ""mlt"", ""mmo"", ""mmx"", ""mna"", ""mnb"", ""mni"", ""mnk"", ""mns"", ""mnw"", ""moc"", ""mog"", ""moh"", ""mon"", ""mos"", ""mph"", ""mpm"", ""mpp"", ""mps"", ""mpx"", ""mqj"", ""mqy"", ""mr"", ""mri"", ""mrj"", ""mrw"", ""msa"", ""msb"", ""msc"", ""msk"", ""msy"", ""mt"", ""mtg"", ""mti"", ""muh"", ""mui"", ""mup"", ""mur"", ""mux"", ""mva"", ""mvn"", ""mvp"", ""mwc"", ""mwf"", ""mwl"", ""mwm"", ""mwn"", ""mwp"", ""mwv"", ""mww"", ""mxb"", ""mxt"", ""mxv"", ""mxx"", ""my"", ""mya"", ""myb"", ""myk"", ""myu"", ""myv"", ""myw"", ""myy"", ""mza"", ""mzh"", ""mzn"", ""naf"", ""nah"", ""nak"", ""nan"", ""nap"", ""naq"", ""nas"", ""nav"", ""nb"", ""nbc"", ""nbe"", ""nbl"", ""nbu"", ""nca"", ""nch"", ""ncj"", ""ncx"", ""nd"", ""ndc"", ""nde"", ""ndo"", ""nds"", ""nep"", ""new"", ""nfa"", ""ng"", ""ngl"", ""ngu"", ""nhe"", ""nhg"", ""nhi"", ""nho"", ""nhr"", ""nhw"", ""nhx"", ""nia"", ""nif"", ""nii"", ""nij"", ""nin"", ""niu"", ""njm"", ""njn"", ""njz"", ""nl"", ""nld"", ""nlg"", ""nmf"", ""nmz"", ""nn"", ""nnb"", ""nnh"", ""nno"", ""nnp"", ""nnw"", ""nob"", ""nog"", ""non"", ""nop"", ""nor"", ""not"", ""nov"", ""nph"", ""npi"", ""npy"", ""nqo"", ""nr"", ""nrm"", ""nsa"", ""nsn"", ""nso"", ""nss"", ""nst"", ""nsu"", ""ntp"", ""ntu"", ""nuj"", ""nus"", ""nuy"", ""nv"", ""nvm"", ""nwi"", ""ny"", ""nya"", ""nyk"", ""nyn"", ""nyu"", ""nyy"", ""nzi"", ""nzm"", ""obo"", ""oc"", ""oci"", ""ojb"", ""oji"", ""okv"", ""olo"", ""omb"", ""omw"", ""ong"", ""opm"", ""ori"", ""orm"", ""orv"", ""ory"", ""os"", ""oss"", ""ota"", ""otd"", ""ote"", ""ots"", ""otw"", ""pa"", ""pad"", ""pag"", ""pam"", ""pan"", ""pao"", ""pap"", ""pau"", ""pbb"", ""pbt"", ""pcd"", ""pck"", ""pcm"", ""pdc"", ""pdt"", ""pes"", ""pfl"", ""pib"", ""pis"", ""pjt"", ""pl"", ""plg"", ""pls"", ""plt"", ""plu"", ""plw"", ""pma"", ""pmf"", ""pms"", ""pmx"", ""pnb"", ""pnt"", ""poe"", ""poh"", ""poi"", ""pol"", ""pon"", ""por"", ""pot"", ""ppk"", ""ppo"", ""pps"", ""prg"", ""prs"", ""pt"", ""ptp"", ""ptu"", ""pui"", ""pus"", ""pwg"", ""pwn"", ""qub"", ""quc"", ""que"", ""quf"", ""qug"", ""quh"", ""qul"", ""qup"", ""quw"", ""quy"", ""quz"", ""qvc"", ""qvh"", ""qvi"", ""qvn"", ""qvs"", ""qvw"", ""qxl"", ""qxn"", ""qxo"", ""rad"", ""raj"", ""rap"", ""rar"", ""raw"", ""rcf"", ""rej"", ""rgu"", ""rhg"", ""ria"", ""rif"", ""rjs"", ""rkb"", ""rm"", ""rmc"", ""rml"", ""rmn"", ""rmo"", ""rmq"", ""rmy"", ""rn"", ""rnl"", ""ro"", ""roh"", ""rom"", ""ron"", ""roo"", ""rop"", ""row"", ""rro"", ""rtm"", ""ru"", ""rue"", ""ruf"", ""rug"", ""run"", ""rup"", ""rus"", ""rw"", ""rwo"", ""sa"", ""sab"", ""sag"", ""sah"", ""san"", ""sas"", ""sat"", ""sbd"", ""sbe"", ""sc"", ""scn"", ""sco"", ""sd"", ""sda"", ""sdc"", ""sdh"", ""se"", ""seh"", ""ses"", ""sg"", ""sgb"", ""sgc"", ""sgh"", ""sgs"", ""sgw"", ""shi"", ""shk"", ""shn"", ""shp"", ""shu"", ""si"", ""sid"", ""sil"", ""sim"", ""sin"", ""sk"", ""skg"", ""skr"", ""sl"", ""slk"", ""sll"", ""slv"", ""sm"", ""sma"", ""sme"", ""smj"", ""smk"", ""sml"", ""smn"", ""smo"", ""sms"", ""sn"", ""sna"", ""snc"", ""snd"", ""snf"", ""snn"", ""snp"", ""snw"", ""sny"", ""so"", ""som"", ""sop"", ""soq"", ""sot"", ""spa"", ""spl"", ""spm"", ""spp"", ""sps"", ""sqi"", ""sr"", ""srd"", ""srm"", ""srn"", ""srp"", ""srr"", ""ss"", ""ssd"", ""ssg"", ""ssw"", ""ssx"", ""st"", ""stq"", ""su"", ""suc"", ""sue"", ""suk"", ""sun"", ""sus"", ""suz"", ""sv"", ""swa"", ""swb"", ""swc"", ""swe"", ""swg"", ""swh"", ""swp"", ""sxb"", ""sxn"", ""sxw"", ""syb"", ""syc"", ""syl"", ""syr"", ""szl"", ""szy"", ""ta"", ""tab"", ""tah"", ""taj"", ""tam"", ""tap"", ""taq"", ""tar"", ""tat"", ""taw"", ""tay"", ""tbg"", ""tbo"", ""tbw"", ""tby"", ""tbz"", ""tca"", ""tcs"", ""tcy"", ""tcz"", ""tdt"", ""tdx"", ""te"", ""tel"", ""teo"", ""tet"", ""tfr"", ""tg"", ""tgk"", ""tgo"", ""tgp"", ""th"", ""tha"", ""thl"", ""ti"", ""tif"", ""tig"", ""tih"", ""tir"", ""tiv"", ""tk"", ""tke"", ""tkl"", ""tkr"", ""tku"", ""tlb"", ""tlf"", ""tlh"", ""tll"", ""tly"", ""tmd"", ""tmh"", ""tn"", ""tnc"", ""tnk"", ""tnn"", ""tnp"", ""tnr"", ""to"", ""tob"", ""tod"", ""tog"", ""toi"", ""toj"", ""tok"", ""ton"", ""too"", ""top"", ""tos"", ""tpi"", ""tr"", ""trc"", ""trn"", ""trp"", ""trq"", ""trv"", ""ts"", ""tsg"", ""tsn"", ""tso"", ""tsz"", ""tt"", ""ttc"", ""tte"", ""ttq"", ""tuc"", ""tuf"", ""tui"", ""tuk"", ""tum"", ""tur"", ""tvk"", ""tvl"", ""tw"", ""twi"", ""twu"", ""txu"", ""ty"", ""tyv"", ""tzh"", ""tzj"", ""tzm"", ""tzo"", ""ubr"", ""ubu"", ""udm"", ""ug"", ""uig"", ""uk"", ""ukr"", ""umb"", ""und"", ""upv"", ""ur"", ""urd"", ""urh"", ""usa"", ""usp"", ""uvh"", ""uvl"", ""uzb"", ""uzn"", ""uzs"", ""vap"", ""ve"", ""vec"", ""ven"", ""vep"", ""vi"", ""vid"", ""vie"", ""vls"", ""vmw"", ""vmy"", ""vo"", ""vol"", ""vro"", ""vun"", ""wa"", ""waj"", ""wal"", ""war"", ""wat"", ""way"", ""wbm"", ""wbp"", ""wed"", ""wes"", ""wln"", ""wls"", ""wlv"", ""wlx"", ""wmw"", ""wnc"", ""wnu"", ""wo"", ""wol"", ""wos"", ""wrs"", ""wsg"", ""wsk"", ""wuu"", ""wuv"", ""xal"", ""xbi"", ""xh"", ""xho"", ""xla"", ""xmf"", ""xmm"", ""xmv"", ""xog"", ""xon"", ""xsm"", ""xsr"", ""xtd"", ""xtm"", ""xtn"", ""yaa"", ""yal"", ""yao"", ""yap"", ""yby"", ""ydd"", ""yid"", ""yka"", ""yle"", ""yli"", ""yml"", ""yo"", ""yom"", ""yon"", ""yor"", ""yrk"", ""yrl"", ""yss"", ""yua"", ""yue"", ""yuj"", ""yut"", ""yuw"", ""yva"", ""zac"", ""zai"", ""zam"", ""zao"", ""zap"", ""zas"", ""zat"", ""zdj"", ""zea"", ""zgh"", ""zha"", ""zho"", ""zia"", ""zom"", ""zos"", ""zpm"", ""zpo"", ""zpt"", ""zpu"", ""zsm"", ""zu"", ""zul"", ""zyb"", ""zyp"", ""zza""]}","## Dataset Description + +- **Repository:** [https://github.com/cisnlp/GlotCC](https://github.com/cisnlp/GlotCC) +- **Paper:** [https://arxiv.org/abs/2410.23825](https://arxiv.org/abs/2410.23825) +- **Point of Contact:** [amir@cis.lmu.de](mailto:amir@cis.lmu.de) + +### Dataset Summary + + + + +**GlotCC-V1.0** is a document-level, general domain dataset derived from CommonCrawl, covering more than **1000** languages. +It is built using the [GlotLID](https://github.com/cisnlp/GlotLID) language identification and [Ungoliant](https://github.com/kargaranamir/ungoliant) pipeline from CommonCrawl. +We release our pipeline as open-source at [https://github.com/cisnlp/GlotCC](https://github.com/cisnlp/GlotCC). + +**List of Languages:** See [https://datasets-server.huggingface.co/splits?dataset=cis-lmu/GlotCC-V1](https://datasets-server.huggingface.co/splits?dataset=cis-lmu/GlotCC-V1) to get the list of splits available. + + +### Usage (Huggingface Hub -- Recommended) + +Replace `bal-Arab` with your specific language. + + +```python +from huggingface_hub import snapshot_download + +folder = snapshot_download( + ""cis-lmu/glotcc-v1"", + repo_type=""dataset"", + local_dir=""./path/to/glotcc-v1/"", + # Replace ""v1.0/bal-Arab/*"" with the path for any other language available in the dataset + allow_patterns=""v1.0/bal-Arab/*"" +) + +``` + + +For faster downloads, make sure to `pip install huggingface_hub[hf_transfer]` and set the environment variable `HF_HUB_ENABLE_HF_TRANSFER`=1. + +Then you can load it with any library that supports Parquet files, such as Pandas: + +```python +import pandas as pd + +# Load the dataset from a Parquet file +# Replace the file path with the path to the desired language's Parquet file +dataset = pd.read_parquet('./path/to/glotcc-v1/v1.0/bal-Arab/bal-Arab_0.parquet') + +# Print the first 5 rows of the dataset +print(dataset.head()) +``` + + +### Usage (Huggingface datasets) + + +```python +from datasets import load_dataset + +# Replace ""bal-Arab"" with the name of any other language available in the dataset +dataset = load_dataset(""cis-lmu/glotcc-v1"", name=""bal-Arab"", split=""train"") + +# Print the first row of data +print(dataset[0]) + +``` + + +### Usage (Huggingface datasets -- streaming=True) + + +```python +from datasets import load_dataset + +# Replace ""bal-Arab"" with the name of any other language available in the dataset +fw = load_dataset(""cis-lmu/glotcc-v1"", name=""bal-Arab"", split=""train"", streaming=True) + +# Create an iterator from the streaming dataset +iterator = iter(fw) + +# Print the next item from the iterator +print(next(iterator)) + +``` + + +### Usage (direct download) + +If you prefer not to use the Hugging Face datasets or hub you can download it directly. For example, to download the first file of `bal-Arab`: + +```python +!wget https://huggingface.co/datasets/cis-lmu/GlotCC-V1/resolve/main/v1.0/bal-Arab/bal-Arab_0.parquet +``` + + +## Additional Information + +The dataset is currently heavily under audit and changes accordingly. + + +### Licensing Information + +GlotCC data is released under the following licensing scheme: We do not own any of the text from which this data has been extracted. The data is licensed under the terms of the CommonCrawl [Terms of Use](https://commoncrawl.org/terms-of-use). We license the actual packaging, metadata, and annotations of this data under the Creative Commons [CC0 license](https://github.com/cisnlp/GlotCC/blob/main/LICENSE). + + +### Citation Information + +If you find our data useful for your research, please cite: + + +``` +@article{kargaran2024glotcc, + title = {Glot{CC}: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages}, + author = {Kargaran, Amir Hossein and Yvon, Fran{\c{c}}ois and Sch{\""u}tze, Hinrich}, + journal = {Advances in Neural Information Processing Systems}, + year = {2024}, + url = {https://arxiv.org/abs/2410.23825} +} +```" +simon3000/genshin-voice,"{""language"": [""zh"", ""en"", ""ja"", ""ko""], ""task_categories"": [""audio-classification"", ""automatic-speech-recognition"", ""text-to-speech""], ""pretty_name"": ""Genshin Voice"", ""dataset_info"": {""features"": [{""name"": ""audio"", ""dtype"": ""audio""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""language"", ""dtype"": ""string""}, {""name"": ""speaker"", ""dtype"": ""string""}, {""name"": ""speaker_type"", ""dtype"": ""string""}, {""name"": ""type"", ""dtype"": ""string""}, {""name"": ""inGameFilename"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 264598217401.752, ""num_examples"": 463383}], ""download_size"": 227704444125, ""dataset_size"": 264598217401.752}, ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""train"", ""path"": ""data/train-*""}]}]}","# Genshin Voice + +Genshin Voice is a dataset of voice lines from the popular game [Genshin Impact](https://genshin.hoyoverse.com/). + +Hugging Face 🤗 [Genshin-Voice](https://huggingface.co/datasets/simon3000/genshin-voice) + + +Last update at `2024-08-30` + +`463383` wavs + +`20231` without speaker (4%) + +`24819` without transcription (5%) + +`602` without inGameFilename (0%) + + +## Dataset Details + +### Dataset Description + +The dataset contains voice lines from the game's characters in multiple languages, including Chinese, English, Japanese, and Korean. + +The voice lines are spoken by the characters in the game and cover a wide range of topics, including greetings, combat, and story dialogue. + +- **Language(s) (NLP):** Chinese, English, Japanese, Korean + +## Uses + +To install Hugging Face's datasets library, follow the instructions from [this link](https://huggingface.co/docs/datasets/installation#audio). + +### Example: Load the dataset and filter for Chinese voices of Ganyu with transcriptions + +```python +from datasets import load_dataset +import soundfile as sf +import os + +# Load the dataset +dataset = load_dataset('simon3000/genshin-voice', split='train', streaming=True) + +# Filter the dataset for Chinese voices of Ganyu with transcriptions +chinese_ganyu = dataset.filter(lambda voice: voice['language'] == 'Chinese' and voice['speaker'] == 'Ganyu' and voice['transcription'] != '') + +# Create a folder to store the audio and transcription files +ganyu_folder = 'ganyu' +os.makedirs(ganyu_folder, exist_ok=True) + +# Process each voice in the filtered dataset +for i, voice in enumerate(chinese_ganyu): + audio_path = os.path.join(ganyu_folder, f'{i}_audio.wav') # Path to save the audio file + transcription_path = os.path.join(ganyu_folder, f'{i}_transcription.txt') # Path to save the transcription file + + # Save the audio file + sf.write(audio_path, voice['audio']['array'], voice['audio']['sampling_rate']) + + # Save the transcription file + with open(transcription_path, 'w') as transcription_file: + transcription_file.write(voice['transcription']) + + print(f'{i} done') # Print the progress +``` + +### You unpacked the game and just want to know what the wavs are about + +result.json format: (subject to change) + +```json +{ + ""9b5502fb1b83cb97.wav"": { + ""inGameFilename"": ""VO_friendship\\VO_raidenShogun\\vo_raidenEi_dialog_pendant.wem"", + ""filename"": ""9b5502fb1b83cb97.wav"", + ""language"": ""English(US)"", + ""transcription"": ""Really? So in all this time, no new Electro Visions have appeared in the outside world? Well, what I can say on this topic is subject to certain constraints, but... it is not by my will that Visions are granted or denied. The key is people's desire, and... well, there's another side to it too."", + ""speaker"": ""Raiden Shogun"", + ""talkRoleType"": """", + ""talkRoleID"": """", + ""guid"": ""f8e72b65-6c0a-4df1-a2f0-2bb08dbeab75"", + ""voiceConfigs"": [ + { + ""gameTrigger"": ""Fetter"", + ""gameTriggerArgs"": 3001, + ""avatarName"": ""Switch_raidenShogun"" + } + ] + } +} +``` + +## Dataset Creation + +### Source Data + +The data was obtained by unpacking the [Genshin Impact](https://genshin.hoyoverse.com/) game. + +#### Data Collection and Processing + +Please refer to [Genshin-Voice](https://github.com/simon300000/genshin-voice) and [w4123/GenshinVoice](https://github.com/w4123/GenshinVoice) for more information on how the data was processed. + +#### Who are the source data producers? + +The source data producers are the developers of the game, miHoYo. + +### Annotations + +The dataset contains official annotations from the game, including language, speaker name, and transcription. + +## Bias, Risks, and Limitations + +Annotations are incomplete. Some voice lines are missing speaker names and transcriptions. + +Speakers and transcriptions may contain markups and placeholders: `#パイモン：{NICKNAME}、すごく怖い悪夢を見たことってあるか？\\n{NICKNAME}：...` + +### Recommendations + +Users should be made aware of the risks, biases and limitations of the dataset. + +Speaker names can be partially inferred from the ingame filenames. + +## Licensing Information + +Copyright © COGNOSPHERE. All Rights Reserved. + +## More Information + +I can upload wav files on demand." +WueNLP/sib-fleurs,"{""license"": ""cc-by-sa-4.0"", ""language"": [""ace"", ""acm"", ""acq"", ""aeb"", ""af"", ""ajp"", ""ak"", ""als"", ""am"", ""apc"", ""ar"", ""ars"", ""ary"", ""arz"", ""as"", ""ast"", ""awa"", ""ayr"", ""azb"", ""azj"", ""ba"", ""bm"", ""ban"", ""be"", ""bem"", ""bn"", ""bho"", ""bjn"", ""bo"", ""bs"", ""bug"", ""bg"", ""ca"", ""ceb"", ""cs"", ""cjk"", ""ckb"", ""crh"", ""cy"", ""da"", ""de"", ""dik"", ""dyu"", ""dz"", ""el"", ""en"", ""eo"", ""et"", ""eu"", ""ee"", ""fo"", ""fj"", ""fi"", ""fon"", ""fr"", ""fur"", ""fuv"", ""gaz"", ""gd"", ""ga"", ""gl"", ""gn"", ""gu"", ""ht"", ""ha"", ""he"", ""hi"", ""hne"", ""hr"", ""hu"", ""hy"", ""ig"", ""ilo"", ""id"", ""is"", ""it"", ""jv"", ""ja"", ""kab"", ""kac"", ""kam"", ""kn"", ""ks"", ""ka"", ""kk"", ""kbp"", ""kea"", ""khk"", ""km"", ""ki"", ""rw"", ""ky"", ""kmb"", ""kmr"", ""knc"", ""kg"", ""ko"", ""lo"", ""lij"", ""li"", ""ln"", ""lt"", ""lmo"", ""ltg"", ""lb"", ""lua"", ""lg"", ""luo"", ""lus"", ""lvs"", ""mag"", ""mai"", ""ml"", ""mar"", ""min"", ""mk"", ""mt"", ""mni"", ""mos"", ""mi"", ""my"", ""nl"", ""nn"", ""nb"", ""npi"", ""nqo"", ""nso"", ""nus"", ""ny"", ""oc"", ""ory"", ""pag"", ""pa"", ""pap"", ""pbt"", ""pes"", ""plt"", ""pl"", ""pt"", ""prs"", ""quy"", ""ro"", ""rn"", ""ru"", ""sg"", ""sa"", ""sat"", ""scn"", ""shn"", ""si"", ""sk"", ""sl"", ""sm"", ""sn"", ""sd"", ""so"", ""st"", ""es"", ""sc"", ""sr"", ""ss"", ""su"", ""sv"", ""swh"", ""szl"", ""ta"", ""taq"", ""tt"", ""te"", ""tg"", ""tl"", ""th"", ""ti"", ""tpi"", ""tn"", ""ts"", ""tk"", ""tum"", ""tr"", ""tw"", ""tzm"", ""ug"", ""uk"", ""umb"", ""ur"", ""uzn"", ""vec"", ""vi"", ""war"", ""wo"", ""xh"", ""ydd"", ""yo"", ""yue"", ""zh"", ""zsm"", ""zu"", ""multilingual""], ""annotations_creators"": [""found""], ""language_creators"": [""expert-generated""], ""multilinguality"": [""multilingual""], ""task_categories"": [""audio-classification"", ""automatic-speech-recognition"", ""audio-text-to-text"", ""text-to-speech"", ""question-answering"", ""document-question-answering""], ""pretty_name"": ""SIB-Fleurs"", ""dataset_info"": [{""config_name"": ""afr_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 524232877.0, ""num_examples"": 406}, {""name"": ""validation"", ""num_bytes"": 76384271.0, ""num_examples"": 86}, {""name"": ""test"", ""num_bytes"": 84400076.0, ""num_examples"": 95}], ""download_size"": 673661100, ""dataset_size"": 685017224.0}, {""config_name"": ""amh_Ethi"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1289823377.0, ""num_examples"": 752}, {""name"": ""validation"", ""num_bytes"": 65389982.0, ""num_examples"": 54}, {""name"": ""test"", ""num_bytes"": 185857834.0, ""num_examples"": 149}], ""download_size"": 1525564166, ""dataset_size"": 1541071193.0}, {""config_name"": ""arb_Arab"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 646819902.0, ""num_examples"": 579}, {""name"": ""validation"", ""num_bytes"": 95091075.0, ""num_examples"": 64}, {""name"": ""test"", ""num_bytes"": 144786307.0, ""num_examples"": 133}], ""download_size"": 878867591, ""dataset_size"": 886697284.0}, {""config_name"": ""asm_Beng"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1235366957.0, ""num_examples"": 730}, {""name"": ""validation"", ""num_bytes"": 158536549.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 400145792.0, ""num_examples"": 176}], ""download_size"": 1782426273, ""dataset_size"": 1794049298.0}, {""config_name"": ""ast_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 866679990.0, ""num_examples"": 701}, {""name"": ""validation"", ""num_bytes"": 102384453.0, ""num_examples"": 69}, {""name"": ""test"", ""num_bytes"": 282753773.0, ""num_examples"": 177}], ""download_size"": 1245085728, ""dataset_size"": 1251818216.0}, {""config_name"": ""azj_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1090899299.0, ""num_examples"": 712}, {""name"": ""validation"", ""num_bytes"": 147617247.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 379234055.0, ""num_examples"": 174}], ""download_size"": 1602247163, ""dataset_size"": 1617750601.0}, {""config_name"": ""bel_Cyrl"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1105817781.0, ""num_examples"": 690}, {""name"": ""validation"", ""num_bytes"": 186825266.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 486320479.0, ""num_examples"": 177}], ""download_size"": 1753989008, ""dataset_size"": 1778963526.0}, {""config_name"": ""ben_Beng"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1232070743.0, ""num_examples"": 742}, {""name"": ""validation"", ""num_bytes"": 157285034.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 397951833.0, ""num_examples"": 176}], ""download_size"": 1782546384, ""dataset_size"": 1787307610.0}, {""config_name"": ""bos_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1173791520.0, ""num_examples"": 746}, {""name"": ""validation"", ""num_bytes"": 149405247.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 369790849.0, ""num_examples"": 177}], ""download_size"": 1654694782, ""dataset_size"": 1692987616.0}, {""config_name"": ""bul_Cyrl"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1101248058.0, ""num_examples"": 749}, {""name"": ""validation"", ""num_bytes"": 117353674.0, ""num_examples"": 70}, {""name"": ""test"", ""num_bytes"": 221557279.0, ""num_examples"": 176}], ""download_size"": 1421883953, ""dataset_size"": 1440159011.0}, {""config_name"": ""cat_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 863830240.0, ""num_examples"": 683}, {""name"": ""validation"", ""num_bytes"": 147554660.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 353869370.0, ""num_examples"": 177}], ""download_size"": 1340643723, ""dataset_size"": 1365254270.0}, {""config_name"": ""ceb_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1398384311.0, ""num_examples"": 741}, {""name"": ""validation"", ""num_bytes"": 95970795.0, ""num_examples"": 61}, {""name"": ""test"", ""num_bytes"": 240259442.0, ""num_examples"": 149}], ""download_size"": 1718325671, ""dataset_size"": 1734614548.0}, {""config_name"": ""ces_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 970924211.0, ""num_examples"": 732}, {""name"": ""validation"", ""num_bytes"": 112601348.0, ""num_examples"": 68}, {""name"": ""test"", ""num_bytes"": 277229156.0, ""num_examples"": 172}], ""download_size"": 1333906872, ""dataset_size"": 1360754715.0}, {""config_name"": ""ckb_Arab"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1178357835.0, ""num_examples"": 738}, {""name"": ""validation"", ""num_bytes"": 134860481.0, ""num_examples"": 70}, {""name"": ""test"", ""num_bytes"": 342458168.0, ""num_examples"": 176}], ""download_size"": 1613748924, ""dataset_size"": 1655676484.0}, {""config_name"": ""cym_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1385174116.0, ""num_examples"": 739}, {""name"": ""validation"", ""num_bytes"": 200018352.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 486565088.0, ""num_examples"": 177}], ""download_size"": 2038201423, ""dataset_size"": 2071757556.0}, {""config_name"": ""dan_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 877728248.0, ""num_examples"": 696}, {""name"": ""validation"", ""num_bytes"": 130348707.0, ""num_examples"": 70}, {""name"": ""test"", ""num_bytes"": 340140011.0, ""num_examples"": 177}], ""download_size"": 1319500991, ""dataset_size"": 1348216966.0}, {""config_name"": ""deu_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1059347230.0, ""num_examples"": 736}, {""name"": ""validation"", ""num_bytes"": 136254869.0, ""num_examples"": 69}, {""name"": ""test"", ""num_bytes"": 364325435.0, ""num_examples"": 175}], ""download_size"": 1542935687, ""dataset_size"": 1559927534.0}, {""config_name"": ""ell_Grek"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1169505435.0, ""num_examples"": 750}, {""name"": ""validation"", ""num_bytes"": 86533682.0, ""num_examples"": 67}, {""name"": ""test"", ""num_bytes"": 228840869.0, ""num_examples"": 168}], ""download_size"": 1470419073, ""dataset_size"": 1484879986.0}, {""config_name"": ""eng_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 865407552.0, ""num_examples"": 738}, {""name"": ""validation"", ""num_bytes"": 113902786.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 197416856.0, ""num_examples"": 177}], ""download_size"": 1168283579, ""dataset_size"": 1176727194.0}, {""config_name"": ""est_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 841849798.0, ""num_examples"": 700}, {""name"": ""validation"", ""num_bytes"": 136854050.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 352690669.0, ""num_examples"": 176}], ""download_size"": 1311922527, ""dataset_size"": 1331394517.0}, {""config_name"": ""fin_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1013025006.0, ""num_examples"": 735}, {""name"": ""validation"", ""num_bytes"": 154629039.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 377490223.0, ""num_examples"": 175}], ""download_size"": 1514479202, ""dataset_size"": 1545144268.0}, {""config_name"": ""fra_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1200484942.0, ""num_examples"": 753}, {""name"": ""validation"", ""num_bytes"": 89645406.0, ""num_examples"": 65}, {""name"": ""test"", ""num_bytes"": 219759551.0, ""num_examples"": 164}], ""download_size"": 1473280670, ""dataset_size"": 1509889899.0}, {""config_name"": ""fuv_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1625942463.0, ""num_examples"": 752}, {""name"": ""validation"", ""num_bytes"": 110111916.0, ""num_examples"": 68}, {""name"": ""test"", ""num_bytes"": 305080005.0, ""num_examples"": 166}], ""download_size"": 2031410049, ""dataset_size"": 2041134384.0}, {""config_name"": ""gaz_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 766698042.0, ""num_examples"": 574}, {""name"": ""validation"", ""num_bytes"": 4996373.0, ""num_examples"": 6}, {""name"": ""test"", ""num_bytes"": 12726015.0, ""num_examples"": 17}], ""download_size"": 778314621, ""dataset_size"": 784420430.0}, {""config_name"": ""gle_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1417633991.0, ""num_examples"": 731}, {""name"": ""validation"", ""num_bytes"": 168821631.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 409952057.0, ""num_examples"": 176}], ""download_size"": 1963143042, ""dataset_size"": 1996407679.0}, {""config_name"": ""glg_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 776866102.0, ""num_examples"": 660}, {""name"": ""validation"", ""num_bytes"": 115361837.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 308185507.0, ""num_examples"": 174}], ""download_size"": 1195253363, ""dataset_size"": 1200413446.0}, {""config_name"": ""guj_Gujr"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1049403304.0, ""num_examples"": 752}, {""name"": ""validation"", ""num_bytes"": 130727757.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 341271185.0, ""num_examples"": 177}], ""download_size"": 1519511715, ""dataset_size"": 1521402246.0}, {""config_name"": ""hau_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1579344700.0, ""num_examples"": 753}, {""name"": ""validation"", ""num_bytes"": 175883597.0, ""num_examples"": 70}, {""name"": ""test"", ""num_bytes"": 374260636.0, ""num_examples"": 166}], ""download_size"": 2128392442, ""dataset_size"": 2129488933.0}, {""config_name"": ""heb_Hebr"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1094855635.0, ""num_examples"": 754}, {""name"": ""validation"", ""num_bytes"": 91724842.0, ""num_examples"": 70}, {""name"": ""test"", ""num_bytes"": 238749489.0, ""num_examples"": 175}], ""download_size"": 1420931124, ""dataset_size"": 1425329966.0}, {""config_name"": ""hin_Deva"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 784008338.0, ""num_examples"": 653}, {""name"": ""validation"", ""num_bytes"": 73025370.0, ""num_examples"": 60}, {""name"": ""test"", ""num_bytes"": 148402410.0, ""num_examples"": 132}], ""download_size"": 999448112, ""dataset_size"": 1005436118.0}, {""config_name"": ""hrv_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1374835242.0, ""num_examples"": 756}, {""name"": ""validation"", ""num_bytes"": 116395175.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 300472197.0, ""num_examples"": 176}], ""download_size"": 1739639653, ""dataset_size"": 1791702614.0}, {""config_name"": ""hun_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1070647343.0, ""num_examples"": 750}, {""name"": ""validation"", ""num_bytes"": 146140834.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 359201948.0, ""num_examples"": 177}], ""download_size"": 1560605445, ""dataset_size"": 1575990125.0}, {""config_name"": ""hye_Armn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1199310259.0, ""num_examples"": 741}, {""name"": ""validation"", ""num_bytes"": 133092440.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 348410386.0, ""num_examples"": 177}], ""download_size"": 1641173951, ""dataset_size"": 1680813085.0}, {""config_name"": ""ibo_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1627430548.0, ""num_examples"": 737}, {""name"": ""validation"", ""num_bytes"": 215297933.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 554277405.0, ""num_examples"": 177}], ""download_size"": 2327164690, ""dataset_size"": 2397005886.0}, {""config_name"": ""ind_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1070832404.0, ""num_examples"": 728}, {""name"": ""validation"", ""num_bytes"": 114893806.0, ""num_examples"": 69}, {""name"": ""test"", ""num_bytes"": 278118946.0, ""num_examples"": 167}], ""download_size"": 1457872159, ""dataset_size"": 1463845156.0}, {""config_name"": ""isl_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 330951934.0, ""num_examples"": 381}, {""name"": ""validation"", ""num_bytes"": 14249666.0, ""num_examples"": 18}, {""name"": ""test"", ""num_bytes"": 20416835.0, ""num_examples"": 23}], ""download_size"": 363202271, ""dataset_size"": 365618435.0}, {""config_name"": ""ita_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1038872172.0, ""num_examples"": 743}, {""name"": ""validation"", ""num_bytes"": 171701144.0, ""num_examples"": 69}, {""name"": ""test"", ""num_bytes"": 409588210.0, ""num_examples"": 175}], ""download_size"": 1597494540, ""dataset_size"": 1620161526.0}, {""config_name"": ""jav_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1297339053.0, ""num_examples"": 740}, {""name"": ""validation"", ""num_bytes"": 119962974.0, ""num_examples"": 67}, {""name"": ""test"", ""num_bytes"": 326612734.0, ""num_examples"": 171}], ""download_size"": 1737637397, ""dataset_size"": 1743914761.0}, {""config_name"": ""jpn_Jpan"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 868173246.0, ""num_examples"": 662}, {""name"": ""validation"", ""num_bytes"": 106866406.0, ""num_examples"": 62}, {""name"": ""test"", ""num_bytes"": 279227775.0, ""num_examples"": 164}], ""download_size"": 1239767618, ""dataset_size"": 1254267427.0}, {""config_name"": ""kam_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1719637560.0, ""num_examples"": 752}, {""name"": ""validation"", ""num_bytes"": 164496223.0, ""num_examples"": 69}, {""name"": ""test"", ""num_bytes"": 459710265.0, ""num_examples"": 179}], ""download_size"": 2328603553, ""dataset_size"": 2343844048.0}, {""config_name"": ""kan_Knda"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 964875026.0, ""num_examples"": 660}, {""name"": ""validation"", ""num_bytes"": 145728311.0, ""num_examples"": 70}, {""name"": ""test"", ""num_bytes"": 362445901.0, ""num_examples"": 174}], ""download_size"": 1458922305, ""dataset_size"": 1473049238.0}, {""config_name"": ""kat_Geor"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 602155489.0, ""num_examples"": 557}, {""name"": ""validation"", ""num_bytes"": 130581034.0, ""num_examples"": 69}, {""name"": ""test"", ""num_bytes"": 359417267.0, ""num_examples"": 177}], ""download_size"": 1079955726, ""dataset_size"": 1092153790.0}, {""config_name"": ""kaz_Cyrl"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1371437438.0, ""num_examples"": 749}, {""name"": ""validation"", ""num_bytes"": 175322718.0, ""num_examples"": 70}, {""name"": ""test"", ""num_bytes"": 446125883.0, ""num_examples"": 176}], ""download_size"": 1943326254, ""dataset_size"": 1992886039.0}, {""config_name"": ""kea_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1233357045.0, ""num_examples"": 725}, {""name"": ""validation"", ""num_bytes"": 143947103.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 373071809.0, ""num_examples"": 175}], ""download_size"": 1738909295, ""dataset_size"": 1750375957.0}, {""config_name"": ""khk_Cyrl"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1140695534.0, ""num_examples"": 743}, {""name"": ""validation"", ""num_bytes"": 128375508.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 336105200.0, ""num_examples"": 177}], ""download_size"": 1560413545, ""dataset_size"": 1605176242.0}, {""config_name"": ""khm_Khmr"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 854736195.0, ""num_examples"": 588}, {""name"": ""validation"", ""num_bytes"": 150787699.0, ""num_examples"": 69}, {""name"": ""test"", ""num_bytes"": 358796063.0, ""num_examples"": 168}], ""download_size"": 1336834917, ""dataset_size"": 1364319957.0}, {""config_name"": ""kir_Cyrl"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1085673831.0, ""num_examples"": 729}, {""name"": ""validation"", ""num_bytes"": 145080284.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 383793918.0, ""num_examples"": 177}], ""download_size"": 1580489766, ""dataset_size"": 1614548033.0}, {""config_name"": ""kor_Hang"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 926056164.0, ""num_examples"": 669}, {""name"": ""validation"", ""num_bytes"": 92920021.0, ""num_examples"": 61}, {""name"": ""test"", ""num_bytes"": 163632188.0, ""num_examples"": 141}], ""download_size"": 1162697408, ""dataset_size"": 1182608373.0}, {""config_name"": ""lao_Laoo"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 848523584.0, ""num_examples"": 591}, {""name"": ""validation"", ""num_bytes"": 59517451.0, ""num_examples"": 54}, {""name"": ""test"", ""num_bytes"": 168578213.0, ""num_examples"": 132}], ""download_size"": 1075447131, ""dataset_size"": 1076619248.0}, {""config_name"": ""lin_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 2110793488.0, ""num_examples"": 755}, {""name"": ""validation"", ""num_bytes"": 114332315.0, ""num_examples"": 59}, {""name"": ""test"", ""num_bytes"": 291255234.0, ""num_examples"": 139}], ""download_size"": 2505804321, ""dataset_size"": 2516381037.0}, {""config_name"": ""lit_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1140098095.0, ""num_examples"": 730}, {""name"": ""validation"", ""num_bytes"": 134247036.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 346763275.0, ""num_examples"": 178}], ""download_size"": 1580279654, ""dataset_size"": 1621108406.0}, {""config_name"": ""ltz_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 983863587.0, ""num_examples"": 703}, {""name"": ""validation"", ""num_bytes"": 122673699.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 321154716.0, ""num_examples"": 176}], ""download_size"": 1380540072, ""dataset_size"": 1427692002.0}, {""config_name"": ""lug_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1439075546.0, ""num_examples"": 691}, {""name"": ""validation"", ""num_bytes"": 153280122.0, ""num_examples"": 70}, {""name"": ""test"", ""num_bytes"": 409606012.0, ""num_examples"": 173}], ""download_size"": 1972461167, ""dataset_size"": 2001961680.0}, {""config_name"": ""luo_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1164176310.0, ""num_examples"": 698}, {""name"": ""validation"", ""num_bytes"": 42851382.0, ""num_examples"": 39}, {""name"": ""test"", ""num_bytes"": 118611386.0, ""num_examples"": 98}], ""download_size"": 1282391858, ""dataset_size"": 1325639078.0}, {""config_name"": ""lvs_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 763295296.0, ""num_examples"": 634}, {""name"": ""validation"", ""num_bytes"": 119412393.0, ""num_examples"": 69}, {""name"": ""test"", ""num_bytes"": 321894301.0, ""num_examples"": 174}], ""download_size"": 1178718753, ""dataset_size"": 1204601990.0}, {""config_name"": ""mal_Mlym"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1160280548.0, ""num_examples"": 723}, {""name"": ""validation"", ""num_bytes"": 180187126.0, ""num_examples"": 68}, {""name"": ""test"", ""num_bytes"": 453064428.0, ""num_examples"": 174}], ""download_size"": 1782291408, ""dataset_size"": 1793532102.0}, {""config_name"": ""mar_Deva"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1393470704.0, ""num_examples"": 749}, {""name"": ""validation"", ""num_bytes"": 174902664.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 454714148.0, ""num_examples"": 177}], ""download_size"": 2008870076, ""dataset_size"": 2023087516.0}, {""config_name"": ""mkd_Cyrl"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 792228116.0, ""num_examples"": 680}, {""name"": ""validation"", ""num_bytes"": 143667110.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 370880347.0, ""num_examples"": 177}], ""download_size"": 1293866922, ""dataset_size"": 1306775573.0}, {""config_name"": ""mlt_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1148930224.0, ""num_examples"": 731}, {""name"": ""validation"", ""num_bytes"": 164475812.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 415254022.0, ""num_examples"": 176}], ""download_size"": 1702013186, ""dataset_size"": 1728660058.0}, {""config_name"": ""mri_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 2110842467.0, ""num_examples"": 749}, {""name"": ""validation"", ""num_bytes"": 251256822.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 674673277.0, ""num_examples"": 176}], ""download_size"": 3021722547, ""dataset_size"": 3036772566.0}, {""config_name"": ""mya_Mymr"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1401863756.0, ""num_examples"": 746}, {""name"": ""validation"", ""num_bytes"": 187724129.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 447605905.0, ""num_examples"": 175}], ""download_size"": 1976133845, ""dataset_size"": 2037193790.0}, {""config_name"": ""nld_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 881930671.0, ""num_examples"": 729}, {""name"": ""validation"", ""num_bytes"": 54214254.0, ""num_examples"": 58}, {""name"": ""test"", ""num_bytes"": 110418567.0, ""num_examples"": 123}], ""download_size"": 1039307907, ""dataset_size"": 1046563492.0}, {""config_name"": ""nob_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1020875353.0, ""num_examples"": 723}, {""name"": ""validation"", ""num_bytes"": 64869416.0, ""num_examples"": 51}, {""name"": ""test"", ""num_bytes"": 149463914.0, ""num_examples"": 127}], ""download_size"": 1224624229, ""dataset_size"": 1235208683.0}, {""config_name"": ""npi_Deva"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1304469469.0, ""num_examples"": 754}, {""name"": ""validation"", ""num_bytes"": 98605223.0, ""num_examples"": 70}, {""name"": ""test"", ""num_bytes"": 263321688.0, ""num_examples"": 175}], ""download_size"": 1645679853, ""dataset_size"": 1666396380.0}, {""config_name"": ""nso_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1531120766.0, ""num_examples"": 633}, {""name"": ""validation"", ""num_bytes"": 203234215.0, ""num_examples"": 70}, {""name"": ""test"", ""num_bytes"": 489116622.0, ""num_examples"": 169}], ""download_size"": 2206857309, ""dataset_size"": 2223471603.0}, {""config_name"": ""nya_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1242935371.0, ""num_examples"": 720}, {""name"": ""validation"", ""num_bytes"": 141588805.0, ""num_examples"": 68}, {""name"": ""test"", ""num_bytes"": 416888257.0, ""num_examples"": 169}], ""download_size"": 1794458304, ""dataset_size"": 1801412433.0}, {""config_name"": ""oci_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1638068285.0, ""num_examples"": 756}, {""name"": ""validation"", ""num_bytes"": 196795145.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 522449568.0, ""num_examples"": 177}], ""download_size"": 2301324869, ""dataset_size"": 2357312998.0}, {""config_name"": ""ory_Orya"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 413419271.0, ""num_examples"": 442}, {""name"": ""validation"", ""num_bytes"": 141272977.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 344554257.0, ""num_examples"": 168}], ""download_size"": 888825647, ""dataset_size"": 899246505.0}, {""config_name"": ""pan_Guru"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 704776871.0, ""num_examples"": 580}, {""name"": ""validation"", ""num_bytes"": 71033142.0, ""num_examples"": 56}, {""name"": ""test"", ""num_bytes"": 215863237.0, ""num_examples"": 143}], ""download_size"": 982824064, ""dataset_size"": 991673250.0}, {""config_name"": ""pbt_Arab"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1031899644.0, ""num_examples"": 701}, {""name"": ""validation"", ""num_bytes"": 76541359.0, ""num_examples"": 55}, {""name"": ""test"", ""num_bytes"": 203202602.0, ""num_examples"": 144}], ""download_size"": 1291546195, ""dataset_size"": 1311643605.0}, {""config_name"": ""pes_Arab"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1384720135.0, ""num_examples"": 692}, {""name"": ""validation"", ""num_bytes"": 167633472.0, ""num_examples"": 66}, {""name"": ""test"", ""num_bytes"": 425199297.0, ""num_examples"": 165}], ""download_size"": 1949938822, ""dataset_size"": 1977552904.0}, {""config_name"": ""pol_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1062588014.0, ""num_examples"": 723}, {""name"": ""validation"", ""num_bytes"": 91888076.0, ""num_examples"": 68}, {""name"": ""test"", ""num_bytes"": 235374860.0, ""num_examples"": 165}], ""download_size"": 1365817507, ""dataset_size"": 1389850950.0}, {""config_name"": ""por_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1193510057.0, ""num_examples"": 728}, {""name"": ""validation"", ""num_bytes"": 142827506.0, ""num_examples"": 70}, {""name"": ""test"", ""num_bytes"": 373148629.0, ""num_examples"": 177}], ""download_size"": 1691529909, ""dataset_size"": 1709486192.0}, {""config_name"": ""ron_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1175359850.0, ""num_examples"": 734}, {""name"": ""validation"", ""num_bytes"": 120325985.0, ""num_examples"": 69}, {""name"": ""test"", ""num_bytes"": 299962993.0, ""num_examples"": 177}], ""download_size"": 1587074331, ""dataset_size"": 1595648828.0}, {""config_name"": ""rus_Cyrl"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 937479552.0, ""num_examples"": 733}, {""name"": ""validation"", ""num_bytes"": 119059292.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 285964850.0, ""num_examples"": 173}], ""download_size"": 1320374803, ""dataset_size"": 1342503694.0}, {""config_name"": ""slk_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 690086197.0, ""num_examples"": 628}, {""name"": ""validation"", ""num_bytes"": 120987120.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 299231287.0, ""num_examples"": 169}], ""download_size"": 1088431291, ""dataset_size"": 1110304604.0}, {""config_name"": ""slv_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 910836873.0, ""num_examples"": 704}, {""name"": ""validation"", ""num_bytes"": 105291567.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 251449782.0, ""num_examples"": 174}], ""download_size"": 1243394087, ""dataset_size"": 1267578222.0}, {""config_name"": ""sna_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1110133395.0, ""num_examples"": 689}, {""name"": ""test"", ""num_bytes"": 445118730.0, ""num_examples"": 176}, {""name"": ""validation"", ""num_bytes"": 170022414.0, ""num_examples"": 71}], ""download_size"": 1686849697, ""dataset_size"": 1725274539.0}, {""config_name"": ""snd_Arab"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1291698615.0, ""num_examples"": 749}, {""name"": ""validation"", ""num_bytes"": 145074769.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 379409498.0, ""num_examples"": 177}], ""download_size"": 1814212764, ""dataset_size"": 1816182882.0}, {""config_name"": ""som_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1536544214.0, ""num_examples"": 746}, {""name"": ""validation"", ""num_bytes"": 166072722.0, ""num_examples"": 70}, {""name"": ""test"", ""num_bytes"": 450228170.0, ""num_examples"": 177}], ""download_size"": 2114947059, ""dataset_size"": 2152845106.0}, {""config_name"": ""spa_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""validation"", ""num_bytes"": 148994823.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 365613179.0, ""num_examples"": 177}, {""name"": ""train"", ""num_bytes"": 827138506.0, ""num_examples"": 676}], ""download_size"": 1311850951, ""dataset_size"": 1341746508.0}, {""config_name"": ""srp_Cyrl"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1227301685.0, ""num_examples"": 730}, {""name"": ""validation"", ""num_bytes"": 89523997.0, ""num_examples"": 63}, {""name"": ""test"", ""num_bytes"": 246805416.0, ""num_examples"": 164}], ""download_size"": 1555922233, ""dataset_size"": 1563631098.0}, {""config_name"": ""swe_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 955198106.0, ""num_examples"": 686}, {""name"": ""validation"", ""num_bytes"": 111263173.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 265392664.0, ""num_examples"": 168}], ""download_size"": 1276165655, ""dataset_size"": 1331853943.0}, {""config_name"": ""swh_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1575032236.0, ""num_examples"": 745}, {""name"": ""validation"", ""num_bytes"": 89978234.0, ""num_examples"": 65}, {""name"": ""test"", ""num_bytes"": 214908159.0, ""num_examples"": 154}], ""download_size"": 1871495254, ""dataset_size"": 1879918629.0}, {""config_name"": ""tam_Taml"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1012440645.0, ""num_examples"": 693}, {""name"": ""validation"", ""num_bytes"": 143768511.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 245308874.0, ""num_examples"": 169}], ""download_size"": 1391470321, ""dataset_size"": 1401518030.0}, {""config_name"": ""tel_Telu"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 930917723.0, ""num_examples"": 658}, {""name"": ""validation"", ""num_bytes"": 93943473.0, ""num_examples"": 66}, {""name"": ""test"", ""num_bytes"": 171925062.0, ""num_examples"": 153}], ""download_size"": 1184754231, ""dataset_size"": 1196786258.0}, {""config_name"": ""tgk_Cyrl"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1016396657.0, ""num_examples"": 680}, {""name"": ""validation"", ""num_bytes"": 104367919.0, ""num_examples"": 69}, {""name"": ""test"", ""num_bytes"": 291493556.0, ""num_examples"": 163}], ""download_size"": 1377337730, ""dataset_size"": 1412258132.0}, {""config_name"": ""tgl_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 902994682.0, ""num_examples"": 604}, {""name"": ""validation"", ""num_bytes"": 219686509.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 551553192.0, ""num_examples"": 176}], ""download_size"": 1663149178, ""dataset_size"": 1674234383.0}, {""config_name"": ""tha_Thai"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 980135962.0, ""num_examples"": 710}, {""name"": ""validation"", ""num_bytes"": 162467332.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 406974484.0, ""num_examples"": 176}], ""download_size"": 1542445400, ""dataset_size"": 1549577778.0}, {""config_name"": ""tur_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 944011748.0, ""num_examples"": 692}, {""name"": ""validation"", ""num_bytes"": 124523218.0, ""num_examples"": 67}, {""name"": ""test"", ""num_bytes"": 297991664.0, ""num_examples"": 164}], ""download_size"": 1350130541, ""dataset_size"": 1366526630.0}, {""config_name"": ""ukr_Cyrl"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1048224078.0, ""num_examples"": 732}, {""name"": ""validation"", ""num_bytes"": 111149706.0, ""num_examples"": 67}, {""name"": ""test"", ""num_bytes"": 259797654.0, ""num_examples"": 164}], ""download_size"": 1392703995, ""dataset_size"": 1419171438.0}, {""config_name"": ""umb_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1091341178.0, ""num_examples"": 473}, {""name"": ""validation"", ""num_bytes"": 85473293.0, ""num_examples"": 39}, {""name"": ""test"", ""num_bytes"": 270947610.0, ""num_examples"": 108}], ""download_size"": 1437512568, ""dataset_size"": 1447762081.0}, {""config_name"": ""urd_Arab"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 826013912.0, ""num_examples"": 636}, {""name"": ""validation"", ""num_bytes"": 85561681.0, ""num_examples"": 65}, {""name"": ""test"", ""num_bytes"": 100881890.0, ""num_examples"": 120}], ""download_size"": 994627663, ""dataset_size"": 1012457483.0}, {""config_name"": ""uzn_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1164650128.0, ""num_examples"": 734}, {""name"": ""validation"", ""num_bytes"": 129797222.0, ""num_examples"": 69}, {""name"": ""test"", ""num_bytes"": 329525580.0, ""num_examples"": 175}], ""download_size"": 1595253953, ""dataset_size"": 1623972930.0}, {""config_name"": ""vie_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1047994786.0, ""num_examples"": 737}, {""name"": ""validation"", ""num_bytes"": 129736494.0, ""num_examples"": 70}, {""name"": ""test"", ""num_bytes"": 350270337.0, ""num_examples"": 176}], ""download_size"": 1516592431, ""dataset_size"": 1528001617.0}, {""config_name"": ""wol_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 990326354.0, ""num_examples"": 643}, {""name"": ""validation"", ""num_bytes"": 78434391.0, ""num_examples"": 52}, {""name"": ""test"", ""num_bytes"": 210576385.0, ""num_examples"": 123}], ""download_size"": 1178479659, ""dataset_size"": 1279337130.0}, {""config_name"": ""xho_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1551460398.0, ""num_examples"": 756}, {""name"": ""validation"", ""num_bytes"": 171791181.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 440037468.0, ""num_examples"": 177}], ""download_size"": 2117855982, ""dataset_size"": 2163289047.0}, {""config_name"": ""yor_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1150630919.0, ""num_examples"": 686}, {""name"": ""validation"", ""num_bytes"": 196405974.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 438420901.0, ""num_examples"": 172}], ""download_size"": 1783974678, ""dataset_size"": 1785457794.0}, {""config_name"": ""zho_Hans"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1142150085.0, ""num_examples"": 751}, {""name"": ""validation"", ""num_bytes"": 137384393.0, ""num_examples"": 71}, {""name"": ""test"", ""num_bytes"": 363570798.0, ""num_examples"": 176}], ""download_size"": 1620354318, ""dataset_size"": 1643105276.0}, {""config_name"": ""zho_Hant"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 854618903.0, ""num_examples"": 624}, {""name"": ""validation"", ""num_bytes"": 125089728.0, ""num_examples"": 70}, {""name"": ""test"", ""num_bytes"": 304504543.0, ""num_examples"": 172}], ""download_size"": 1280993945, ""dataset_size"": 1284213174.0}, {""config_name"": ""zsm_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1108735035.0, ""num_examples"": 713}, {""name"": ""validation"", ""num_bytes"": 101489819.0, ""num_examples"": 67}, {""name"": ""test"", ""num_bytes"": 267098586.0, ""num_examples"": 171}], ""download_size"": 1468618966, ""dataset_size"": 1477323440.0}, {""config_name"": ""zul_Latn"", ""features"": [{""name"": ""sentence"", ""dtype"": ""string""}, {""name"": ""URL"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int32""}, {""name"": ""domain"", ""dtype"": ""string""}, {""name"": ""topic"", ""dtype"": ""string""}, {""name"": ""has_image"", ""dtype"": ""int32""}, {""name"": ""has_hyperlink"", ""dtype"": ""int32""}, {""name"": ""fleurs_id"", ""dtype"": ""int32""}, {""name"": ""filename"", ""sequence"": ""string""}, {""name"": ""raw_transcription"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""num_samples"", ""sequence"": ""int64""}, {""name"": ""speaker_id"", ""sequence"": ""int64""}, {""name"": ""gender"", ""sequence"": ""string""}, {""name"": ""whisper_asr"", ""sequence"": ""string""}, {""name"": ""whisper_asr_cer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_wer"", ""sequence"": ""float64""}, {""name"": ""whisper_asr_translation"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr"", ""sequence"": ""string""}, {""name"": ""seamlessm4t_asr_cer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_wer"", ""sequence"": ""float64""}, {""name"": ""seamlessm4t_asr_translation"", ""sequence"": ""string""}, {""name"": ""index_id"", ""dtype"": ""int64""}, {""name"": ""category"", ""dtype"": {""class_label"": {""names"": {""0"": ""science/technology"", ""1"": ""travel"", ""2"": ""politics"", ""3"": ""sports"", ""4"": ""health"", ""5"": ""entertainment"", ""6"": ""geography""}}}}, {""name"": ""text"", ""dtype"": ""string""}, {""name"": ""audio"", ""sequence"": {""audio"": {""sampling_rate"": 16000}}}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1645680235.0, ""num_examples"": 739}, {""name"": ""validation"", ""num_bytes"": 165746159.0, ""num_examples"": 69}, {""name"": ""test"", ""num_bytes"": 449851598.0, ""num_examples"": 175}], ""download_size"": 2219566462, ""dataset_size"": 2261277992.0}], ""configs"": [{""config_name"": ""afr_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/afr_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/afr_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/afr_Latn/test-*""}]}, {""config_name"": ""amh_Ethi"", ""data_files"": [{""split"": ""train"", ""path"": ""data/amh_Ethi/train-*""}, {""split"": ""validation"", ""path"": ""data/amh_Ethi/validation-*""}, {""split"": ""test"", ""path"": ""data/amh_Ethi/test-*""}]}, {""config_name"": ""arb_Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""data/arb_Arab/train-*""}, {""split"": ""validation"", ""path"": ""data/arb_Arab/validation-*""}, {""split"": ""test"", ""path"": ""data/arb_Arab/test-*""}]}, {""config_name"": ""asm_Beng"", ""data_files"": [{""split"": ""train"", ""path"": ""data/asm_Beng/train-*""}, {""split"": ""validation"", ""path"": ""data/asm_Beng/validation-*""}, {""split"": ""test"", ""path"": ""data/asm_Beng/test-*""}]}, {""config_name"": ""ast_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ast_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/ast_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/ast_Latn/test-*""}]}, {""config_name"": ""azj_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/azj_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/azj_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/azj_Latn/test-*""}]}, {""config_name"": ""bel_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/bel_Cyrl/train-*""}, {""split"": ""validation"", ""path"": ""data/bel_Cyrl/validation-*""}, {""split"": ""test"", ""path"": ""data/bel_Cyrl/test-*""}]}, {""config_name"": ""ben_Beng"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ben_Beng/train-*""}, {""split"": ""validation"", ""path"": ""data/ben_Beng/validation-*""}, {""split"": ""test"", ""path"": ""data/ben_Beng/test-*""}]}, {""config_name"": ""bos_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/bos_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/bos_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/bos_Latn/test-*""}]}, {""config_name"": ""bul_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/bul_Cyrl/train-*""}, {""split"": ""validation"", ""path"": ""data/bul_Cyrl/validation-*""}, {""split"": ""test"", ""path"": ""data/bul_Cyrl/test-*""}]}, {""config_name"": ""cat_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/cat_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/cat_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/cat_Latn/test-*""}]}, {""config_name"": ""ceb_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ceb_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/ceb_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/ceb_Latn/test-*""}]}, {""config_name"": ""ces_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ces_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/ces_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/ces_Latn/test-*""}]}, {""config_name"": ""ckb_Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ckb_Arab/train-*""}, {""split"": ""validation"", ""path"": ""data/ckb_Arab/validation-*""}, {""split"": ""test"", ""path"": ""data/ckb_Arab/test-*""}]}, {""config_name"": ""cym_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/cym_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/cym_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/cym_Latn/test-*""}]}, {""config_name"": ""dan_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/dan_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/dan_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/dan_Latn/test-*""}]}, {""config_name"": ""deu_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/deu_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/deu_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/deu_Latn/test-*""}]}, {""config_name"": ""ell_Grek"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ell_Grek/train-*""}, {""split"": ""validation"", ""path"": ""data/ell_Grek/validation-*""}, {""split"": ""test"", ""path"": ""data/ell_Grek/test-*""}]}, {""config_name"": ""eng_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/eng_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/eng_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/eng_Latn/test-*""}]}, {""config_name"": ""est_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/est_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/est_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/est_Latn/test-*""}]}, {""config_name"": ""fin_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/fin_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/fin_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/fin_Latn/test-*""}]}, {""config_name"": ""fra_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/fra_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/fra_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/fra_Latn/test-*""}]}, {""config_name"": ""fuv_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/fuv_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/fuv_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/fuv_Latn/test-*""}]}, {""config_name"": ""gaz_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/gaz_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/gaz_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/gaz_Latn/test-*""}]}, {""config_name"": ""gle_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/gle_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/gle_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/gle_Latn/test-*""}]}, {""config_name"": ""glg_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/glg_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/glg_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/glg_Latn/test-*""}]}, {""config_name"": ""guj_Gujr"", ""data_files"": [{""split"": ""train"", ""path"": ""data/guj_Gujr/train-*""}, {""split"": ""validation"", ""path"": ""data/guj_Gujr/validation-*""}, {""split"": ""test"", ""path"": ""data/guj_Gujr/test-*""}]}, {""config_name"": ""hau_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/hau_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/hau_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/hau_Latn/test-*""}]}, {""config_name"": ""heb_Hebr"", ""data_files"": [{""split"": ""train"", ""path"": ""data/heb_Hebr/train-*""}, {""split"": ""validation"", ""path"": ""data/heb_Hebr/validation-*""}, {""split"": ""test"", ""path"": ""data/heb_Hebr/test-*""}]}, {""config_name"": ""hin_Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""data/hin_Deva/train-*""}, {""split"": ""validation"", ""path"": ""data/hin_Deva/validation-*""}, {""split"": ""test"", ""path"": ""data/hin_Deva/test-*""}]}, {""config_name"": ""hrv_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/hrv_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/hrv_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/hrv_Latn/test-*""}]}, {""config_name"": ""hun_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/hun_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/hun_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/hun_Latn/test-*""}]}, {""config_name"": ""hye_Armn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/hye_Armn/train-*""}, {""split"": ""validation"", ""path"": ""data/hye_Armn/validation-*""}, {""split"": ""test"", ""path"": ""data/hye_Armn/test-*""}]}, {""config_name"": ""ibo_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ibo_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/ibo_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/ibo_Latn/test-*""}]}, {""config_name"": ""ind_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ind_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/ind_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/ind_Latn/test-*""}]}, {""config_name"": ""isl_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/isl_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/isl_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/isl_Latn/test-*""}]}, {""config_name"": ""ita_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ita_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/ita_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/ita_Latn/test-*""}]}, {""config_name"": ""jav_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/jav_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/jav_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/jav_Latn/test-*""}]}, {""config_name"": ""jpn_Jpan"", ""data_files"": [{""split"": ""train"", ""path"": ""data/jpn_Jpan/train-*""}, {""split"": ""validation"", ""path"": ""data/jpn_Jpan/validation-*""}, {""split"": ""test"", ""path"": ""data/jpn_Jpan/test-*""}]}, {""config_name"": ""kam_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/kam_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/kam_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/kam_Latn/test-*""}]}, {""config_name"": ""kan_Knda"", ""data_files"": [{""split"": ""train"", ""path"": ""data/kan_Knda/train-*""}, {""split"": ""validation"", ""path"": ""data/kan_Knda/validation-*""}, {""split"": ""test"", ""path"": ""data/kan_Knda/test-*""}]}, {""config_name"": ""kat_Geor"", ""data_files"": [{""split"": ""train"", ""path"": ""data/kat_Geor/train-*""}, {""split"": ""validation"", ""path"": ""data/kat_Geor/validation-*""}, {""split"": ""test"", ""path"": ""data/kat_Geor/test-*""}]}, {""config_name"": ""kaz_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/kaz_Cyrl/train-*""}, {""split"": ""validation"", ""path"": ""data/kaz_Cyrl/validation-*""}, {""split"": ""test"", ""path"": ""data/kaz_Cyrl/test-*""}]}, {""config_name"": ""kea_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/kea_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/kea_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/kea_Latn/test-*""}]}, {""config_name"": ""khk_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/khk_Cyrl/train-*""}, {""split"": ""validation"", ""path"": ""data/khk_Cyrl/validation-*""}, {""split"": ""test"", ""path"": ""data/khk_Cyrl/test-*""}]}, {""config_name"": ""khm_Khmr"", ""data_files"": [{""split"": ""train"", ""path"": ""data/khm_Khmr/train-*""}, {""split"": ""validation"", ""path"": ""data/khm_Khmr/validation-*""}, {""split"": ""test"", ""path"": ""data/khm_Khmr/test-*""}]}, {""config_name"": ""kir_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/kir_Cyrl/train-*""}, {""split"": ""validation"", ""path"": ""data/kir_Cyrl/validation-*""}, {""split"": ""test"", ""path"": ""data/kir_Cyrl/test-*""}]}, {""config_name"": ""kor_Hang"", ""data_files"": [{""split"": ""train"", ""path"": ""data/kor_Hang/train-*""}, {""split"": ""validation"", ""path"": ""data/kor_Hang/validation-*""}, {""split"": ""test"", ""path"": ""data/kor_Hang/test-*""}]}, {""config_name"": ""lao_Laoo"", ""data_files"": [{""split"": ""train"", ""path"": ""data/lao_Laoo/train-*""}, {""split"": ""validation"", ""path"": ""data/lao_Laoo/validation-*""}, {""split"": ""test"", ""path"": ""data/lao_Laoo/test-*""}]}, {""config_name"": ""lin_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/lin_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/lin_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/lin_Latn/test-*""}]}, {""config_name"": ""lit_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/lit_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/lit_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/lit_Latn/test-*""}]}, {""config_name"": ""ltz_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ltz_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/ltz_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/ltz_Latn/test-*""}]}, {""config_name"": ""lug_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/lug_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/lug_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/lug_Latn/test-*""}]}, {""config_name"": ""luo_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/luo_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/luo_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/luo_Latn/test-*""}]}, {""config_name"": ""lvs_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/lvs_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/lvs_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/lvs_Latn/test-*""}]}, {""config_name"": ""mal_Mlym"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mal_Mlym/train-*""}, {""split"": ""validation"", ""path"": ""data/mal_Mlym/validation-*""}, {""split"": ""test"", ""path"": ""data/mal_Mlym/test-*""}]}, {""config_name"": ""mar_Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mar_Deva/train-*""}, {""split"": ""validation"", ""path"": ""data/mar_Deva/validation-*""}, {""split"": ""test"", ""path"": ""data/mar_Deva/test-*""}]}, {""config_name"": ""mkd_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mkd_Cyrl/train-*""}, {""split"": ""validation"", ""path"": ""data/mkd_Cyrl/validation-*""}, {""split"": ""test"", ""path"": ""data/mkd_Cyrl/test-*""}]}, {""config_name"": ""mlt_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mlt_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/mlt_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/mlt_Latn/test-*""}]}, {""config_name"": ""mri_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mri_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/mri_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/mri_Latn/test-*""}]}, {""config_name"": ""mya_Mymr"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mya_Mymr/train-*""}, {""split"": ""validation"", ""path"": ""data/mya_Mymr/validation-*""}, {""split"": ""test"", ""path"": ""data/mya_Mymr/test-*""}]}, {""config_name"": ""nld_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/nld_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/nld_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/nld_Latn/test-*""}]}, {""config_name"": ""nob_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/nob_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/nob_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/nob_Latn/test-*""}]}, {""config_name"": ""npi_Deva"", ""data_files"": [{""split"": ""train"", ""path"": ""data/npi_Deva/train-*""}, {""split"": ""validation"", ""path"": ""data/npi_Deva/validation-*""}, {""split"": ""test"", ""path"": ""data/npi_Deva/test-*""}]}, {""config_name"": ""nso_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/nso_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/nso_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/nso_Latn/test-*""}]}, {""config_name"": ""nya_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/nya_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/nya_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/nya_Latn/test-*""}]}, {""config_name"": ""oci_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/oci_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/oci_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/oci_Latn/test-*""}]}, {""config_name"": ""ory_Orya"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ory_Orya/train-*""}, {""split"": ""validation"", ""path"": ""data/ory_Orya/validation-*""}, {""split"": ""test"", ""path"": ""data/ory_Orya/test-*""}]}, {""config_name"": ""pan_Guru"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pan_Guru/train-*""}, {""split"": ""validation"", ""path"": ""data/pan_Guru/validation-*""}, {""split"": ""test"", ""path"": ""data/pan_Guru/test-*""}]}, {""config_name"": ""pbt_Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pbt_Arab/train-*""}, {""split"": ""validation"", ""path"": ""data/pbt_Arab/validation-*""}, {""split"": ""test"", ""path"": ""data/pbt_Arab/test-*""}]}, {""config_name"": ""pes_Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pes_Arab/train-*""}, {""split"": ""validation"", ""path"": ""data/pes_Arab/validation-*""}, {""split"": ""test"", ""path"": ""data/pes_Arab/test-*""}]}, {""config_name"": ""pol_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pol_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/pol_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/pol_Latn/test-*""}]}, {""config_name"": ""por_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/por_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/por_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/por_Latn/test-*""}]}, {""config_name"": ""ron_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ron_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/ron_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/ron_Latn/test-*""}]}, {""config_name"": ""rus_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/rus_Cyrl/train-*""}, {""split"": ""validation"", ""path"": ""data/rus_Cyrl/validation-*""}, {""split"": ""test"", ""path"": ""data/rus_Cyrl/test-*""}]}, {""config_name"": ""slk_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/slk_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/slk_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/slk_Latn/test-*""}]}, {""config_name"": ""slv_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/slv_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/slv_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/slv_Latn/test-*""}]}, {""config_name"": ""sna_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/sna_Latn/train-*""}, {""split"": ""test"", ""path"": ""data/sna_Latn/test-*""}, {""split"": ""validation"", ""path"": ""data/sna_Latn/validation-*""}]}, {""config_name"": ""snd_Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""data/snd_Arab/train-*""}, {""split"": ""validation"", ""path"": ""data/snd_Arab/validation-*""}, {""split"": ""test"", ""path"": ""data/snd_Arab/test-*""}]}, {""config_name"": ""som_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/som_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/som_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/som_Latn/test-*""}]}, {""config_name"": ""spa_Latn"", ""data_files"": [{""split"": ""validation"", ""path"": ""data/spa_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/spa_Latn/test-*""}, {""split"": ""train"", ""path"": ""data/spa_Latn/train-*""}]}, {""config_name"": ""srp_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/srp_Cyrl/train-*""}, {""split"": ""validation"", ""path"": ""data/srp_Cyrl/validation-*""}, {""split"": ""test"", ""path"": ""data/srp_Cyrl/test-*""}]}, {""config_name"": ""swe_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/swe_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/swe_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/swe_Latn/test-*""}]}, {""config_name"": ""swh_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/swh_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/swh_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/swh_Latn/test-*""}]}, {""config_name"": ""tam_Taml"", ""data_files"": [{""split"": ""train"", ""path"": ""data/tam_Taml/train-*""}, {""split"": ""validation"", ""path"": ""data/tam_Taml/validation-*""}, {""split"": ""test"", ""path"": ""data/tam_Taml/test-*""}]}, {""config_name"": ""tel_Telu"", ""data_files"": [{""split"": ""train"", ""path"": ""data/tel_Telu/train-*""}, {""split"": ""validation"", ""path"": ""data/tel_Telu/validation-*""}, {""split"": ""test"", ""path"": ""data/tel_Telu/test-*""}]}, {""config_name"": ""tgk_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/tgk_Cyrl/train-*""}, {""split"": ""validation"", ""path"": ""data/tgk_Cyrl/validation-*""}, {""split"": ""test"", ""path"": ""data/tgk_Cyrl/test-*""}]}, {""config_name"": ""tgl_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/tgl_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/tgl_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/tgl_Latn/test-*""}]}, {""config_name"": ""tha_Thai"", ""data_files"": [{""split"": ""train"", ""path"": ""data/tha_Thai/train-*""}, {""split"": ""validation"", ""path"": ""data/tha_Thai/validation-*""}, {""split"": ""test"", ""path"": ""data/tha_Thai/test-*""}]}, {""config_name"": ""tur_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/tur_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/tur_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/tur_Latn/test-*""}]}, {""config_name"": ""ukr_Cyrl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ukr_Cyrl/train-*""}, {""split"": ""validation"", ""path"": ""data/ukr_Cyrl/validation-*""}, {""split"": ""test"", ""path"": ""data/ukr_Cyrl/test-*""}]}, {""config_name"": ""umb_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/umb_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/umb_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/umb_Latn/test-*""}]}, {""config_name"": ""urd_Arab"", ""data_files"": [{""split"": ""train"", ""path"": ""data/urd_Arab/train-*""}, {""split"": ""validation"", ""path"": ""data/urd_Arab/validation-*""}, {""split"": ""test"", ""path"": ""data/urd_Arab/test-*""}]}, {""config_name"": ""uzn_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/uzn_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/uzn_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/uzn_Latn/test-*""}]}, {""config_name"": ""vie_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/vie_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/vie_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/vie_Latn/test-*""}]}, {""config_name"": ""wol_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/wol_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/wol_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/wol_Latn/test-*""}]}, {""config_name"": ""xho_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/xho_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/xho_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/xho_Latn/test-*""}]}, {""config_name"": ""yor_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/yor_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/yor_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/yor_Latn/test-*""}]}, {""config_name"": ""zho_Hans"", ""data_files"": [{""split"": ""train"", ""path"": ""data/zho_Hans/train-*""}, {""split"": ""validation"", ""path"": ""data/zho_Hans/validation-*""}, {""split"": ""test"", ""path"": ""data/zho_Hans/test-*""}]}, {""config_name"": ""zho_Hant"", ""data_files"": [{""split"": ""train"", ""path"": ""data/zho_Hant/train-*""}, {""split"": ""validation"", ""path"": ""data/zho_Hant/validation-*""}, {""split"": ""test"", ""path"": ""data/zho_Hant/test-*""}]}, {""config_name"": ""zsm_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/zsm_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/zsm_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/zsm_Latn/test-*""}]}, {""config_name"": ""zul_Latn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/zul_Latn/train-*""}, {""split"": ""validation"", ""path"": ""data/zul_Latn/validation-*""}, {""split"": ""test"", ""path"": ""data/zul_Latn/test-*""}]}]}","# SIB-Fleurs + +SIB-Fleurs is a dataset suitable to evaluate Multilingual Spoken Language Understanding. For each utterance in Fleurs, the task is to determine the topic the utterance belongs to. +The topics are: + +- Science/Technology +- Travel +- Politics +- Sports +- Health +- Entertainment +- Geography + +**Preliminary evaluations can be found at the bottom of the README. The preliminary results in full detail are available in ./results.csv***. + +## Dataset creation + +This dataset processes and merges all available multilingual data from the Fleurs, Flores, and [SIB-200](https://huggingface.co/datasets/Davlan/sib200) datasets. +It aligns the data of SIB to the available instances from the merged Fleurs-Flores data. + +The processing pipeline involves the following steps: +1. Remove all silent and noisy files from Fleurs. +2. Match Fleurs into Flores +3. Merge SIB into available Fleurs-Flores sentences. + +**This dataset retains the training, validation, and test splits of Fleurs and not SIB.** + +Full details and scripts to compile this dataset are available at: [https://github.com/fdschmidt93/fleurs-slu](https://github.com/fdschmidt93/fleurs-slu) + +## Usage + +### Example + +Each sentence in Flores has ~2.3 utterances in Fleurs, on average. That is why each instance comprises the aligned Fleurs data as `list[str, audio, ...]`. We track all available meta data (gender, speaker id) and further provide the ASR, ASR translations, CER, and WER for [SeamlessM4Tv2-Large](https://huggingface.co/facebook/seamless-m4t-v2-large) and [WhisperV3-Large](https://huggingface.co/openai/whisper-large-v3). + +```python +from datasets import load_dataset +eng_Latn = load_dataset(""wuenlp/sib-fleurs"", ""eng_Latn"", split=""test"") +eng_Latn[0] +# { +# 'sentence': 'As knowledge of Greek declined, the West found itself cut off from its Greek philosophical and scientific roots.', +# 'URL': 'https://en.wikibooks.org/wiki/Animal_Behavior/History', +# 'id': 596, +# 'domain': 'wikibooks', +# 'topic': 'Science/Animal Behavior', +# 'has_image': 0, +# 'has_hyperlink': 0, +# 'fleurs_id': 1895, +# 'filename': ['5358875111503056320.wav', '11200231708585274851.wav'], +# 'raw_transcription': 'As knowledge of Greek declined, the West found itself cut off from its Greek philosophical and scientific roots.', +# 'transcription': 'as knowledge of greek declined the west found itself cut off from its greek philosophical and scientific roots', +# 'num_samples': [120960, 162880], +# 'speaker_id': [5, 1], +# 'gender': ['FEMALE', 'MALE'], +# 'whisper_asr': ['As knowledge of Greek declined, the West found itself cut off from its Greek philosophical and scientific roots.', +# 'As knowledge of Greek declined, the West found itself cut off from its Greek philosophical and scientific roots.'], +# 'whisper_asr_cer': [0.0, 0.0], +# 'whisper_asr_wer': [0.0, 0.0], +# 'whisper_asr_translation': ['As knowledge of Greek declined, the West found itself cut off from its Greek philosophical and scientific roots.', +# 'As knowledge of Greek declined, the West found itself cut off from its Greek philosophical and scientific roots.'], +# 'seamlessm4t_asr': ['As knowledge of Greek declined, the West found itself cut off from its Greek philosophical and scientific roots.', +# 'As knowledge of Greek declined, the West found itself cut off from its Greek philosophical and scientific roots.'], +# 'seamlessm4t_asr_cer': [0.0, 0.0], +# 'seamlessm4t_asr_wer': [0.0, 0.0], +# 'seamlessm4t_asr_translation': ['As knowledge of Greek declined, the West found itself cut off from its Greek philosophical and scientific roots.', +# 'As knowledge of Greek declined, the West found itself cut off from its Greek philosophical and scientific roots.'], +# 'index_id': 1592, +# 'category': 0, +# 'text': 'As knowledge of Greek declined, the West found itself cut off from its Greek philosophical and scientific roots.', +# 'audio': [{'path': '5358875111503056320.wav', 'array': array([0.00000000e+00, 0.00000000e+00, 0.00000000e+00, ..., 5.72204590e-06, 7.56978989e-06, 5.42402267e-06]), 'sampling_rate': 16000}, +# {'path': '11200231708585274851.wav', 'array': array([0. , 0. , 0. , ..., 0.00011402, 0.00011003, 0.00012642]), 'sampling_rate': 16000}] +# } + +``` + +### Preprocessing + +Below is an example of how to use the provided functions for selecting utterances from the Sib-Fleurs dataset according to different criteria (e.g. minimizing or maximizing CER, or random selection). You can adjust the selection strategy (`strategy`) as needed. + +The mapping unpacks the below columns according the selection criterion provided by `strategy`. + +- 'filename' +- 'speaker_id' +- 'gender' +- 'whisper_asr' +- 'whisper_asr_cer' +- 'whisper_asr_wer' +- 'whisper_asr_translation' +- 'seamlessm4t_asr' +- 'seamlessm4t_asr_cer' +- 'seamlessm4t_asr_wer' +- 'seamlessm4t_asr_translation' + +**Note:** The selection logic takes into account which models are supported for a given language. If a language is unsupported by one of the models, the function automatically adjusts to only consider CERs from the supported models. + +#### Selection Strategy: + +You can choose how you want to select utterances: + +- `strategy=""best""`: Selects utterances with the minimal Character Error Rate (CER). +- `strategy=""worst""`: Selects utterances with the maximal CER. +- `strategy=""random""`: Selects utterances at random. + +```python +import random +from typing import Any, Callable + +import torch +from datasets import load_dataset +from transformers import PreTrainedTokenizerFast +from datasets.arrow_dataset import Dataset + + +def collect_cer( + examples: dict[str, list[list[float]]], models: list[str] +) -> list[list[float]]: + """""" + Calculate the average CER (Character Error Rate) for each index of each example across specified models. + + Args: + examples (dict[str, list[list[float]]]): Dictionary containing CER lists for different models. + models (list[str]): List of models to include in the calculation. + + Returns: + list[list[float]]: A list where each sublist contains the average CERs for each index of an example. + + Raises: + ValueError: If models have inconsistent numbers of examples or mismatched CER lengths. + """""" + model_cer_lists = [examples[model] for model in models if model in examples] + + if not model_cer_lists or not all( + len(cer_list) == len(model_cer_lists[0]) for cer_list in model_cer_lists + ): + raise ValueError(""All models must have the same number of examples."") + + averaged_cer = [] + for example_group in zip(*model_cer_lists): + if not all( + len(cer_list) == len(example_group[0]) for cer_list in example_group + ): + raise ValueError(""All CER lists for an example must have the same length."") + averaged_cer.append( + [sum(values) / len(values) for values in zip(*example_group)] + ) + + return averaged_cer + + +def select_audio_mapper( + language: str, + strategy: str = ""best"", +) -> Callable[[dict[str, list[Any]]], dict[str, list[Any]]]: + """""" + Create a mapping function for selecting audio data based on CER. + + Args: + language (str): Language code for filtering unsupported models. + strategy (str, optional): Selection strategy ('best', 'worst', or 'random'). Defaults to 'best'. + + Returns: + Callable[[dict[str, list[Any]]], dict[str, list[Any]]]: A function for mapping dataset examples. + + Raises: + ValueError: If an invalid selection strategy is provided. + """""" + + keys = { + ""audio"", + ""filename"", + ""gender"", + ""num_samples"", + ""seamlessm4t_asr"", + ""seamlessm4t_asr_cer"", + ""seamlessm4t_asr_translation"", + ""seamlessm4t_asr_wer"", + ""speaker_id"", + ""split"", + ""whisper_asr"", + ""whisper_asr_cer"", + ""whisper_asr_translation"", + ""whisper_asr_wer"", + } + + # Define unsupported languages for each model + seamless_unsupported = { + ""ast_Latn"", + ""hau_Latn"", + ""kam_Latn"", + ""kea_Latn"", + ""lin_Latn"", + ""mri_Latn"", + ""nso_Latn"", + ""oci_Latn"", + ""tgl_Latn"", + ""umb_Latn"", + ""wol_Latn"", + ""xho_Latn"", + } + whisper_unsupported = { + ""ast_Latn"", + ""ceb_Latn"", + ""ckb_Arab"", + ""fuv_Latn"", + ""gle_Latn"", + ""ibo_Latn"", + ""kam_Latn"", + ""kea_Latn"", + ""kir_Cyrl"", + ""lug_Latn"", + ""luo_Latn"", + ""nso_Latn"", + ""tgl_Latn"", + ""umb_Latn"", + ""wol_Latn"", + ""xho_Latn"", + ""zul_Latn"", + } + + # Define selection strategy + if strategy == ""best"": + select_func = lambda scores: min(range(len(scores)), key=lambda i: scores[i]) + elif strategy == ""worst"": + select_func = lambda scores: max(range(len(scores)), key=lambda i: scores[i]) + elif strategy == ""random"": + select_func = lambda scores: random.randint(0, len(scores) - 1) + else: + raise ValueError(""Invalid 'strategy'. Must be one of 'best', 'worst', or 'random'."") + + # Determine which models are supported for the given language + if language not in whisper_unsupported and language not in seamless_unsupported: + models = [""whisper_asr_cer"", ""seamlessm4t_asr_cer""] + elif language in whisper_unsupported: + models = [""seamlessm4t_asr_cer""] + elif language in seamless_unsupported: + models = [""whisper_asr_cer""] + else: + models = [""whisper_asr_cer"", ""seamlessm4t_asr_cer""] + + def map_fn(examples: dict[str, list[Any]]) -> dict[str, list[Any]]: + """""" + Map function to process dataset examples by selecting CER-based audio data. + + Args: + examples (dict[str, list[Any]]): Dataset examples. + + Returns: + dict[str, list[Any]]: Processed dataset examples. + """""" + cers = collect_cer(examples, models) + indices = [select_func(cer) for cer in cers] + + + for key, values in examples.items(): + if key not in keys: + examples[key] = values + else: + examples[key] = [values[idx] for idx, values in zip(indices, examples[key])] + return examples + + return map_fn + +eng_Latn = load_dataset(""wuenlp/sib"", ""eng_Latn"", split=""test"") +mapper = select_audio_mapper(""eng_Latn"") +dataset = eng_Latn.map(mapper, batched=True, batch_size=50) +``` + + +## ASR results + +We evaluate both speech encoders and LMs in a cascaded pipeline. In the cascaded setup, we first run Automatic Speech Recognition (ASR) using WhisperV3-Large and SeamlessM4Tv2-Large, then process the transcribed text with a language model (currently roberta-large). +We select the best checkpoint by maximizing performance on the English validation set. For evaluation, we test zero-shot cross-lingual transfer across all available languages. The avg column represents the average performance across all languages. For detailed per-language results, please refer to results.csv. + +| Model | Input | ASR Quality | Seed | LR | Batch Size | eng_Latn | avg | +|:-------------------------------------|:--------------------------------|:--------------|-------:|------:|-------------:|:-----------|:------| +| roberta-large | SeamlessM4Tv2 ASR Translation | best | 42 | 3e-5 | 32 | 92.7% | 81.5% | +| roberta-large | SeamlessM4Tv2 ASR Translation | best | 43 | 3e-5 | 32 | 91.0% | 80.4% | +| roberta-large | SeamlessM4Tv2 ASR Translation | worst | 44 | 2e-5 | 32 | 89.8% | 79.8% | +| roberta-large | SeamlessM4Tv2 ASR Translation | best | 43 | 2e-5 | 32 | 87.6% | 79.3% | +| roberta-large | SeamlessM4Tv2 ASR Translation | best | 42 | 2e-5 | 32 | 89.3% | 79.0% | +| roberta-large | SeamlessM4Tv2 ASR Translation | worst | 43 | 3e-5 | 32 | 89.8% | 78.5% | +| roberta-large | SeamlessM4Tv2 ASR Translation | best | 44 | 3e-5 | 32 | 88.1% | 78.5% | +| roberta-large | SeamlessM4Tv2 ASR Translation | worst | 42 | 2e-5 | 32 | 89.3% | 78.4% | +| roberta-large | SeamlessM4Tv2 ASR Translation | best | 44 | 2e-5 | 32 | 87.6% | 78.2% | +| roberta-large | SeamlessM4Tv2 ASR Translation | worst | 43 | 2e-5 | 32 | 85.3% | 77.9% | +| roberta-large | SeamlessM4Tv2 ASR Translation | worst | 44 | 3e-5 | 32 | 88.1% | 77.5% | +| roberta-large | SeamlessM4Tv2 ASR Translation | worst | 42 | 3e-5 | 32 | 87.6% | 76.3% | +| seamless-m4t-v2-large-speech-encoder | Speech | best | 42 | 3e-5 | 32 | 85.9% | 70.0% | +| roberta-large | WhisperV3-Large ASR Translation | best | 43 | 3e-5 | 32 | 90.4% | 69.1% | +| roberta-large | WhisperV3-Large ASR Translation | best | 42 | 3e-5 | 32 | 91.5% | 68.9% | +| roberta-large | WhisperV3-Large ASR Translation | best | 43 | 2e-5 | 32 | 88.7% | 68.5% | +| roberta-large | WhisperV3-Large ASR Translation | worst | 43 | 2e-5 | 32 | 91.0% | 68.1% | +| seamless-m4t-v2-large-speech-encoder | Speech | worst | 42 | 3e-5 | 32 | 85.9% | 67.8% | +| roberta-large | WhisperV3-Large ASR Translation | worst | 43 | 3e-5 | 32 | 90.4% | 67.6% | +| roberta-large | WhisperV3-Large ASR Translation | best | 44 | 3e-5 | 32 | 89.3% | 67.3% | +| roberta-large | WhisperV3-Large ASR Translation | best | 44 | 2e-5 | 32 | 86.4% | 67.1% | +| roberta-large | WhisperV3-Large ASR Translation | worst | 44 | 2e-5 | 32 | 90.4% | 66.8% | +| roberta-large | WhisperV3-Large ASR Translation | worst | 44 | 3e-5 | 32 | 89.3% | 66.8% | +| roberta-large | WhisperV3-Large ASR Translation | best | 42 | 2e-5 | 32 | 87.6% | 66.8% | +| roberta-large | WhisperV3-Large ASR Translation | worst | 42 | 3e-5 | 32 | 89.8% | 66.0% | +| roberta-large | WhisperV3-Large ASR Translation | worst | 42 | 2e-5 | 32 | 89.3% | 65.9% | +| roberta-large | SeamlessM4Tv2 ASR Translation | best | 42 | 1e-5 | 32 | 67.8% | 66.0% | +| roberta-large | SeamlessM4Tv2 ASR Translation | best | 43 | 1e-5 | 32 | 66.7% | 64.7% | +| roberta-large | SeamlessM4Tv2 ASR Translation | worst | 42 | 1e-5 | 32 | 65.0% | 64.5% | +| roberta-large | SeamlessM4Tv2 ASR Translation | best | 44 | 1e-5 | 32 | 66.7% | 64.0% | +| roberta-large | SeamlessM4Tv2 ASR Translation | worst | 43 | 1e-5 | 32 | 66.1% | 63.7% | +| roberta-large | WhisperV3-Large ASR Translation | best | 42 | 1e-5 | 32 | 80.2% | 62.6% | +| roberta-large | SeamlessM4Tv2 ASR Translation | worst | 44 | 1e-5 | 32 | 63.8% | 61.7% | +| roberta-large | WhisperV3-Large ASR Translation | best | 44 | 1e-5 | 32 | 76.3% | 60.8% | +| roberta-large | WhisperV3-Large ASR Translation | worst | 43 | 1e-5 | 32 | 78.0% | 60.7% | +| roberta-large | WhisperV3-Large ASR Translation | worst | 42 | 1e-5 | 32 | 76.3% | 59.5% | +| roberta-large | WhisperV3-Large ASR Translation | worst | 44 | 1e-5 | 32 | 74.0% | 58.2% | +| seamless-m4t-v2-large-speech-encoder | Speech | worst | 43 | 3e-5 | 32 | 83.1% | 57.4% | +| seamless-m4t-v2-large-speech-encoder | Speech | best | 43 | 3e-5 | 32 | 81.9% | 56.2% | +| seamless-m4t-v2-large-speech-encoder | Speech | best | 44 | 3e-5 | 32 | 83.6% | 55.6% | +| seamless-m4t-v2-large-speech-encoder | Speech | worst | 44 | 3e-5 | 32 | 81.4% | 55.5% | +| seamless-m4t-v2-large-speech-encoder | Speech | best | 42 | 2e-5 | 32 | 74.6% | 50.8% | +| whisper-large-v3-turbo | Speech | worst | 42 | 2e-5 | 32 | 81.4% | 50.4% | +| whisper-large-v3-turbo | Speech | best | 42 | 1e-5 | 32 | 80.2% | 48.7% | +| whisper-large-v3-turbo | Speech | worst | 42 | 1e-5 | 32 | 79.7% | 47.4% | +| whisper-large-v3-turbo | Speech | best | 44 | 2e-5 | 32 | 83.6% | 46.9% | +| whisper-large-v3-turbo | Speech | best | 42 | 2e-5 | 32 | 77.4% | 45.8% | +| whisper-large-v3-turbo | Speech | best | 43 | 1e-5 | 32 | 75.7% | 45.3% | +| seamless-m4t-v2-large-speech-encoder | Speech | best | 44 | 2e-5 | 32 | 78.5% | 44.0% | +| seamless-m4t-v2-large-speech-encoder | Speech | worst | 42 | 2e-5 | 32 | 66.1% | 43.5% | +| seamless-m4t-v2-large-speech-encoder | Speech | worst | 44 | 2e-5 | 32 | 74.0% | 43.1% | +| whisper-large-v3-turbo | Speech | worst | 42 | 3e-5 | 32 | 76.8% | 42.4% | +| seamless-m4t-v2-large-speech-encoder | Speech | best | 43 | 2e-5 | 32 | 76.3% | 41.9% | +| whisper-large-v3-turbo | Speech | worst | 43 | 3e-5 | 32 | 78.0% | 41.8% | +| whisper-large-v3-turbo | Speech | best | 43 | 2e-5 | 32 | 74.0% | 41.2% | +| seamless-m4t-v2-large-speech-encoder | Speech | worst | 43 | 2e-5 | 32 | 76.3% | 41.0% | +| whisper-large-v3-turbo | Speech | best | 42 | 3e-5 | 32 | 76.3% | 40.6% | +| whisper-large-v3-turbo | Speech | best | 43 | 3e-5 | 32 | 78.5% | 39.3% | +| whisper-large-v3-turbo | Speech | worst | 44 | 2e-5 | 32 | 80.8% | 39.3% | +| whisper-large-v3-turbo | Speech | worst | 43 | 2e-5 | 32 | 76.3% | 39.2% | +| whisper-large-v3-turbo | Speech | worst | 44 | 1e-5 | 32 | 75.7% | 38.8% | +| whisper-large-v3-turbo | Speech | best | 44 | 3e-5 | 32 | 76.8% | 37.1% | +| whisper-large-v3-turbo | Speech | worst | 44 | 3e-5 | 32 | 75.1% | 37.0% | +| whisper-large-v3-turbo | Speech | worst | 43 | 1e-5 | 32 | 73.4% | 35.8% | +| whisper-large-v3-turbo | Speech | best | 44 | 1e-5 | 32 | 76.8% | 34.5% | +| seamless-m4t-v2-large-speech-encoder | Speech | worst | 42 | 1e-5 | 32 | 33.9% | 26.5% | +| seamless-m4t-v2-large-speech-encoder | Speech | best | 42 | 1e-5 | 32 | 28.8% | 24.7% | +| seamless-m4t-v2-large-speech-encoder | Speech | best | 43 | 1e-5 | 32 | 18.6% | 18.4% | +| seamless-m4t-v2-large-speech-encoder | Speech | worst | 43 | 1e-5 | 32 | 18.6% | 18.1% | +| seamless-m4t-v2-large-speech-encoder | Speech | worst | 44 | 1e-5 | 32 | 16.9% | 13.0% | +| seamless-m4t-v2-large-speech-encoder | Speech | best | 44 | 1e-5 | 32 | 18.6% | 12.7% | + +# Statistics + +The table below denotes the number of available examples per split by language. The original SIB splits have been realigned to match the Fleurs splits. + +| Language | Train | Validation | Test | +|:---------|--------:|-------------:|-------:| +| `afr_Latn` | 406 | 86 | 95 | +| `amh_Ethi` | 752 | 54 | 149 | +| `arb_Arab` | 579 | 64 | 133 | +| `asm_Beng` | 730 | 71 | 176 | +| `ast_Latn` | 701 | 69 | 177 | +| `azj_Latn` | 712 | 71 | 174 | +| `bel_Cyrl` | 690 | 71 | 177 | +| `bul_Cyrl` | 749 | 70 | 176 | +| `ben_Beng` | 742 | 71 | 176 | +| `bos_Latn` | 746 | 71 | 177 | +| `cat_Latn` | 683 | 71 | 177 | +| `ceb_Latn` | 741 | 61 | 149 | +| `ckb_Arab` | 738 | 70 | 176 | +| `zho_Hans` | 751 | 71 | 176 | +| `ces_Latn` | 732 | 68 | 172 | +| `cym_Latn` | 739 | 71 | 177 | +| `dan_Latn` | 696 | 70 | 177 | +| `deu_Latn` | 736 | 69 | 175 | +| `ell_Grek` | 750 | 67 | 168 | +| `eng_Latn` | 738 | 71 | 177 | +| `spa_Latn` | 676 | 71 | 177 | +| `est_Latn` | 700 | 71 | 176 | +| `pes_Arab` | 692 | 66 | 165 | +| `fin_Latn` | 735 | 71 | 175 | +| `tgl_Latn` | 604 | 71 | 176 | +| `fra_Latn` | 753 | 65 | 164 | +| `gle_Latn` | 731 | 71 | 176 | +| `glg_Latn` | 660 | 71 | 174 | +| `guj_Gujr` | 752 | 71 | 177 | +| `hau_Latn` | 753 | 70 | 166 | +| `heb_Hebr` | 754 | 70 | 175 | +| `hin_Deva` | 653 | 60 | 132 | +| `hrv_Latn` | 756 | 71 | 176 | +| `hun_Latn` | 750 | 71 | 177 | +| `hye_Armn` | 741 | 71 | 177 | +| `ind_Latn` | 728 | 69 | 167 | +| `ibo_Latn` | 737 | 71 | 177 | +| `isl_Latn` | 381 | 18 | 23 | +| `ita_Latn` | 743 | 69 | 175 | +| `jpn_Jpan` | 662 | 62 | 164 | +| `jav_Latn` | 740 | 67 | 171 | +| `kat_Geor` | 557 | 69 | 177 | +| `kam_Latn` | 752 | 69 | 179 | +| `kea_Latn` | 725 | 71 | 175 | +| `kaz_Cyrl` | 749 | 70 | 176 | +| `khm_Khmr` | 588 | 69 | 168 | +| `kan_Knda` | 660 | 70 | 174 | +| `kor_Hang` | 669 | 61 | 141 | +| `kir_Cyrl` | 729 | 71 | 177 | +| `ltz_Latn` | 703 | 71 | 176 | +| `lug_Latn` | 691 | 70 | 173 | +| `lin_Latn` | 755 | 59 | 139 | +| `lao_Laoo` | 591 | 54 | 132 | +| `lit_Latn` | 730 | 71 | 178 | +| `luo_Latn` | 698 | 39 | 98 | +| `lvs_Latn` | 634 | 69 | 174 | +| `mri_Latn` | 749 | 71 | 176 | +| `mkd_Cyrl` | 680 | 71 | 177 | +| `mal_Mlym` | 723 | 68 | 174 | +| `khk_Cyrl` | 743 | 71 | 177 | +| `mar_Deva` | 749 | 71 | 177 | +| `zsm_Latn` | 713 | 67 | 171 | +| `mlt_Latn` | 731 | 71 | 176 | +| `mya_Mymr` | 746 | 71 | 175 | +| `nob_Latn` | 723 | 51 | 127 | +| `npi_Deva` | 754 | 70 | 175 | +| `nld_Latn` | 729 | 58 | 123 | +| `nso_Latn` | 633 | 70 | 169 | +| `nya_Latn` | 720 | 68 | 169 | +| `oci_Latn` | 756 | 71 | 177 | +| `ory_Orya` | 442 | 71 | 168 | +| `pan_Guru` | 580 | 56 | 143 | +| `pol_Latn` | 723 | 68 | 165 | +| `pbt_Arab` | 701 | 55 | 144 | +| `por_Latn` | 728 | 70 | 177 | +| `ron_Latn` | 734 | 69 | 177 | +| `rus_Cyrl` | 733 | 71 | 173 | +| `snd_Arab` | 749 | 71 | 177 | +| `slk_Latn` | 628 | 71 | 169 | +| `slv_Latn` | 704 | 71 | 174 | +| `sna_Latn` | 689 | 71 | 176 | +| `som_Latn` | 746 | 70 | 177 | +| `srp_Cyrl` | 730 | 63 | 164 | +| `swe_Latn` | 686 | 71 | 168 | +| `swh_Latn` | 745 | 65 | 154 | +| `tam_Taml` | 693 | 71 | 169 | +| `tel_Telu` | 658 | 66 | 153 | +| `tgk_Cyrl` | 680 | 69 | 163 | +| `tha_Thai` | 710 | 71 | 176 | +| `tur_Latn` | 692 | 67 | 164 | +| `ukr_Cyrl` | 732 | 67 | 164 | +| `umb_Latn` | 473 | 39 | 108 | +| `urd_Arab` | 636 | 65 | 120 | +| `uzn_Latn` | 734 | 69 | 175 | +| `vie_Latn` | 737 | 70 | 176 | +| `wol_Latn` | 643 | 52 | 123 | +| `xho_Latn` | 756 | 71 | 177 | +| `yor_Latn` | 686 | 71 | 172 | +| `zho_Hant` | 624 | 70 | 172 | +| `zul_Latn` | 739 | 69 | 175 | +| `fuv_Latn` | 752 | 68 | 166 | +| `gaz_Latn` | 574 | 6 | 17 | + +# Citations + +If you are using this dataset, please cite the following papers. Our paper is forthcoming and will be added as soon as possible. + +``` +@misc{adelani2023sib200, + title={SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects}, + author={David Ifeoluwa Adelani and Hannah Liu and Xiaoyu Shen and Nikita Vassilyev and Jesujoba O. Alabi and Yanke Mao and Haonan Gao and Annie En-Shiun Lee}, + year={2023}, + eprint={2309.07445}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +```" +ontocord/CulturaY,"{""configs"": [{""config_name"": ""af"", ""data_files"": ""af/*.jsonl.zst""}, {""config_name"": ""ar"", ""data_files"": ""ar/*.jsonl.zst""}, {""config_name"": ""az"", ""data_files"": ""az/*.jsonl.zst""}, {""config_name"": ""be"", ""data_files"": ""be/*.jsonl.zst""}, {""config_name"": ""bg"", ""data_files"": ""bg/*.jsonl.zst""}, {""config_name"": ""bn"", ""data_files"": ""bn/*.jsonl.zst""}, {""config_name"": ""ca"", ""data_files"": ""ca/*.jsonl.zst""}, {""config_name"": ""cs"", ""data_files"": ""cs/*.jsonl.zst""}, {""config_name"": ""cy"", ""data_files"": ""cy/*.jsonl.zst""}, {""config_name"": ""da"", ""data_files"": ""da/*.jsonl.zst""}, {""config_name"": ""de"", ""data_files"": ""de/*.jsonl.zst""}, {""config_name"": ""el"", ""data_files"": ""el/*.jsonl.zst""}, {""config_name"": ""en"", ""data_files"": ""en/*.jsonl.zst""}, {""config_name"": ""eo"", ""data_files"": ""eo/*.jsonl.zst""}, {""config_name"": ""es"", ""data_files"": ""es/*.jsonl.zst""}, {""config_name"": ""et"", ""data_files"": ""et/*.jsonl.zst""}, {""config_name"": ""eu"", ""data_files"": ""eu/*.jsonl.zst""}, {""config_name"": ""fa"", ""data_files"": ""fa/*.jsonl.zst""}, {""config_name"": ""fi"", ""data_files"": ""fi/*.jsonl.zst""}, {""config_name"": ""fr"", ""data_files"": ""fr/*.jsonl.zst""}, {""config_name"": ""ga"", ""data_files"": ""ga/*.jsonl.zst""}, {""config_name"": ""gl"", ""data_files"": ""gl/*.jsonl.zst""}, {""config_name"": ""gu"", ""data_files"": ""gu/*.jsonl.zst""}, {""config_name"": ""hbs"", ""data_files"": ""hbs/*.jsonl.zst""}, {""config_name"": ""he"", ""data_files"": ""he/*.jsonl.zst""}, {""config_name"": ""hi"", ""data_files"": ""hi/*.jsonl.zst""}, {""config_name"": ""hu"", ""data_files"": ""hu/*.jsonl.zst""}, {""config_name"": ""hy"", ""data_files"": ""hy/*.jsonl.zst""}, {""config_name"": ""id"", ""data_files"": ""id/*.jsonl.zst""}, {""config_name"": ""is"", ""data_files"": ""is/*.jsonl.zst""}, {""config_name"": ""it"", ""data_files"": ""it/*.jsonl.zst""}, {""config_name"": ""ja"", ""data_files"": ""ja/*.jsonl.zst""}, {""config_name"": ""ka"", ""data_files"": ""ka/*.jsonl.zst""}, {""config_name"": ""kk"", ""data_files"": ""kk/*.jsonl.zst""}, {""config_name"": ""kn"", ""data_files"": ""kn/*.jsonl.zst""}, {""config_name"": ""ko"", ""data_files"": ""ko/*.jsonl.zst""}, {""config_name"": ""ky"", ""data_files"": ""ky/*.jsonl.zst""}, {""config_name"": ""la"", ""data_files"": ""la/*.jsonl.zst""}, {""config_name"": ""lt"", ""data_files"": ""lt/*.jsonl.zst""}, {""config_name"": ""lv"", ""data_files"": ""lv/*.jsonl.zst""}, {""config_name"": ""mk"", ""data_files"": ""mk/*.jsonl.zst""}, {""config_name"": ""ml"", ""data_files"": ""ml/*.jsonl.zst""}, {""config_name"": ""mn"", ""data_files"": ""mn/*.jsonl.zst""}, {""config_name"": ""mr"", ""data_files"": ""mr/*.jsonl.zst""}, {""config_name"": ""ms"", ""data_files"": ""ms/*.jsonl.zst""}, {""config_name"": ""mt"", ""data_files"": ""mt/*.jsonl.zst""}, {""config_name"": ""my"", ""data_files"": ""my/*.jsonl.zst""}, {""config_name"": ""nb"", ""data_files"": ""nb/*.jsonl.zst""}, {""config_name"": ""ne"", ""data_files"": ""ne/*.jsonl.zst""}, {""config_name"": ""nl"", ""data_files"": ""nl/*.jsonl.zst""}, {""config_name"": ""nn"", ""data_files"": ""nn/*.jsonl.zst""}, {""config_name"": ""pa"", ""data_files"": ""pa/*.jsonl.zst""}, {""config_name"": ""pl"", ""data_files"": ""pl/*.jsonl.zst""}, {""config_name"": ""ps"", ""data_files"": ""ps/*.jsonl.zst""}, {""config_name"": ""pt"", ""data_files"": ""pt/*.jsonl.zst""}, {""config_name"": ""ro"", ""data_files"": ""ro/*.jsonl.zst""}, {""config_name"": ""ru"", ""data_files"": ""ru/*.jsonl.zst""}, {""config_name"": ""si"", ""data_files"": ""si/*.jsonl.zst""}, {""config_name"": ""sk"", ""data_files"": ""sk/*.jsonl.zst""}, {""config_name"": ""sl"", ""data_files"": ""sl/*.jsonl.zst""}, {""config_name"": ""so"", ""data_files"": ""so/*.jsonl.zst""}, {""config_name"": ""sq"", ""data_files"": ""sq/*.jsonl.zst""}, {""config_name"": ""sv"", ""data_files"": ""sv/*.jsonl.zst""}, {""config_name"": ""sw"", ""data_files"": ""sw/*.jsonl.zst""}, {""config_name"": ""ta"", ""data_files"": ""ta/*.jsonl.zst""}, {""config_name"": ""te"", ""data_files"": ""te/*.jsonl.zst""}, {""config_name"": ""th"", ""data_files"": ""th/*.jsonl.zst""}, {""config_name"": ""tl"", ""data_files"": ""tl/*.jsonl.zst""}, {""config_name"": ""tr"", ""data_files"": ""tr/*.jsonl.zst""}, {""config_name"": ""tt"", ""data_files"": ""tt/*.jsonl.zst""}, {""config_name"": ""uk"", ""data_files"": ""uk/*.jsonl.zst""}, {""config_name"": ""ur"", ""data_files"": ""ur/*.jsonl.zst""}, {""config_name"": ""uz"", ""data_files"": ""uz/*.jsonl.zst""}, {""config_name"": ""vi"", ""data_files"": ""vi/*.jsonl.zst""}, {""config_name"": ""zh"", ""data_files"": ""zh/*.jsonl.zst""}], ""pretty_name"": ""CulturaY"", ""annotations_creators"": [""no-annotation""], ""language_creators"": [""found""], ""language"": [""af"", ""ar"", ""az"", ""be"", ""bg"", ""bn"", ""ca"", ""cs"", ""cy"", ""da"", ""de"", ""el"", ""en"", ""eo"", ""es"", ""et"", ""eu"", ""fa"", ""fi"", ""fr"", ""ga"", ""gl"", ""gu"", ""hbs"", ""he"", ""hi"", ""hu"", ""hy"", ""id"", ""is"", ""it"", ""ja"", ""ka"", ""kk"", ""kn"", ""ko"", ""ky"", ""la"", ""lt"", ""lv"", ""mk"", ""ml"", ""mn"", ""mr"", ""ms"", ""mt"", ""my"", ""nb"", ""ne"", ""nl"", ""nn"", ""pa"", ""pl"", ""ps"", ""pt"", ""ro"", ""ru"", ""si"", ""sk"", ""sl"", ""so"", ""sq"", ""sv"", ""sw"", ""ta"", ""te"", ""th"", ""tl"", ""tr"", ""tt"", ""uk"", ""ur"", ""uz"", ""vi"", ""zh""], ""multilinguality"": [""multilingual""], ""size_categories"": [""n<1K"", ""1K>> from datasets import load_dataset + +>>> ds = load_dataset(""nlpai-lab/kullm-v2"", split=""train"") +>>> ds +DatasetDict({ + train: Dataset({ + features: ['id', 'instruction', 'input', 'output'], + num_rows: 152630 + }) +}) +``` + +```python +>>> ds[0] +{'id': 'alpaca_{idx}', + 'instruction': '3원색이란 무엇인가요?', + 'input': '', + 'output': '세 가지 기본 색은 빨강, 파랑, 노랑입니다. 이 색은 다른 색을 혼합하여 만들 수 없고 다른 모든 색은 다양한 비율로 조합하여 만들 수 있기 때문에 원색이라고 부릅니다. 빛에 사용되는 첨가제 색상 시스템에서 원색은 빨강, 녹색, 파랑(RGB)입니다.'} +```" +adithya7/xlel_wd_dictionary,"{""annotations_creators"": [""found""], ""language_creators"": [""found""], ""language"": [""af"", ""ar"", ""be"", ""bg"", ""bn"", ""ca"", ""cs"", ""da"", ""de"", ""el"", ""en"", ""es"", ""fa"", ""fi"", ""fr"", ""he"", ""hi"", ""hu"", ""id"", ""it"", ""ja"", ""ko"", ""ml"", ""mr"", ""ms"", ""nl"", ""no"", ""pl"", ""pt"", ""ro"", ""ru"", ""si"", ""sk"", ""sl"", ""sr"", ""sv"", ""sw"", ""ta"", ""te"", ""th"", ""tr"", ""uk"", ""vi"", ""zh""], ""license"": [""cc-by-4.0""], ""multilinguality"": [""multilingual""], ""pretty_name"": ""XLEL-WD is a multilingual event linking dataset. This supplementary dataset contains a dictionary of event items from Wikidata. The descriptions for Wikidata event items are taken from the corresponding multilingual Wikipedia articles."", ""size_categories"": [""10K +- **Repository:** +- **Paper:** +- **Leaderboard:** N/A +- **Point of Contact:** Adithya Pratapa + +### Dataset Summary + +XLEL-WD is a multilingual event linking dataset. This supplementary dataset contains a dictionary of event items from Wikidata. The descriptions for Wikidata event items are taken from the corresponding multilingual Wikipedia articles. + +### Supported Tasks and Leaderboards + +This dictionary can be used as a part of the event linking task. + +### Languages + +This dataset contains text from 44 languages. The language names and their ISO 639-1 codes are listed below. For details on the dataset distribution for each language, refer to the original paper. + +| Language | Code | Language | Code | Language | Code | Language | Code | +| -------- | ---- | -------- | ---- | -------- | ---- | -------- | ---- | +| Afrikaans | af | Arabic | ar | Belarusian | be | Bulgarian | bg | +| Bengali | bn | Catalan | ca | Czech | cs | Danish | da | +| German | de | Greek | el | English | en | Spanish | es | +| Persian | fa | Finnish | fi | French | fr | Hebrew | he | +| Hindi | hi | Hungarian | hu | Indonesian | id | Italian | it | +| Japanese | ja | Korean | ko | Malayalam | ml | Marathi | mr | +| Malay | ms | Dutch | nl | Norwegian | no | Polish | pl | +| Portuguese | pt | Romanian | ro | Russian | ru | Sinhala | si | +| Slovak | sk | Slovene | sl | Serbian | sr | Swedish | sv | +| Swahili | sw | Tamil | ta | Telugu | te | Thai | th | +| Turkish | tr | Ukrainian | uk | Vietnamese | vi | Chinese | zh | + +## Dataset Structure + +### Data Instances + +Each instance in the `label_dict.jsonl` file follows the below template, + +```json +{ + ""label_id"": ""830917"", + ""label_title"": ""2010 European Aquatics Championships"", + ""label_desc"": ""The 2010 European Aquatics Championships were held from 4–15 August 2010 in Budapest and Balatonfüred, Hungary. It was the fourth time that the city of Budapest hosts this event after 1926, 1958 and 2006. Events in swimming, diving, synchronised swimming (synchro) and open water swimming were scheduled."", + ""label_lang"": ""en"" +} +``` + +### Data Fields + +| Field | Meaning | +| ----- | ------- | +| `label_id` | Wikidata ID | +| `label_title` | Title for the event, as collected from the corresponding Wikipedia article | +| `label_desc` | Description for the event, as collected from the corresponding Wikipedia article | +| `label_lang` | language used for the title and description | + +### Data Splits + +This dictionary has a single split, `dictionary`. It contains 10947 event items from Wikidata and a total of 114834 text descriptions collected from multilingual Wikipedia articles. + +## Dataset Creation + +### Curation Rationale + +This datasets helps address the task of event linking. KB linking is extensively studied for entities, but its unclear if the same methodologies can be extended for linking mentions to events from KB. Event items are collected from Wikidata. + +### Source Data + +#### Initial Data Collection and Normalization + +A Wikidata item is considered a potential event if it has spatial and temporal properties. The final event set is collected after post-processing for quality control. + +#### Who are the source language producers? + +The titles and descriptions for the events are written by Wikipedia contributors. + +### Annotations + +#### Annotation process + +This dataset was automatically compiled from Wikidata. It was post-processed to improve data quality. + +#### Who are the annotators? + +Wikidata and Wikipedia contributors. + +### Personal and Sensitive Information + +[More Information Needed] + +## Considerations for Using the Data + +### Social Impact of Dataset + +[More Information Needed] + +### Discussion of Biases + +[More Information Needed] + +### Other Known Limitations + +This dictionary primarily contains eventive nouns from Wikidata. It does not include other event items from Wikidata such as disease outbreak (Q3241045), military offensive (Q2001676), war (Q198), etc., + +## Additional Information + +### Dataset Curators + +The dataset was curated by Adithya Pratapa, Rishubh Gupta and Teruko Mitamura. The code for collecting the dataset is available at [Github:xlel-wd](https://github.com/adithya7/xlel-wd). + +### Licensing Information + +XLEL-WD dataset is released under [CC-BY-4.0 license](https://creativecommons.org/licenses/by/4.0/). + +### Citation Information + +```bib +@article{pratapa-etal-2022-multilingual, + title = {Multilingual Event Linking to Wikidata}, + author = {Pratapa, Adithya and Gupta, Rishubh and Mitamura, Teruko}, + publisher = {arXiv}, + year = {2022}, + url = {https://arxiv.org/abs/2204.06535}, +} +``` + +### Contributions + +Thanks to [@adithya7](https://github.com/adithya7) for adding this dataset." +stanford-oval/ccnews,"{""language"": [""multilingual"", ""af"", ""am"", ""ar"", ""as"", ""az"", ""be"", ""bg"", ""bn"", ""br"", ""bs"", ""ca"", ""cs"", ""cy"", ""da"", ""de"", ""el"", ""en"", ""eo"", ""es"", ""et"", ""eu"", ""fa"", ""fi"", ""fr"", ""fy"", ""ga"", ""gd"", ""gl"", ""gu"", ""ha"", ""he"", ""hi"", ""hr"", ""hu"", ""hy"", ""id"", ""is"", ""it"", ""ja"", ""jv"", ""ka"", ""kk"", ""km"", ""kn"", ""ko"", ""ku"", ""ky"", ""la"", ""lo"", ""lt"", ""lv"", ""mg"", ""mk"", ""ml"", ""mn"", ""mr"", ""ms"", ""my"", ""ne"", ""nl"", ""no"", ""om"", ""or"", ""pa"", ""pl"", ""ps"", ""pt"", ""ro"", ""ru"", ""sa"", ""sd"", ""si"", ""sk"", ""sl"", ""so"", ""sq"", ""sr"", ""su"", ""sv"", ""sw"", ""ta"", ""te"", ""th"", ""tl"", ""tr"", ""ug"", ""uk"", ""ur"", ""uz"", ""vi"", ""xh"", ""yi"", ""zh""], ""pretty_name"": ""All of Common Crawl News, 100+ languages, preprocessed and cleaned"", ""task_categories"": [""text-classification"", ""question-answering"", ""text-generation"", ""text2text-generation""], ""size_categories"": [""100M + +## Dataset Descritpion + +Korean Hate Speech Evaluation Datasets : trained with [BEEP!](https://huggingface.co/datasets/kor_hate) and evaluate with [APEACH](https://github.com/jason9693/APEACH) + +- **Repository: [Korean HateSpeech Evaluation Dataset](https://github.com/jason9693/APEACH)** +- **Paper: [APEACH: Attacking Pejorative Expressions with Analysis on Crowd-Generated Hate Speech Evaluation Datasets](https://arxiv.org/abs/2202.12459)** +- **Point of Contact: [Kichang Yang](ykcha9@gmail.com)** + +### Languages + +ko-KR + +## Dataset Structure + +### Data Instances + +A sample from this dataset looks as follows: + +```json +{'text': ['(현재 호텔주인 심정) 아18 난 마른하늘에 날벼락맞고 호텔망하게생겼는데 누군 계속 추모받네....', + '....한국적인 미인의 대표적인 분...너무나 곱고아름다운모습...그모습뒤의 슬픔을 미처 알지못했네요ㅠ'], + 'class': ['Spoiled', 'Default']} +``` + +### Dataset Fields + +The dataset has the following fields (also called ""features""): + +```json +{ + ""text"": ""Value(dtype='string', id=None)"", + ""class"": ""ClassLabel(num_classes=2, names=['Default', 'Spoiled'], id=None)"" +} +``` + +### Dataset Splits + +This dataset is split into a train and validation split. The split sizes are as follow: + +| Split name | Num samples | +| ------------ | ------------------- | +| train (binarized BEEP!) | 7896 | +| valid (APEACH) | 3770 | + +## Citation +``` +@article{yang2022apeach, + title={APEACH: Attacking Pejorative Expressions with Analysis on Crowd-Generated Hate Speech Evaluation Datasets}, + author={Yang, Kichang and Jang, Wonjun and Cho, Won Ik}, + journal={arXiv preprint arXiv:2202.12459}, + year={2022} +} +```" +xu-song/cc100-samples,"{""annotations_creators"": [""no-annotation""], ""language_creators"": [""found""], ""datasets"": [""cc100""], ""language"": [""af"", ""am"", ""ar"", ""as"", ""az"", ""be"", ""bg"", ""bn"", ""br"", ""bs"", ""ca"", ""cs"", ""cy"", ""da"", ""de"", ""el"", ""en"", ""eo"", ""es"", ""et"", ""eu"", ""fa"", ""ff"", ""fi"", ""fr"", ""fy"", ""ga"", ""gd"", ""gl"", ""gn"", ""gu"", ""ha"", ""he"", ""hi"", ""hr"", ""ht"", ""hu"", ""hy"", ""id"", ""ig"", ""is"", ""it"", ""ja"", ""jv"", ""ka"", ""kk"", ""km"", ""kn"", ""ko"", ""ku"", ""ky"", ""la"", ""lg"", ""li"", ""ln"", ""lo"", ""lt"", ""lv"", ""mg"", ""mk"", ""ml"", ""mn"", ""mr"", ""ms"", ""my"", ""ne"", ""nl"", ""no"", ""ns"", ""om"", ""or"", ""pa"", ""pl"", ""ps"", ""pt"", ""qu"", ""rm"", ""ro"", ""ru"", ""sa"", ""sc"", ""sd"", ""si"", ""sk"", ""sl"", ""so"", ""sq"", ""sr"", ""ss"", ""su"", ""sv"", ""sw"", ""ta"", ""te"", ""th"", ""tl"", ""tn"", ""tr"", ""ug"", ""uk"", ""ur"", ""uz"", ""vi"", ""wo"", ""xh"", ""yi"", ""yo"", ""zh"", ""zu""], ""language_bcp47"": [""bn-Latn"", ""hi-Latn"", ""my-x-zawgyi"", ""ta-Latn"", ""te-Latn"", ""ur-Latn"", ""zh-Hans"", ""zh-Hant""], ""license"": [""unknown""], ""multilinguality"": [""multilingual""], ""size_categories"": [""1K + +A dataset containing strings from projects hosted on [Weblate](https://hosted.weblate.org) and their translations into other languages. +Please consider [donating](https://weblate.org/en/donate/) or [contributing](https://weblate.org/en/contribute/) to Weblate if you find this dataset useful. + +To avoid rows with values like ""None"" and ""N/A"" being interpreted as missing values, pass the keep_default_na parameter like this: +``` +from datasets import load_dataset + +dataset = load_dataset(""ayymen/Weblate-Translations"", keep_default_na=False) +``` + +## Dataset Details + +### Dataset Description + + + + + +- **Curated by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** Each sentence pair in the dataset has a corresponding license in the ""license"" column. This license is the one specified in the component or project containing the sentence. + +### Dataset Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + +- Machine Translation +- Language Identification + +### Direct Use + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Dataset Structure + + + +[More Information Needed] + +## Dataset Creation + +### Curation Rationale + + + +[More Information Needed] + +### Source Data + + + +#### Data Collection and Processing + + + +- Sentence pairs with empty/missing elements were dropped. +- Identical pairs were dropped. +- Trailing whitespace was stripped. +- Rows were deduplicated based on all 3 columns including ""license"", on a config/subset/tsv file basis. Which means that a single config might contain two identical sentence pairs with different licenses. Or a different config/subset might contain the exact same row (most likely a different variant/dialect of the same language(s)). + +#### Who are the source data producers? + + + +[More Information Needed] + +### Annotations [optional] + + + +#### Annotation process + + + +[More Information Needed] + +#### Who are the annotators? + + + +Weblate users. + +#### Personal and Sensitive Information + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations. + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Dataset Card Authors [optional] + +[More Information Needed] + +## Dataset Card Contact + +[More Information Needed]" +heegyu/namuwiki-extracted,"{""license"": ""cc-by-nc-sa-2.0"", ""language"": [""ko""], ""language_creators"": [""other""], ""multilinguality"": [""monolingual""], ""size_categories"": [""100K +- 571308rows +- download size: 2.19GB + +## 주의사항 +namu-wiki-extractor를 이용하여 전처리, 추가로 아래 전처리를 수행했습니다 +1. 헤더 제거 `== 개요 ==` +1. 테이블 제거 +1. `[age(1997-01-01)]` 는 전처리 시점 기준으로 적용(2022년 10월 2일) +1. `[math(a / b + c)]` 는 제거하지 않음. +1. math 마크다운이 각주 내에 있을 경우, 각주가 전처리되지 않은 문제 있음. + + +## Usage +```bash +pip install datasets +``` + +```python +from datasets import load_dataset +dataset = load_dataset(""heegyu/namuwiki-extracted"") +print(dataset[""train""][0]) +``` +``` +{ +'title': '!!아앗!!', +'text': '！！ああっと！！ ▲신 세계수의 미궁 2에서 뜬 !!아앗!! 세계수의 미궁 시리즈에 전통으로 등장하는 대사. 2편부터 등장했으며 훌륭한 사망 플래그의 예시이다. 세계수의 모험가들이 탐험하는 던전인 수해의 구석구석에는 채취/벌채/채굴 포인트가 있으며, 이를 위한 채집 스킬에 ...', +'contributors': '110.46.34.123,kirby10,max0243,218.54.117.149,ruby3141,121.165.63.239,iviyuki,1.229.200.194,anatra95,kiri47,175.127.134.2,nickchaos71,chkong1998,kiwitree2,namubot,huwieblusnow', +'namespace': '' +} +```" +bongsoo/kowiki20220620,"{""language"": [""ko""], ""license"": ""apache-2.0""}",-kowiki202206 1줄 말뭉치 +wikimedia/wikisource,"{""language"": [""ar"", ""as"", ""az"", ""ban"", ""be"", ""bg"", ""bn"", ""br"", ""bs"", ""ca"", ""cs"", ""cy"", ""da"", ""de"", ""el"", ""en"", ""eo"", ""es"", ""et"", ""eu"", ""fa"", ""fi"", ""fo"", ""fr"", ""gl"", ""gu"", ""he"", ""hi"", ""hr"", ""hu"", ""hy"", ""id"", ""is"", ""it"", ""ja"", ""jv"", ""kn"", ""ko"", ""la"", ""li"", ""lij"", ""lt"", ""mk"", ""ml"", ""mr"", ""nan"", ""nap"", ""nl"", ""no"", ""or"", ""pa"", ""pl"", ""pms"", ""pt"", ""ro"", ""ru"", ""sa"", ""sah"", ""sk"", ""sl"", ""sr"", ""su"", ""sv"", ""ta"", ""te"", ""th"", ""tr"", ""uk"", ""vec"", ""vi"", ""wa"", ""yi"", ""zh""], ""license"": [""cc-by-sa-3.0"", ""gfdl""], ""size_categories"": [""n<1K"", ""1K + +This is a dataset containing strings from various Mozilla projects on Mozilla's [Pontoon](https://pontoon.mozilla.org) localization platform and their translations into more than 200 languages. +Source strings are in English. + +To avoid rows with values like ""None"" and ""N/A"" being interpreted as missing values, pass the keep_default_na parameter like this: +``` +from datasets import load_dataset + +dataset = load_dataset(""ayymen/Pontoon-Translations"", keep_default_na=False) +``` + +## Dataset Details + +### Dataset Description + + + + + +- **Curated by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** Per [Pontoons's terms](https://pontoon.mozilla.org/terms/) ""Translations are governed by the [Mozilla Public License 2.0](https://www.mozilla.org/en-US/MPL/2.0/), or another license or set of licenses acceptable to the Mozilla Foundation."" + +### Dataset Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + +- Machine Translation +- Language Identification + +### Direct Use + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Dataset Structure + + + +[More Information Needed] + +## Dataset Creation + +### Curation Rationale + + + +[More Information Needed] + +### Source Data + + + +#### Data Collection and Processing + + + +- Sentence pairs with empty/missing elements were dropped. +- Identical pairs were dropped. +- Rows where the english string does not contain any letters were dropped. +- Leading and trailing whitespace was stripped. +- Rows were deduplicated. + +#### Who are the source data producers? + + + +[More Information Needed] + +### Annotations [optional] + + + +#### Annotation process + + + +[More Information Needed] + +#### Who are the annotators? + + + +Pontoon users. + +#### Personal and Sensitive Information + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations. + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Dataset Card Authors [optional] + +[More Information Needed] + +## Dataset Card Contact + +[More Information Needed]" +openai/MMMLU,"{""task_categories"": [""question-answering""], ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""test"", ""path"": ""test/*.csv""}]}, {""config_name"": ""AR_XY"", ""data_files"": [{""split"": ""test"", ""path"": ""test/mmlu_AR-XY.csv""}]}, {""config_name"": ""BN_BD"", ""data_files"": [{""split"": ""test"", ""path"": ""test/mmlu_BN-BD.csv""}]}, {""config_name"": ""DE_DE"", ""data_files"": [{""split"": ""test"", ""path"": ""test/mmlu_DE-DE.csv""}]}, {""config_name"": ""ES_LA"", ""data_files"": [{""split"": ""test"", ""path"": ""test/mmlu_ES-LA.csv""}]}, {""config_name"": ""FR_FR"", ""data_files"": [{""split"": ""test"", ""path"": ""test/mmlu_FR-FR.csv""}]}, {""config_name"": ""HI_IN"", ""data_files"": [{""split"": ""test"", ""path"": ""test/mmlu_HI-IN.csv""}]}, {""config_name"": ""ID_ID"", ""data_files"": [{""split"": ""test"", ""path"": ""test/mmlu_ID-ID.csv""}]}, {""config_name"": ""IT_IT"", ""data_files"": [{""split"": ""test"", ""path"": ""test/mmlu_IT-IT.csv""}]}, {""config_name"": ""JA_JP"", ""data_files"": [{""split"": ""test"", ""path"": ""test/mmlu_JA-JP.csv""}]}, {""config_name"": ""KO_KR"", ""data_files"": [{""split"": ""test"", ""path"": ""test/mmlu_KO-KR.csv""}]}, {""config_name"": ""PT_BR"", ""data_files"": [{""split"": ""test"", ""path"": ""test/mmlu_PT-BR.csv""}]}, {""config_name"": ""SW_KE"", ""data_files"": [{""split"": ""test"", ""path"": ""test/mmlu_SW-KE.csv""}]}, {""config_name"": ""YO_NG"", ""data_files"": [{""split"": ""test"", ""path"": ""test/mmlu_YO-NG.csv""}]}, {""config_name"": ""ZH_CN"", ""data_files"": [{""split"": ""test"", ""path"": ""test/mmlu_ZH-CN.csv""}]}], ""language"": [""ar"", ""bn"", ""de"", ""es"", ""fr"", ""hi"", ""id"", ""it"", ""ja"", ""ko"", ""pt"", ""sw"", ""yo"", ""zh""], ""license"": ""mit""}","# Multilingual Massive Multitask Language Understanding (MMMLU) + +The MMLU is a widely recognized benchmark of general knowledge attained by AI models. It covers a broad range of topics from 57 different categories, covering elementary-level knowledge up to advanced professional subjects like law, physics, history, and computer science. + +We translated the MMLU’s test set into 14 languages using professional human translators. Relying on human translators for this evaluation increases confidence in the accuracy of the translations, especially for low-resource languages like Yoruba. We are publishing the professional human translations and the code we use to run the evaluations. + +This effort reflects our commitment to improving the multilingual capabilities of AI models, ensuring they perform accurately across languages, particularly for underrepresented communities. By prioritizing high-quality translations, we aim to make AI technology more inclusive and effective for users worldwide. + +## Locales + +MMMLU contains the MMLU test set translated into the following locales: +* AR_XY (Arabic) +* BN_BD (Bengali) +* DE_DE (German) +* ES_LA (Spanish) +* FR_FR (French) +* HI_IN (Hindi) +* ID_ID (Indonesian) +* IT_IT (Italian) +* JA_JP (Japanese) +* KO_KR (Korean) +* PT_BR (Brazilian Portuguese) +* SW_KE (Swahili) +* YO_NG (Yoruba) +* ZH_CN (Simplified Chinese) + +## Sources + +Hendrycks, D., Burns, C., Kadavath, S., Arora, A., Basart, S., Tang, E., Song, D., & Steinhardt, J. (2021). [*Measuring Massive Multitask Language Understanding*](https://arxiv.org/abs/2009.03300). + +[OpenAI Simple Evals GitHub Repository](https://github.com/openai/simple-evals)" +sentence-transformers/parallel-sentences-opus-100,"{""annotations_creators"": [""no-annotation""], ""language_creators"": [""found""], ""language"": [""af"", ""am"", ""an"", ""ar"", ""as"", ""az"", ""be"", ""bg"", ""bn"", ""br"", ""bs"", ""ca"", ""cs"", ""cy"", ""da"", ""de"", ""dz"", ""el"", ""en"", ""eo"", ""es"", ""et"", ""eu"", ""fa"", ""fi"", ""fr"", ""fy"", ""ga"", ""gd"", ""gl"", ""gu"", ""ha"", ""he"", ""hi"", ""hr"", ""hu"", ""hy"", ""id"", ""ig"", ""is"", ""it"", ""ja"", ""ka"", ""kk"", ""km"", ""kn"", ""ko"", ""ku"", ""ky"", ""li"", ""lt"", ""lv"", ""mg"", ""mk"", ""ml"", ""mn"", ""mr"", ""ms"", ""mt"", ""my"", ""nb"", ""ne"", ""nl"", ""nn"", ""no"", ""oc"", ""or"", ""pa"", ""pl"", ""ps"", ""pt"", ""ro"", ""ru"", ""rw"", ""se"", ""sh"", ""si"", ""sk"", ""sl"", ""sq"", ""sr"", ""sv"", ""ta"", ""te"", ""tg"", ""th"", ""tk"", ""tr"", ""tt"", ""ug"", ""uk"", ""ur"", ""uz"", ""vi"", ""wa"", ""xh"", ""yi"", ""yo"", ""zh"", ""zu""], ""size_categories"": [""10M wc -l * + 6206 sharegpt_gpt4.jsonl # 清洗后的高质量gpt4日常问答数据集，大小：6K，主要是知识问答、编程题、推理计算，包括简体中文、繁体中文、英文、日文、韩文等多国语言多轮对话数据集。 + 58674 sharegpt_V3_format.jsonl # 原V3版sharegpt规范格式后的数据集，大小：58K，主要是日常问答，提问偏口语化，多国语言，多轮对话。 + 38535 sharegpt_zh_38K_format.jsonl # 中文gpt4日常问答数据集，大小：38K，主要是知识问答、翻译任务、求助、编程推理任务等偏口语提问，中文，多轮对话。 + 103415 total +``` + +#### Who are the annotators? +原作者。 + + +### Licensing Information + +same to sharegpt. + + + +### Contributions + +[shibing624](https://github.com/shibing624) add this dataset." +GEM/surface_realisation_st_2020,"{""annotations_creators"": [""none""], ""language_creators"": [""unknown""], ""language"": [""ar"", ""zh"", ""en"", ""fr"", ""hi"", ""id"", ""ja"", ""ko"", ""pt"", ""ru"", ""es""], ""license"": [""cc-by-2.5""], ""multilinguality"": [""unknown""], ""size_categories"": [""unknown""], ""source_datasets"": [""original""], ""task_categories"": [""table-to-text""], ""task_ids"": [], ""pretty_name"": ""surface_realisation_st_2020"", ""tags"": [""data-to-text""]}","# Dataset Card for GEM/surface_realisation_st_2020 + +## Dataset Description + +- **Homepage:** http://taln.upf.edu/pages/msr2020-ws/SRST.html#data +- **Repository:** https://sites.google.com/site/genchalrepository/surface-realisation/sr-20-multilingual +- **Paper:** https://aclanthology.org/2020.msr-1.1/ +- **Leaderboard:** N/A +- **Point of Contact:** Simon Mille + +### Link to Main Data Card + +You can find the main data card on the [GEM Website](https://gem-benchmark.com/data_cards/surface_realisation_st_2020). + +### Dataset Summary + +This dataset was used as part of the multilingual surface realization shared task in which a model gets full or partial universal dependency structures and has to reconstruct the natural language. This dataset support 11 languages. + +You can load the dataset via: +``` +import datasets +data = datasets.load_dataset('GEM/surface_realisation_st_2020') +``` +The data loader can be found [here](https://huggingface.co/datasets/GEM/surface_realisation_st_2020). + +#### website +[Website](http://taln.upf.edu/pages/msr2020-ws/SRST.html#data) + +#### paper +[ACL Anthology](https://aclanthology.org/2020.msr-1.1/) + +#### authors +Simon Mille (Pompeu Fabra University); Leo Wanner (Pompeu Fabra University); Anya Belz (Brighton University); Bernd Bohnet (Google Inc.); Thiago Castro Ferreira (Federal University of Minas Gerais); Yvette Graham (ADAPT/Trinity College Dublin) + +## Dataset Overview + +### Where to find the Data and its Documentation + +#### Webpage + + + +[Website](http://taln.upf.edu/pages/msr2020-ws/SRST.html#data) + +#### Download + + + +[Website](https://sites.google.com/site/genchalrepository/surface-realisation/sr-20-multilingual) + +#### Paper + + + +[ACL Anthology](https://aclanthology.org/2020.msr-1.1/) + +#### BibTex + + + +``` +@inproceedings{mille-etal-2020-third, + title = ""The Third Multilingual Surface Realisation Shared Task ({SR}{'}20): Overview and Evaluation Results"", + author = ""Mille, Simon and + Belz, Anya and + Bohnet, Bernd and + Castro Ferreira, Thiago and + Graham, Yvette and + Wanner, Leo"", + booktitle = ""Proceedings of the Third Workshop on Multilingual Surface Realisation"", + month = dec, + year = ""2020"", + address = ""Barcelona, Spain (Online)"", + publisher = ""Association for Computational Linguistics"", + url = ""https://aclanthology.org/2020.msr-1.1"", + pages = ""1--20"", + abstract = ""This paper presents results from the Third Shared Task on Multilingual Surface Realisation (SR{'}20) which was organised as part of the COLING{'}20 Workshop on Multilingual Surface Realisation. As in SR{'}18 and SR{'}19, the shared task comprised two tracks: (1) a Shallow Track where the inputs were full UD structures with word order information removed and tokens lemmatised; and (2) a Deep Track where additionally, functional words and morphological information were removed. Moreover, each track had two subtracks: (a) restricted-resource, where only the data provided or approved as part of a track could be used for training models, and (b) open-resource, where any data could be used. The Shallow Track was offered in 11 languages, whereas the Deep Track in 3 ones. Systems were evaluated using both automatic metrics and direct assessment by human evaluators in terms of Readability and Meaning Similarity to reference outputs. We present the evaluation results, along with descriptions of the SR{'}19 tracks, data and evaluation methods, as well as brief summaries of the participating systems. For full descriptions of the participating systems, please see the separate system reports elsewhere in this volume."", +} +``` + +#### Contact Name + + + + +Simon Mille + +#### Contact Email + + + +sfmille@gmail.com + +#### Has a Leaderboard? + + + +no + + +### Languages and Intended Use + +#### Multilingual? + + + + +yes + +#### Covered Dialects + + + +No multiple dialects. + +#### Covered Languages + + + + +`Arabic`, `Chinese`, `English`, `French`, `Hindi`, `Indonesian`, `Japanese`, `Korean`, `Portuguese`, `Russian`, `Spanish, Castilian` + +#### Whose Language? + + + +Unknown + +#### License + + + + +cc-by-2.5: Creative Commons Attribution 2.5 Generic + +#### Intended Use + + + +The dataset is intended to be used for training models to solve several NLG subtasks, such as function word introduction, morphological agreement resolution, word order determination and inflection generation. + +Comment about the license: the dataset has multiple licences, since each original dataset has their own type of licence. All datasets but one are CC-BY and subclasses of it, the other one is GPL (French Sequoia). + +#### Primary Task + + + +Data-to-Text + +#### Communicative Goal + + + + +The models are able to introduce surface features (syntax, morphology, topology) from more or less abstract inputs in different, the most abstract being predicate-argument structures. The datasets cover a large variety of domains (news, blogs, forums, wikipedia pages, etc.). + + +### Credit + +#### Curation Organization Type(s) + + + +`industry`, `academic` + +#### Curation Organization(s) + + + +Pompeu Fabra University, Google Inc., University of Brighton, Federal University of Minas Gerais, ADAPT/Trinity College Dublin + +#### Dataset Creators + + + +Simon Mille (Pompeu Fabra University); Leo Wanner (Pompeu Fabra University); Anya Belz (Brighton University); Bernd Bohnet (Google Inc.); Thiago Castro Ferreira (Federal University of Minas Gerais); Yvette Graham (ADAPT/Trinity College Dublin) + +#### Funding + + + +Mostly EU funds via H2020 projects + +#### Who added the Dataset to GEM? + + + +Simon Mille (Pompeu Fabra University) + + +### Dataset Structure + +#### Data Fields + + + +`input` (string): this field contains an input tree in CoNLL-U format; the CoNLL-U format is a one-word-per-line format with the following tab-separated 10 columns (see [here](http://universaldependencies.org/format.html)): [1] Position, [2] Lemma, [3] Wordform, [4] Part of Speech, [5] Fine-grained Part of Speech (if available), [6] Features (FEATS), [7] governor, [8] dependency relation, [9] additional dependency information, and [10] metadata. For the surface task, the input is a Universal Dependency tree of a given language in which the word order was scrambled and the surface forms removed (only lemmas are available); for the deep task, the input is a tree derived from the surface input, with predicate-argument relations between content words only (function words were removed) and without any morphological agreement information. + +`target_tokenized` (string): this field contains the target sentence to generate, in which every non-initial and non-final token is surrounded by two spaces. This output is usually used for automatic evaluations. + +`target` (string): this field contains the detokenised target sentence to generate. This output is usually used for human evaluations. + +`gem_id` (string): a unique ID. + +`sentence_id` (string): the original ID of a sentence in the UD dataset. + +#### Reason for Structure + + + +The structure of the input (CoNLL-U) was chosen according to the standards in parsing, and because the original UD datasets were provided in this format. + +#### How were labels chosen? + + + +The input labels for the surface track are the original labels in the UD treebanks; see [here](https://universaldependencies.org/u/dep/index.html) for the dependencies, [here](https://universaldependencies.org/u/feat/index.html) for the features, and [here](https://universaldependencies.org/u/pos/index.html) for the PoS tags. + +The input labels for the deep track are a subset of the PoS tags and features of the surface track, and for the relations, universal predicate-argument relations augmented with a few specific relations to capture coordinations and named entity relations for instance. + +#### Example Instance + + + +``` +{""input"": ""1\tGoogle\t_\tPROPN\tNNP\tNumber=Sing\t5\tnsubj\t_\t_\n2\t\t_\tPUNCT\t.\tlin=+1\t5\tpunct\t_\t_\n3\tinto\t_\tADP\tIN\t_\t6\tcase\t_\t_\n4\tif\t_\tSCONJ\tIN\t_\t5\tmark\t_\t_\n5\tmorph\t_\tVERB\tVBD\tMood=Ind|Tense=Past|VerbForm=Fin\t7\tadvcl\t_\t_\n6\tGoogleOS\t_\tPROPN\tNNP\tNumber=Sing\t5\tobl\t_\t_\n7\twhat\t_\tPRON\tWP\tPronType=Int\t0\troot\t_\t_"", ""target_tokenized"": ""What if Google Morphed Into GoogleOS ?"", ""target"": ""What if Google Morphed Into GoogleOS?"", ""gem_id"": ""GEM-surface_realisation_st_2020-T1-test-en_ewt-ud-test-0"", ""sentence_id"": """"} +``` + +#### Data Splits + + + +There are 119 splits in the dataset: + +- 29 training sets, which correspond to 20 UD datasets (11 languages), 9 of which have both surface and deep inputs (3 languages); +- 29 development set which correspond to the 29 training sets above; +- 29 test sets for the data described above; +- 4 out-of-domain test sets, 3 surface inputs and 1 deep one (3 languages for which PUD out-of-domain datasets were available); +- 9 automatically parsed in-domain test sets, 6 surface inputs and 3 deep inputs (6 languages for which good UD parsers were available); +- 9 automatically parsed out-of-domain test sets, 6 surface inputs and 3 deep inputs (6 languages for which we were able to create clean Wikipedia text and that had a good UD parser). + +#### Splitting Criteria + + + +Described above for more clarity. + +#### + + + +An outlier would usually be an input that corresponds to a very long sentence (e.g. 159 words in English, when the average number of words per sentence is around 25). + + + +## Dataset in GEM + +### Rationale for Inclusion in GEM + +#### Why is the Dataset in GEM? + + + +The datset includes languages from different families and some languages not often used in NLG (e.g. Arabic, Indonesian, Korean, Hindi). It proposes two tasks, which can be tackled both separately and in one shot, with different levels of difficulty: the most superficial task (T1) consits in ordering and inflecting some trees, and the deeper task (T2) includes extra tasks such as defining the syntactic structure and introducing function words and morphological agreement information. Both tasks can allow for developing modules for pipeline NLG architectures. T1 is rather straightforward to evaluate: BLEU works quite well for some languages since all the words are present in the input and few word orders only can be possible for a syntactic tree. But T2 is more challenging to evaluate, since more outputs are correct given one particular input. + +There is a large variety of sizes in the datasets, both clean and noisy data, parallel data in different languages, and many already available system outputs to use as baselines. + +#### Similar Datasets + + + +yes + +#### Unique Language Coverage + + + +yes + +#### Difference from other GEM datasets + + + +This is possibly the only dataset that starts the generation process from predicate-argument structures and from syntactic structures. It also has parallel datasets in a few languages (coming from the PUD parallel annotations). + +#### Ability that the Dataset measures + + + +Syntacticisation, functional word introduction, word order resolution, agreement resolution, morphological inflection + + +### GEM-Specific Curation + +#### Modificatied for GEM? + + + +no + +#### Additional Splits? + + + +no + + +### Getting Started with the Task + +#### Pointers to Resources + + + +[Website](http://taln.upf.edu/pages/msr2020-ws/SRST.html) + +#### Technical Terms + + + +Syntacticisation: prediction of the syntactic + + + +## Previous Results + +### Previous Results + +#### Measured Model Abilities + + + +Syntacticisation, functional word introduction, word order resolution, morphological agreement resolution, morphological inflection + +#### Metrics + + + +`BLEU`, `BERT-Score`, `Other: Other Metrics` + +#### Other Metrics + + + +NIST: n-gram similarity metric weighted in favour of less frequent n-grams which are taken to be more informative. + +Normalised edit distance (DIST): inverse, normalised, character-based string-edit distance that starts by computing the minimum number of character inserts, deletes and substitutions (all at cost 1) required to turn the system output into the (single) reference text. + +#### Proposed Evaluation + + + +BLEU, NIST, BERTScore and DIST simply aim at calculating in different ways the similarity between a predicted and a reference sentence. + +Two additional criteria have been used for human evaluation, Readability and Meaning SImilarity. The statement to be assessed in the Readability evaluation was: ""The text reads well and is free from grammatical errors and awkward constructions."". The corresponding statement in the Meaning Similarity evaluation, in which system outputs (‘the black text’) were compared to reference sentences (‘the gray text’), was: ""The meaning of the gray text is adequately expressed by the black text."" + + +#### Previous results available? + + + +yes + +#### Other Evaluation Approaches + + + +Same as above. + +#### Relevant Previous Results + + + +- [Fast and Accurate Non-Projective Dependency Tree Linearization](https://aclanthology.org/2020.acl-main.134/) +- [Shape of Synth to Come: Why We Should Use Synthetic Data for English Surface Realization](https://aclanthology.org/2020.acl-main.665/) + + + +## Dataset Curation + +### Original Curation + +#### Original Curation Rationale + + + +The datasets were created in the context of the Surface Realisation Shared Task series. + +#### Communicative Goal + + + +The dataset's objective was to allow for training systems to perform tasks related to surface realisation (introduction of function words, syntacticisation, resolution of morphological agreements, word order resolution, inflection generation. + +#### Sourced from Different Sources + + + +yes + +#### Source Details + + + +Each of the 20 used UD datasets comes from various sources, all listed on the individual page of each UD treeebank (https://universaldependencies.org/). + +Additional test sets were created for the task, and were obtained from Wikipedia pages for 6 languages. + + +### Language Data + +#### How was Language Data Obtained? + + + +`Found` + +#### Where was it found? + + + +`Multiple websites` + +#### Language Producers + + + +There are numerous sources of language in the multiple datasets. + +#### Topics Covered + + + +There is a large variety of topics in the multiple datasets. + +#### Data Validation + + + +not validated + +#### Data Preprocessing + + + +The text data was detokenised so as to create references for automatic evaluations (several languages don't use spaces to separate words, and running metrics like BLEU would not make sense without separating all the tokens in a sentence). + +#### Was Data Filtered? + + + +hybrid + +#### Filter Criteria + + + +For the Wikipedia test created for the shared task, extensive filtering was applied to achieve reasonably good text quality. Sentences that include special characters, contain unusual tokens (e.g. ISBN), or have unbalanced quotation marks or brackets were skipped. Furthermore, only sentences with more than 5 tokens and shorter than 50 tokens were selected. After the initial filtering, quite a few malformed sentences remained. In order to remove those, the sentences were scored with BERT and +only the top half scored sentences were kept. Finally, via manual inspection, patterns and expressions were identified to +further reduce the number of malformed sentences. + + +### Structured Annotations + +#### Additional Annotations? + + + + +none + +#### Annotation Service? + + + +no + + +### Consent + +#### Any Consent Policy? + + + +no + +#### Justification for Using the Data + + + +The Universal Dependency data had been previously used for shared tasks on parsing, so it made sense to reuse it for generation. + + +### Private Identifying Information (PII) + +#### Contains PII? + + + + +unlikely + +#### Any PII Identification? + + + +no identification + + +### Maintenance + +#### Any Maintenance Plan? + + + +no + + + +## Broader Social Context + +### Previous Work on the Social Impact of the Dataset + +#### Usage of Models based on the Data + + + +no + + +### Impact on Under-Served Communities + +#### Addresses needs of underserved Communities? + + + +yes + +#### Details on how Dataset Addresses the Needs + + + +Thanks to the original work of the UD dataset creators, the surface realisation dataset addresses a few languages which are possibly under-served in NLG: e.g. Arabic, Hindi, Indonesian, Korean. + + +### Discussion of Biases + +#### Any Documented Social Biases? + + + +no + +#### Are the Language Producers Representative of the Language? + + + +It is very likely that the distribution of language producers is not fully represented in the datasets of each language. + + + +## Considerations for Using the Data + +### PII Risks and Liability + +#### Potential PII Risk + + + +No risks foreseen. + + +### Licenses + +#### Copyright Restrictions on the Dataset + + + +`multiple licenses`, `open license - commercial use allowed` + +#### Copyright Restrictions on the Language Data + + + +`multiple licenses`, `open license - commercial use allowed` + + +### Known Technical Limitations + +#### Technical Limitations + + + +The deep track inputs (predicate-argument structures) are not of perfect quality, they were derived automatically from gold or predicted syntactic parses using handcrafted grammars. + +#### Unsuited Applications + + + +The datasets are probably not fitted to train tools to produce ""unusual"" languages (e.g. poetry, kid writing etc.). + +#### Discouraged Use Cases + + + +To be thought of :)" +royboy0416/ko-alpaca,"{""license"": ""cc-by-4.0"", ""task_categories"": [""text-generation""], ""language"": [""ko""]}","Testing purpose only. Do not redistribute. + +Original contents: [url] https://huggingface.co/datasets/tatsu-lab/alpaca + +Ko-alpaca: [url] https://github.com/Beomi/KoAlpaca/blob/main/ko_alpaca_data.json" +sean0042/KorMedMCQA,"{""language"": [""ko""], ""license"": ""cc-by-nc-2.0"", ""size_categories"": [""10K>> from datasets import load_dataset +>>> dataset = load_dataset(""Bingsu/zeroth-korean"") +>>> dataset +DatasetDict({ + train: Dataset({ + features: ['audio', 'text'], + num_rows: 22263 + }) + test: Dataset({ + features: ['text', 'audio'], + num_rows: 457 + }) +}) +``` + +### Data Size + +download: 2.68 GiB
+generated: 2.85 GiB
+total: 5.52 GiB + +### Data Fields + +- audio: `audio`, sampling rate = 16000 + - A dictionary containing the path to the downloaded audio file, the decoded audio array, and the sampling rate. + - Note that when accessing the audio column: `dataset[0][""audio""]` the audio file is automatically decoded and resampled to `dataset.features[""audio""].sampling_rate`. Decoding and resampling of a large number of audio files might take a significant amount of time. Thus it is important to first query the sample index before the ""audio"" column, i.e. `dataset[0][""audio""]` should always be preferred over `dataset[""audio""][0]`. +- text: `string` + +```pycon +>>> dataset[""train""][0] +{'audio': {'path': None, + 'array': array([-3.0517578e-05, 0.0000000e+00, -3.0517578e-05, ..., + 0.0000000e+00, 0.0000000e+00, -6.1035156e-05], dtype=float32), + 'sampling_rate': 16000}, + 'text': '인사를 결정하는 과정에서 당 지도부가 우 원내대표 및 원내지도부와 충분한 상의를 거치지 않은 채 일방적으로 인사를 했다는 불만도 원내지도부를 중심으로 흘러나왔다'} +``` + + +### Data Splits + +| | train | test | +| ---------- | -------- | ----- | +| # of data | 22263 | 457 |" +MarkrAI/KoCommercial-Dataset,"{""language"": [""ko""], ""license"": ""mit"", ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""train"", ""path"": ""data/train-*""}]}], ""dataset_info"": {""features"": [{""name"": ""input"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""output"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 187990458, ""num_examples"": 175454}], ""download_size"": 110149618, ""dataset_size"": 187990458}}","# SSL 데이터 생성을 위한 코드 공개 + +**[SSL 데이터 생성용 Github Repo](https://github.com/DopeorNope-Lee/Ko-Fine-tuning_DataGen)** + +- NIA와 AI-Hub와의 저작권 협의 하에, 조금 혼선이 생긴것 죄송합니다. + +- 이에 기존에 저희가 code베이스로 SSL 데이터를 생성했던 코드를 그대로 공개드립니다. + +- 다만, 이 과정에서는 저희 이후 파이프라인인, 자체 로컬 모델을 가지고 필터링하거나 수정하는 과정이 없어, 어느정도 감안을 해주시면 감사하겠습니다. + +- 코드는 누구나 사용하실 수 있고 과제와 Task에 맞게 활용하시면 감사하겠습니다! + + +-------------------- +# Dataset: KoCommercial-Dataset + +## Info + +**Dataset 개수:** 약 1.44M + +**License:** MIT + +**Dataset list(전부 상업적 용도로 이용가능)** +1. [kyujinpy/KOpen-platypus](kyujinpy/KOpen-platypus) (*Except non-commercial datasets) +2. [beomi/KoAlpaca-v1.1a](https://huggingface.co/datasets/beomi/KoAlpaca-v1.1a) +3. [HumanF-MarkrAI/WIKI_QA_Near_dedup](https://huggingface.co/datasets/HumanF-MarkrAI/WIKI_QA_Near_dedup) +4. [KorQuadv1.0](https://korquad.github.io/KorQuad%201.0/) +5. [AIHUB](https://www.aihub.or.kr/)(AIHUB데이터는, 위의 github주소를 통해, 데이터를 생성하셔 사용하시면 됩니다.) +- [일반상식 문장 생성 데이터](https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&aihubDataSe=data&dataSetSn=713090) +- [도서자료 요약](https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&aihubDataSe=data&dataSetSn=93) +- [논문자료 요약](https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&aihubDataSe=data&dataSetSn=90) +- [문서요약 텍스트](https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&aihubDataSe=data&dataSetSn=97) + +--- + +**Self-Supervised method(AIHUB 데이터셋 가공)** + + + +**0. (Default) Summary & Instruction-Answer** +``` + +주어진 문장에 적절한 제목을 생성하고, 내용을 요약해주세요. + +문장: 원고가 소속회사의 노동조합에서 분규가 발생하자 노조활동을 구실로 정상적인 근무를 해태하고, ... + + +제목: 부당노동행위구제재심판정취소 +원고가 주동하여 회사업무능률을 저해하고 회사업무상의 지휘명령에 위반하였다면 이에 따른 징계해고는 사내질서를 유지하기 위한 사용자 고유의 정당한 징계권의 행사로 보아야 한다. +``` + +**1. Sentence order inference** +``` + +임의의 순서로 나열된 문장들이 주어집니다. 주어진 문장들을 이용해 원본의 배열을 유추하고, 그 내용을 재구성하세요. + +임의의 순서로 나열된 문장: ['나는', '천재다', '그러나', '바보다', '동시에'] + + +나는 천재다. 그러나 동시에 바보다. +``` + +**2. Original sentence inference** +``` + +주어진 제목과 요약문에 대한 정보를 토대로, 요약되기 전 문장을 유추해서 생성해주세요. + +제목: 수산물 수급 위기관리체계 구축을 위한 기초연구 +요약문: 현대 사회에서 발생하는 다양하고... + + +지금의 국가가 직면하는 위기는 전통사회의 그것과 위기의 규모뿐만아니라... +``` + +**3. Last sentence prediction** +``` + +주어진 문장 뒤에 자연스럽게 이어질 문장을 생성해주세요. + +문장: ...최근에 방문한 조선예술영화촬영소 에 있는 ‘문화성혁명사적관’(김정일관)에는 1960년대 중반부터 2000년대까지 40년 동안 김정일의 문화예술 부문 지도가 11,890건이며, 그 중 문화예술기관을 직접 방문하여 지도한 이른바 ‘현���지도’가 1,770건이라는 안내판이 있었다. + + +북한 연극이 김정일과 주체사상이라는 키워드를 떠나 존재할 수 없다는 것을 단적으로 말해 준다 +``` + +**4. Multi question** +``` + +주어진 정보를 기반으로 질문에 답하세요. 답을 모른다면 답을 지어내지 말고 그냥 모른다고 말하세요. + +1839년 바그너는 괴테의 파우스트을 처음 읽고 그 내용에 마음이... + +질문: +1. 바그너는 괴테의 파우스트를 읽고 무엇을 쓰고자 했는가? +2. 바그너는 교향곡 작곡을 어디까지 쓴 뒤에 중단했는가? +3. 바그너가 파우스트 서곡을 쓸 때 어떤 곡의 영향을 받았는가? +4. 1839년 바그너가 교향곡의 소재로 쓰려고 했던 책은? +5. 파우스트 서곡의 라단조 조성이 영향을 받은 베토벤의 곡은? +6. 바그너가 파우스트를 처음으로 읽은 년도는? +7. 바그너가 처음 교향곡 작곡을 한 장소는? +8. 바그너의 1악장의 초연은 어디서 연주되었는가? + + +1. 교향곡 +2. 1악장 +3. 베토벤의 교향곡 9번 +4. 파우스트 +5. 합창교향곡 +6. 1839 +7. 파리 +8. 드레스덴 +``` + +**5. Mask Prediction** +``` + +주어진 문장에서 에 들어갈 적절한 단어를 생성해주세요. + +독도는 이다. + + +우리땅 +``` + +--- + +# References + +1.[The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning (Kim et al., 2023)](https://huggingface.co/papers/2305.14045) + +2.[Adapting Large Language Models via Reading Comprehension (Cheng et al., 2023)](https://huggingface.co/papers/2309.09530) + +3.[Deduplicating Training Data Makes Language Models Better(Lee et al., 2021)](https://huggingface.co/papers/2107.06499) + +--- + +# Acknowledgement + +- 이 모델은 과학기술정보통신부·광주광역시가 공동 지원한 '인공지능 중심 산업융합 집적단지 조성사업'으로 지원을 받아 수행된 연구 결과입니다. + +- This model was supported by Artificial intelligence industrial convergence cluster development project funded by the Ministry of Science and ICT(MSIT, Korea)&Gwangju Metropolitan City. + +- 또한 수많은 오픈소스 개발자들과 연구자들에게 감사드리고, 최근 한국어 LLM 오픈생태계에 많은 공헌을 해주신, [Beomi](https://huggingface.co/beomi) 님과 [maywell](https://huggingface.co/maywell) 님에게도 감사의 인사 드립니다." +jeanlee/kmhas_korean_hate_speech,"{""annotations_creators"": [""crowdsourced""], ""language"": [""ko""], ""language_creators"": [""found""], ""license"": [""cc-by-sa-4.0""], ""multilinguality"": [""monolingual""], ""pretty_name"": ""K-MHaS"", ""size_categories"": [""100K + + +## Dataset Description + +- **Homepage:** [K-MHaS](https://github.com/adlnlp/K-MHaS) +- **Repository:** [Korean Multi-label Hate Speech Dataset](https://github.com/adlnlp/K-MHaS) +- **Paper:** [K-MHaS: A Multi-label Hate Speech Detection Dataset in Korean Online News Comment](https://arxiv.org/abs/2208.10684) +- **Point of Contact:** [Caren Han](caren.han@sydney.edu.au) +- **Sample code:** [Colab](https://colab.research.google.com/drive/171KhS1_LVBtpAFd_kaT8lcrZmhcz5ehY?usp=sharing) + + +### Dataset Summary + +The Korean Multi-label Hate Speech Dataset, **K-MHaS**, consists of 109,692 utterances from Korean online news comments, labelled with 8 fine-grained hate speech classes (labels: `Politics`, `Origin`, `Physical`, `Age`, `Gender`, `Religion`, `Race`, `Profanity`) or `Not Hate Speech` class. Each utterance provides from a single to four labels that can handles Korean language patterns effectively. For more details, please refer to our paper about [**K-MHaS**](https://aclanthology.org/2022.coling-1.311), published at COLING 2022. + +### Supported Tasks and Leaderboards +Hate Speech Detection + +* `binary classification` (labels: `Hate Speech`, `Not Hate Speech`) +* `multi-label classification`: (labels: `Politics`, `Origin`, `Physical`, `Age`, `Gender`, `Religion`, `Race`, `Profanity`, `Not Hate Speech`) + +For the multi-label classification, a `Hate Speech` class from the binary classification, is broken down into eight classes, associated with the hate speech category. In order to reflect the social and historical context, we select the eight hate speech classes. For example, the `Politics` class is chosen, due to a significant influence on the style of Korean hate speech. + +### Languages + +Korean + +## Dataset Structure + +### Data Instances + +The dataset is provided with train/validation/test set in the txt format. Each instance is a news comment with a corresponding one or more hate speech classes (labels: `Politics`, `Origin`, `Physical`, `Age`, `Gender`, `Religion`, `Race`, `Profanity`) or `Not Hate Speech` class. The label numbers matching in both English and Korean is in the data fields section. + +```python +{'text':'수꼴틀딱시키들이 다 디져야 나라가 똑바로 될것같다..답이 없는 종자들ㅠ' + 'label': [2, 3, 4] +} +``` + +### Data Fields + +* `text`: utterance from Korean online news comment. +* `label`: the label numbers matching with 8 fine-grained hate speech classes and `not hate speech` class are follows. + * `0`: `Origin`(`출신차별`) hate speech based on place of origin or identity; + * `1`: `Physical`(`외모차별`) hate speech based on physical appearance (e.g. body, face) or disability; + * `2`: `Politics`(`정치성향차별`) hate speech based on political stance; + * `3`: `Profanity`(`혐오욕설`) hate speech in the form of swearing, cursing, cussing, obscene words, or expletives; or an unspecified hate speech category; + * `4`: `Age`(`연령차별`) hate speech based on age; + * `5`: `Gender`(`성차별`) hate speech based on gender or sexual orientation (e.g. woman, homosexual); + * `6`: `Race`(`인종차별`) hate speech based on ethnicity; + * `7`: `Religion`(`종교차별`) hate speech based on religion; + * `8`: `Not Hate Speech`(`해당사항없음`). + +### Data Splits + +In our repository, we provide splitted datasets that have 78,977(train) / 8,776 (validation) / 21,939 (test) samples, preserving the class proportion. + +## Dataset Creation + +### Curation Rationale + +We propose K-MHaS, a large size Korean multi-label hate speech detection dataset that represents Korean language patterns effectively. Most datasets in hate speech research are annotated using a single label classification of particular aspects, even though the subjectivity of hate speech cannot be explained with a mutually exclusive annotation scheme. We propose a multi-label hate speech annotation scheme that allows overlapping labels associated with the subjectivity and the intersectionality of hate speech. + +### Source Data + +#### Initial Data Collection and Normalization + +Our dataset is based on the Korean online news comments available on Kaggle and Github. The unlabeled raw data was collected between January 2018 and June 2020. Please see the details in our paper [K-MHaS](https://aclanthology.org/2022.coling-1.311) published at COLING2020. + + +#### Who are the source language producers? + +The language producers are users who left the comments on the Korean online news platform between 2018 and 2020. + +### Annotations + +#### Annotation process + +We begin with the common categories of hate speech found in literature and match the keywords for each category. After the preliminary round, we investigate the results to merge or remove labels in order to provide the most representative subtype labels of hate speech contextual to the cultural background. Our annotation instructions explain a twolayered annotation to (a) distinguish hate and not hate speech, and (b) the categories of hate speech. Annotators are requested to consider given keywords or alternatives of each category within social, cultural, and historical circumstances. For more details, please refer to the paper [K-MHaS](https://aclanthology.org/2022.coling-1.311). + +#### Who are the annotators? + +Five native speakers were recruited for manual annotation in both the preliminary and main rounds. + +### Personal and Sensitive Information + +This datasets contains examples of hateful language, however, has no personal information. + +## Considerations for Using the Data + +### Social Impact of Dataset + +We propose K-MHaS, a new large-sized dataset for Korean hate speech detection with a multi-label annotation scheme. We provided extensive baseline experiment results, presenting the usability of a dataset to detect Korean language patterns in hate speech. + +### Discussion of Biases + +All annotators were recruited from a crowdsourcing platform. They were informed about hate speech before handling the data. Our instructions allowed them to feel free to leave if they were uncomfortable with the content. With respect to the potential risks, we note that the subjectivity of human annotation would impact on the quality of the dataset. + +### Other Known Limitations + +[More Information Needed] + +## Additional Information + +### Dataset Curators + +This dataset is curated by Taejun Lim, Heejun Lee and Bogeun Jo. + +### Licensing Information + +Creative Commons Attribution-ShareAlike 4.0 International (cc-by-sa-4.0). + +### Citation Information + +``` +@inproceedings{lee-etal-2022-k, + title = ""K-{MH}a{S}: A Multi-label Hate Speech Detection Dataset in {K}orean Online News Comment"", + author = ""Lee, Jean and + Lim, Taejun and + Lee, Heejun and + Jo, Bogeun and + Kim, Yangsok and + Yoon, Heegeun and + Han, Soyeon Caren"", + booktitle = ""Proceedings of the 29th International Conference on Computational Linguistics"", + month = oct, + year = ""2022"", + address = ""Gyeongju, Republic of Korea"", + publisher = ""International Committee on Computational Linguistics"", + url = ""https://aclanthology.org/2022.coling-1.311"", + pages = ""3530--3538"", + abstract = ""Online hate speech detection has become an important issue due to the growth of online content, but resources in languages other than English are extremely limited. We introduce K-MHaS, a new multi-label dataset for hate speech detection that effectively handles Korean language patterns. The dataset consists of 109k utterances from news comments and provides a multi-label classification using 1 to 4 labels, and handles subjectivity and intersectionality. We evaluate strong baselines on K-MHaS. KR-BERT with a sub-character tokenizer outperforms others, recognizing decomposed characters in each hate speech class."", +} +``` + +### Contributions +The contributors of the work are: +- [Jean Lee](https://jeanlee-ai.github.io/) (The University of Sydney) +- [Taejun Lim](https://github.com/taezun) (The University of Sydney) +- [Heejun Lee](https://bigwaveai.com/) (BigWave AI) +- [Bogeun Jo](https://bigwaveai.com/) (BigWave AI) +- Yangsok Kim (Keimyung University) +- Heegeun Yoon (National Information Society Agency) +- [Soyeon Caren Han](https://drcarenhan.github.io/) (The University of Western Australia and The University of Sydney)" +djstrong/oscar-small,"{""annotations_creators"": [""no-annotation""], ""language_creators"": [""found""], ""language"": [""af"", ""am"", ""ar"", ""arz"", ""as"", ""az"", ""azb"", ""ba"", ""be"", ""bg"", ""bn"", ""bo"", ""br"", ""ca"", ""ce"", ""ceb"", ""ckb"", ""cs"", ""cv"", ""cy"", ""da"", ""de"", ""dv"", ""el"", ""en"", ""eo"", ""es"", ""et"", ""eu"", ""fa"", ""fi"", ""fr"", ""fy"", ""ga"", ""gl"", ""gu"", ""he"", ""hi"", ""hr"", ""hu"", ""hy"", ""id"", ""is"", ""it"", ""ja"", ""ka"", ""kk"", ""km"", ""kn"", ""ko"", ""ku"", ""ky"", ""la"", ""lb"", ""lo"", ""lt"", ""lv"", ""mg"", ""mhr"", ""mk"", ""ml"", ""mn"", ""mr"", ""ms"", ""mt"", ""my"", ""nds"", ""ne"", ""nl"", ""nn"", ""no"", ""or"", ""os"", ""pa"", ""pl"", ""pnb"", ""ps"", ""pt"", ""ro"", ""ru"", ""sa"", ""sah"", ""sd"", ""sh"", ""si"", ""sk"", ""sl"", ""sq"", ""sr"", ""sv"", ""sw"", ""ta"", ""te"", ""tg"", ""th"", ""tk"", ""tl"", ""tr"", ""tt"", ""ug"", ""uk"", ""ur"", ""uz"", ""vi"", ""yi"", ""zh""], ""license"": [""cc0-1.0""], ""multilinguality"": [""multilingual""], ""source_datasets"": [""oscar""], ""task_categories"": [""text-generation""], ""task_ids"": [""language-modeling""], ""paperswithcode_id"": ""oscar"", ""pretty_name"": ""OSCAR""}","## WARNING: this dataset is an extract of the OSCAR dataset published here to simulate the use of the full dataset in low-resource contexts. +Using this dataset is equivalent to using a processed version of OSCAR legally speaking. I take no credit for the gathering of the original data and hence refer entirely to the original dataset in the card below. + +# Dataset Card for ""oscar"" + +## Table of Contents +- [Dataset Description](#dataset-description) + - [Dataset Summary](#dataset-summary) + - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) + - [Languages](#languages) +- [Dataset Structure](#dataset-structure) + - [Data Instances](#data-instances) + - [Data Fields](#data-fields) + - [Data Splits](#data-splits) +- [Dataset Creation](#dataset-creation) + - [Curation Rationale](#curation-rationale) + - [Source Data](#source-data) + - [Annotations](#annotations) + - [Personal and Sensitive Information](#personal-and-sensitive-information) +- [Considerations for Using the Data](#considerations-for-using-the-data) + - [Social Impact of Dataset](#social-impact-of-dataset) + - [Discussion of Biases](#discussion-of-biases) + - [Other Known Limitations](#other-known-limitations) +- [Additional Information](#additional-information) + - [Dataset Curators](#dataset-curators) + - [Licensing Information](#licensing-information) + - [Citation Information](#citation-information) + - [Contributions](#contributions) + +## Dataset Description + +- **Homepage:** [https://oscar-corpus.com](https://oscar-corpus.com) +- **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) +- **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) +- **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) + +### Dataset Summary + +OSCAR or **O**pen **S**uper-large **C**rawled [**A**LMAnaCH](https://team.inria.fr/almanach/) co**R**pus is a huge multilingual corpus obtained by language classification and filtering of the [Common Crawl](https://commoncrawl.org/) corpus using the [goclassy](https://github.com/pjox/goclassy) architecture. Data is distributed by language in both original and deduplicated form. + +### Supported Tasks and Leaderboards + +OSCAR is mainly inteded to pretrain language models and word represantations. + +### Languages + +All the data is distributed by language, both the original and the deduplicated versions of the data are available. 166 different languages are available. The table in subsection [Data Splits Sample Size](#data-splits-sample-size) provides the language code for each subcorpus as well as the number of words (space separated tokens), lines and sizes for both the original and the deduplicated versions of OSCAR. + +## Dataset Structure + +We show detailed information for all the configurations of the dataset. + +## Dataset Creation + +### Curation Rationale + +OSCAR was constructed new pipeline derived from the [fastText's one](https://github.com/facebookresearch/fastText), called [_goclassy_](https://github.com/pjox/goclassy). Goclassy reuses the [fastText linear classifier](https://fasttext.cc) and the pre-trained fastText model for language recognition, but it completely rewrites and parallelises their pipeline in an asynchronous manner. + +The order of operations is more or less the same as in the fastText pre-processing pipeline but instead of clustering multiple operations into a single blocking process, a worker is launched for each operation but bounding the number of possible parallel operations at a given time by the number of available threads instead of the number of CPUs. Goclassy is implemented in the [Go programming language](https://golang.org/) so it lets the [Go runtime](https://golang.org/src/runtime/mprof.go) handle the scheduling of the processes. Thus the goclassy's pipeline one does not have to wait for a whole WET file to download, decompress and classify in order to start downloading and processing the next one, a new file will start downloading and processing as soon as the scheduler is able to allocate a new process. + +Filtering and cleaning processes at line level are done before feeding each line to the classifier. Lines shorter than 100 UTF-8 characters and lines containing invalid UTF-8 characters are discarted and are not classified. After all files are proccesed the deduplicated versions are constructed and everything is then splitted in shards and compressed. + +### Source Data + +#### Initial Data Collection and Normalization + +[Common Crawl](https://commoncrawl.org/) is a non-profit foundation which produces and maintains an open repository of web crawled data that is both accessible and analysable. Common Crawl's complete web archive consists of petabytes of data collected over 8 years of web crawling. The repository contains raw web page HTML data (WARC files), metdata extracts (WAT files) and plain text extracts (WET files). The organisation's crawlers has always respected [nofollow](http://microformats.org/wiki/rel-nofollow) and [robots.txt](https://www.robotstxt.org/) policies. + +Each monthly Common Crawl snapshot is in itself a massive multilingual corpus, where every single file contains data coming from multiple web pages written in a large variety of languages and covering all possible types of topics. + +To construct OSCAR the WET files of Common Crawl were used. These contain the extracted plain texts from the websites mostly converted to UTF-8, as well as headers containing the metatada of each crawled document. Each WET file comes compressed in gzip format and is stored on Amazon Web Services. In the case of OSCAR, the **November 2018** snapshot was used. It surpasses 20TB of uncompressed data and contains more than 50 thousand plain text files where each file consists of the plain text from multiple websites along its metadata header. + +#### Who are the source language producers? + +The data comes from multiple web pages in a large variety of languages. + +### Annotations + +The dataset does not contain any additional annotations. + +#### Annotation process + +N/A + +#### Who are the annotators? + +N/A + +### Personal and Sensitive Information + +Being constructed from Common Crawl, Personal and sensitive information might be present. This **must** be considered before training deep learning models with OSCAR, specially in the case of text-generation models. + +## Considerations for Using the Data + +### Social Impact of Dataset + +OSCAR is intended to bring more data to a wide variety of lanuages, the aim of the corpus is to make large amounts of data available to lower resource languages in order to facilitate the pre-training of state-of-the-art language modeling architectures. + +### Discussion of Biases + +OSCAR is not properly filtered yet and this can be reflected on the models trained with it. Care is advised specially concerning biases of the resulting models. + +### Other Known Limitations + +The [fastText linear classifier](https://fasttext.cc) is limed both in performance and the variety of languages it can recognize, so the quality of some OSCAR sub-corpora might be lower than expected, specially for the lowest-resource langiuages. Some audits have already been done by [third parties](https://arxiv.org/abs/2010.14571). + +## Additional Information + +### Dataset Curators + +The corpus was put together by [Pedro J. Ortiz](https://pjortiz.eu/), [Benoît Sagot](http://pauillac.inria.fr/~sagot/), and [Laurent Romary](https://cv.archives-ouvertes.fr/laurentromary), during work done at [Inria](https://www.inria.fr/en), particularly at the [ALMAnaCH team](https://team.inria.fr/almanach/). + +### Licensing Information + + These data are released under this licensing scheme + We do not own any of the text from which these data has been extracted. + We license the actual packaging of these data under the Creative Commons CC0 license (""no rights reserved"") http://creativecommons.org/publicdomain/zero/1.0/ + To the extent possible under law, Inria has waived all copyright and related or neighboring rights to OSCAR + This work is published from: France. + + Should you consider that our data contains material that is owned by you and should therefore not be reproduced here, please: + * Clearly identify yourself, with detailed contact data such as an address, telephone number or email address at which you can be contacted. + * Clearly identify the copyrighted work claimed to be infringed. + * Clearly identify the material that is claimed to be infringing and information reasonably sufficient to allow us to locate the material. + + We will comply to legitimate requests by removing the affected sources from the next release of the corpus. + +### Citation Information + +``` +@inproceedings{ortiz-suarez-etal-2020-monolingual, + title = ""A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages"", + author = ""Ortiz Su{'a}rez, Pedro Javier and + Romary, Laurent and + Sagot, Benoit"", + booktitle = ""Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics"", + month = jul, + year = ""2020"", + address = ""Online"", + publisher = ""Association for Computational Linguistics"", + url = ""https://www.aclweb.org/anthology/2020.acl-main.156"", + pages = ""1703--1714"", + abstract = ""We use the multilingual OSCAR corpus, extracted from Common Crawl via language classification, filtering and cleaning, to train monolingual contextualized word embeddings (ELMo) for five mid-resource languages. We then compare the performance of OSCAR-based and Wikipedia-based ELMo embeddings for these languages on the part-of-speech tagging and parsing tasks. We show that, despite the noise in the Common-Crawl-based OSCAR data, embeddings trained on OSCAR perform much better than monolingual embeddings trained on Wikipedia. They actually equal or improve the current state of the art in tagging and parsing for all five languages. In particular, they also improve over multilingual Wikipedia-based contextual embeddings (multilingual BERT), which almost always constitutes the previous state of the art, thereby showing that the benefit of a larger, more diverse corpus surpasses the cross-lingual benefit of multilingual embedding architectures."", +} + +@inproceedings{OrtizSuarezSagotRomary2019, + author = {Pedro Javier {Ortiz Su{'a}rez} and Benoit Sagot and Laurent Romary}, + title = {Asynchronous pipelines for processing huge corpora on medium to low resource infrastructures}, + series = {Proceedings of the Workshop on Challenges in the Management of Large Corpora (CMLC-7) 2019. Cardiff, 22nd July 2019}, + editor = {Piotr BaÅ„ski and Adrien Barbaresi and Hanno Biber and Evelyn Breiteneder and Simon Clematide and Marc Kupietz and Harald L{""u}ngen and Caroline Iliadi}, + publisher = {Leibniz-Institut f{""u}r Deutsche Sprache}, + address = {Mannheim}, + doi = {10.14618/ids-pub-9021}, + url = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-90215}, + pages = {9 -- 16}, + year = {2019}, + abstract = {Common Crawl is a considerably large, heterogeneous multilingual corpus comprised of crawled documents from the internet, surpassing 20TB of data and distributed as a set of more than 50 thousand plain text files where each contains many documents written in a wide variety of languages. Even though each document has a metadata block associated to it, this data lacks any information about the language in which each document is written, making it extremely difficult to use Common Crawl for monolingual applications. We propose a general, highly parallel, multithreaded pipeline to clean and classify Common Crawl by language; we specifically design it so that it runs efficiently on medium to low resource infrastructures where I/O speeds are the main constraint. We develop the pipeline so that it can be easily reapplied to any kind of heterogeneous corpus and so that it can be parameterised to a wide range of infrastructures. We also distribute a 6.3TB version of Common Crawl, filtered, classified by language, shuffled at line level in order to avoid copyright issues, and ready to be used for NLP applications.}, + language = {en} +} + +``` + +### Contributions + +Thanks to [@pjox](https://github.com/pjox) and [@lhoestq](https://github.com/lhoestq) for adding this dataset." +lcw99/wikipedia-korean-20221001,"{""language"": [""ko""], ""license"": ""apache-2.0""}",[20240501 update](https://huggingface.co/datasets/lcw99/wikipedia-korean-20240501) +kyujinpy/KOpen-platypus,"{""language"": [""en"", ""ko""], ""license"": ""cc-by-4.0"", ""size_categories"": [""10K Post-processing 작업 내용 + +- Add post-processing (v2) ++) 단답형 Task 삭제. + +## OpenOrca-Ko-v2 +1. NIV // 약 1500개 +2. FLAN // 약 9000개 +3. T0 // 약 6000개 +4. CoT // 약 2000개 +> Dataset 구성 + +- 수작업으로 고친 내용(v2) +1. 영어로 된 답변 수정. (Ex. Nick -> 닉, Lucky -> 운이 좋음, ...) +2. KoCoT 데이터셋 제거. +3. Yes, True, False 등등 일부 답변 수정 +> Post-processing 작업 내용 + + +## Translation +Using DeepL Pro API. Thanks. + +--- +>Below is original dataset card + +## Table of Contents +- [Dataset Summary](#dataset-summary) +- [Dataset Attribution](#dataset-attribution) +- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) +- [Languages](#languages) +- [Dataset Structure](#dataset-structure) + - [Data Instances](#data-instances) + - [Data Fields](#data-fields) + - [Data Splits](#data-splits) +- [Dataset Creation](#dataset-creation) + - [Curation Rationale](#curation-rationale) + - [Source Data](#source-data) +- [Dataset Use](#dataset-use) + - [Use Cases](#use-cases) + - [Usage Caveats](#usage-caveats) + - [Getting Started](#getting-started) + + +

🐋 The OpenOrca Dataset! 🐋

+ +![OpenOrca Logo](https://huggingface.co/datasets/Open-Orca/OpenOrca/resolve/main/OpenOrcaLogo.png ""OpenOrca Logo"") + + + +We are thrilled to announce the release of the OpenOrca dataset! +This rich collection of augmented FLAN data aligns, as best as possible, with the distributions outlined in the [Orca paper](https://arxiv.org/abs/2306.02707). +It has been instrumental in generating high-performing model checkpoints and serves as a valuable resource for all NLP researchers and developers! + +# Official Models + +## OpenOrca-Platypus2-13B + +Our [latest release](https://huggingface.co/Open-Orca/OpenOrca-Platypus2-13B), the first 13B model to score higher than LLaMA1-65B on the HuggingFace Leaderboard! +Released in partnership with Platypus. + +## LlongOrca 7B & 13B + +* Our [first 7B release](https://huggingface.co/Open-Orca/LlongOrca-7B-16k), trained on top of LLongMA2 to achieve 16,000 tokens context. #1 long context 7B model at release time, with >99% of the overall #1 model's performance. +* [LlongOrca-13B-16k](https://huggingface.co/Open-Orca/LlongOrca-13B-16k), trained on top of LLongMA2. #1 long context 13B model at release time, with >97% of the overall #1 model's performance. + +## OpenOrcaxOpenChat-Preview2-13B + +Our [second model](https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-13B), highlighting that we've surpassed the performance reported in the Orca paper. +Was #1 at release time, now surpassed by our own OpenOrca-Platypus2-13B. +Released in partnership with OpenChat. + +## OpenOrca-Preview1-13B + +[OpenOrca-Preview1-13B](https://huggingface.co/Open-Orca/OpenOrca-Preview1-13B) +This model was trained in less than a day, for <$200, with <10% of our data. +At release, it beat the current state of the art models on BigBench-Hard and AGIEval. Achieves ~60% of the improvements reported in the Orca paper. + + + +# Dataset Summary + +The OpenOrca dataset is a collection of augmented [FLAN Collection data](https://arxiv.org/abs/2301.13688). +Currently ~1M GPT-4 completions, and ~3.2M GPT-3.5 completions. +It is tabularized in alignment with the distributions presented in the ORCA paper and currently represents a partial completion of the full intended dataset, with ongoing generation to expand its scope. +The data is primarily used for training and evaluation in the field of natural language processing. + + + +# Dataset Attribution + +We would like to give special recognition to the following contributors for their significant efforts and dedication: + + + Teknium + WingLian/Caseus + Eric Hartford + NanoBit + Pankaj + Winddude + Rohan + + http://AlignmentLab.ai: + Autometa + Entropi + AtlasUnified + NeverendingToast + NanoBit + WingLian/Caseus + +Also of course, as always, TheBloke, for being the backbone of the whole community. + +Many thanks to NanoBit and Caseus, makers of [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl), for lending us their expertise on the platform that developed and trained manticore, minotaur, and many others! + +We are welcoming sponsors or collaborators to help us build these models to the scale they deserve. Please reach out via our socials: +http://Alignmentlab.ai https://discord.gg/n9hXaBPWxx + +Want to visualize our full dataset? Check out our [Nomic Atlas Map](https://atlas.nomic.ai/map/c1b88b47-2d9b-47e0-9002-b80766792582/2560fd25-52fe-42f1-a58f-ff5eccc890d2). + [](https://atlas.nomic.ai/map/c1b88b47-2d9b-47e0-9002-b80766792582/2560fd25-52fe-42f1-a58f-ff5eccc890d2) + + + + +# Supported Tasks and Leaderboards + +This dataset supports a range of tasks including language modeling, text generation, and text augmentation. +It has been instrumental in the generation of multiple high-performing model checkpoints which have exhibited exceptional performance in our unit testing. +Further information on leaderboards will be updated as they become available. + + + +# Languages + +The language of the data is primarily English. + + + +# Dataset Structure + + + +## Data Instances + +A data instance in this dataset represents entries from the FLAN collection which have been augmented by submitting the listed question to either GPT-4 or GPT-3.5. +The response is then entered into the response field. + + + +## Data Fields + +The fields are: +1) 'id', a unique numbered identifier which includes one of 'niv', 't0', 'cot', or 'flan' to represent which source FLAN Collection submix the 'question' is sourced from. +2) 'system_prompt', representing the System Prompt presented to the GPT-3.5 or GPT-4 API for the datapoint +3) 'question', representing a question entry as provided by the FLAN Collection +4) 'response', a response to that question received from a query to either GPT-3.5 or GPT-4. + + + +## Data Splits + +The data is unsplit. + + + +# Dataset Creation + + + +## Curation Rationale + +The dataset was created to provide a source of augmented text data for researchers and developers. +The datapoints are intended primarily to provide an enhancement of the core FLAN Collection data which relies upon the detailed step by step reasoning capabilities of GPT-3.5 and GPT-4. +This ""reasoning trace"" augmentation has demonstrated exceptional results, allowing a LLaMA-13B model trained with this data to rival or beat GPT-3.5 on broad sets of hard reasoning tasks which all models below 100B parameters had previously performed dramatically worse on. + + + +## Source Data + +The data is generated using techniques in alignment with the distributions outlined in the Orca paper, except as noted below: + +1) There is not enough CoT data in the FLAN Collection to generate 150K zero-shot entries, as the paper purports to use. + We suspect this portion was either undocumented or misrepresented. We have used the ~75K points available. +2) We used the pre-generated FLAN Collection datasets hosted on HuggingFace under conceptofmind, e.g. [conceptofmind/flan2021](https://huggingface.co/datasets/conceptofmind/flan2021_submix_original). + These are referenced by the [official FLAN Collection repo](https://github.com/google-research/FLAN/tree/main/flan/v2) as the preferred data source. + However, these are a subset of the full FLAN Collection data, and have less than the required entries for the flan2021 and t0 submixes, by ~1.25M and 200k respectively. + +Combined, this gave us ~1.5M fewer datapoints than in the original Orca paper. Completing the set is an ongoing work. + + + +# Dataset Use + + + +## Use Cases + +The dataset can be used for tasks related to language understanding, natural language processing, machine learning model training, and model performance evaluation. + + + +## Usage Caveats + +Given that this is a work-in-progress dataset, it is recommended to regularly check for updates and improvements. +Further, the data should be used in accordance with the guidelines and recommendations outlined in the Orca paper. + + + +## Getting Started + +This dataset is organized such that it can be naively loaded via Hugging Face datasets library. +We recommend using streaming due to the large size of the files. +Regular updates and data generation progress can be monitored through the OpenOrca repository on Hugging Face. + + +# Citation + +```bibtex +@misc{OpenOrca, + title = {OpenOrca: An Open Dataset of GPT Augmented FLAN Reasoning Traces}, + author = {Wing Lian and Bleys Goodson and Eugene Pentland and Austin Cook and Chanvichet Vong and ""Teknium""}, + year = {2023}, + publisher = {HuggingFace}, + journal = {HuggingFace repository}, + howpublished = {\url{https://https://huggingface.co/Open-Orca/OpenOrca}, +} +``` +```bibtex +@misc{mukherjee2023orca, + title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4}, + author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah}, + year={2023}, + eprint={2306.02707}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +``` +```bibtex +@misc{longpre2023flan, + title={The Flan Collection: Designing Data and Methods for Effective Instruction Tuning}, + author={Shayne Longpre and Le Hou and Tu Vu and Albert Webson and Hyung Won Chung and Yi Tay and Denny Zhou and Quoc V. Le and Barret Zoph and Jason Wei and Adam Roberts}, + year={2023}, + eprint={2301.13688}, + archivePrefix={arXiv}, + primaryClass={cs.AI} +} +``` +```bibtex +@misc{touvron2023llama, + title={Llama 2: Open Foundation and Fine-Tuned Chat Models}, + author={Hugo Touvron and Louis Martin and Kevin Stone and Peter Albert and Amjad Almahairi and Yasmine Babaei and Nikolay Bashlykov and Soumya Batra and Prajjwal Bhargava and Shruti Bhosale and Dan Bikel and Lukas Blecher and Cristian Canton Ferrer and Moya Chen and Guillem Cucurull and David Esiobu and Jude Fernandes and Jeremy Fu and Wenyin Fu and Brian Fuller and Cynthia Gao and Vedanuj Goswami and Naman Goyal and Anthony Hartshorn and Saghar Hosseini and Rui Hou and Hakan Inan and Marcin Kardas and Viktor Kerkez and Madian Khabsa and Isabel Kloumann and Artem Korenev and Punit Singh Koura and Marie-Anne Lachaux and Thibaut Lavril and Jenya Lee and Diana Liskovich and Yinghai Lu and Yuning Mao and Xavier Martinet and Todor Mihaylov and Pushkar Mishra and Igor Molybog and Yixin Nie and Andrew Poulton and Jeremy Reizenstein and Rashi Rungta and Kalyan Saladi and Alan Schelten and Ruan Silva and Eric Michael Smith and Ranjan Subramanian and Xiaoqing Ellen Tan and Binh Tang and Ross Taylor and Adina Williams and Jian Xiang Kuan and Puxin Xu and Zheng Yan and Iliyan Zarov and Yuchen Zhang and Angela Fan and Melanie Kambadur and Sharan Narang and Aurelien Rodriguez and Robert Stojnic and Sergey Edunov and Thomas Scialom}, + year={2023}, + eprint= arXiv 2307.09288 +} +@software{touvron2023llama, + title={LLaMA: Open and Efficient Foundation Language Models}, + author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and Rodriguez, Aurelien and Joulin, Armand and Grave, Edouard and Lample, Guillaume}, + journal={arXiv preprint arXiv:2302.13971}, + year={2023} +} +```" +cyanic-selkie/wikianc,"{""license"": ""cc-by-sa-4.0"", ""pretty_name"": ""WikiAnc"", ""annotations_creators"": [""machine-generated"", ""crowdsourced""], ""language_creators"": [""machine-generated"", ""crowdsourced""], ""task_categories"": [""token-classification""], ""multilinguality"": [""multilingual""], ""language"": [""en"", ""ceb"", ""de"", ""sv"", ""fr"", ""nl"", ""ru"", ""es"", ""it"", ""arz"", ""pl"", ""ja"", ""zh"", ""vi"", ""uk"", ""war"", ""ar"", ""pt"", ""fa"", ""ca"", ""sr"", ""id"", ""ko"", ""no"", ""ce"", ""fi"", ""cs"", ""tr"", ""hu"", ""tt"", ""sh"", ""ro"", ""eu"", ""ms"", ""eo"", ""he"", ""hy"", ""da"", ""bg"", ""cy"", ""sk"", ""azb"", ""uz"", ""et"", ""be"", ""kk"", ""min"", ""el"", ""hr"", ""lt"", ""gl"", ""az"", ""ur"", ""sl"", ""lld"", ""ka"", ""nn"", ""hi"", ""th"", ""ta"", ""bn"", ""la"", ""mk"", ""ast"", ""lv"", ""af"", ""tg"", ""my"", ""mg"", ""mr"", ""sq"", ""bs"", ""oc"", ""te"", ""ml"", ""nds"", ""br"", ""ky"", ""sw"", ""jv"", ""lmo"", ""new"", ""pnb"", ""vec"", ""ht"", ""pms"", ""ba"", ""lb"", ""su"", ""ku"", ""ga"", ""szl"", ""is"", ""fy"", ""cv"", ""ckb"", ""pa"", ""tl"", ""an"", ""wuu"", ""diq"", ""io"", ""sco"", ""vo"", ""yo"", ""ne"", ""ia"", ""kn"", ""gu"", ""als"", ""ha"", ""avk"", ""bar"", ""crh"", ""scn"", ""bpy"", ""qu"", ""mn"", ""nv"", ""xmf"", ""ban"", ""si"", ""tum"", ""ps"", ""ig"", ""frr"", ""os"", ""mzn"", ""or"", ""sah"", ""cdo"", ""gd"", ""bug"", ""yi"", ""sd"", ""ilo"", ""am"", ""nap"", ""li"", ""bcl"", ""fo"", ""gor"", ""hsb"", ""mai"", ""shn"", ""eml"", ""ace"", ""sa"", ""as"", ""wa"", ""ie"", ""hyw"", ""lij"", ""mhr"", ""zu"", ""sn"", ""hif"", ""mrj"", ""bjn"", ""km"", ""mni"", ""hak"", ""pam"", ""sat"", ""rue"", ""nso"", ""bh"", ""so"", ""mi"", ""se"", ""myv"", ""vls"", ""dag"", ""sc"", ""co"", ""ary"", ""kw"", ""bo"", ""vep"", ""glk"", ""tk"", ""kab"", ""gan"", ""rw"", ""ab"", ""gv"", ""ug"", ""nah"", ""zea"", ""skr"", ""frp"", ""udm"", ""pcd"", ""mt"", ""kv"", ""csb"", ""gn"", ""smn"", ""ay"", ""nrm"", ""ks"", ""lez"", ""lfn"", ""olo"", ""mwl"", ""lo"", ""stq"", ""ang"", ""mdf"", ""fur"", ""rm"", ""lad"", ""kaa"", ""gom"", ""ext"", ""koi"", ""tyv"", ""pap"", ""av"", ""dsb"", ""ln"", ""dty"", ""tw"", ""dv"", ""ksh"", ""za"", ""gag"", ""bxr"", ""pfl"", ""lg"", ""szy"", ""pag"", ""blk"", ""pi"", ""tay"", ""haw"", ""awa"", ""inh"", ""krc"", ""xal"", ""pdc"", ""to"", ""atj"", ""tcy"", ""arc"", ""mnw"", ""shi"", ""jam"", ""kbp"", ""wo"", ""anp"", ""kbd"", ""nia"", ""om"", ""nov"", ""ki"", ""nqo"", ""bi"", ""xh"", ""tpi"", ""ff"", ""tet"", ""jbo"", ""fj"", ""kg"", ""lbe"", ""ty"", ""cu"", ""guw"", ""trv"", ""ami"", ""srn"", ""sm"", ""mad"", ""alt"", ""ltg"", ""gcr"", ""chr"", ""tn"", ""ny"", ""st"", ""pih"", ""got"", ""rmy"", ""ee"", ""pcm"", ""bm"", ""ss"", ""gpe"", ""ts"", ""ve"", ""kcg"", ""chy"", ""rn"", ""ch"", ""gur"", ""ik"", ""ady"", ""fat"", ""pnt"", ""guc"", ""iu"", ""pwn"", ""sg"", ""din"", ""ti"", ""kl"", ""dz"", ""cr""], ""tags"": [""wikidata"", ""wikipedia"", ""wikification"", ""named-entity-linking"", ""nel"", ""entity-linking"", ""el"", ""named-entity-disambiguation"", ""ned"", ""entity-disambiguation"", ""ed""], ""configs"": [{""config_name"": ""ab"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ab/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ab/validation.parquet""}]}, {""config_name"": ""ace"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ace/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ace/validation.parquet""}]}, {""config_name"": ""ady"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ady/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ady/validation.parquet""}]}, {""config_name"": ""af"", ""data_files"": [{""split"": ""train"", ""path"": ""data/af/train.parquet""}, {""split"": ""validation"", ""path"": ""data/af/validation.parquet""}]}, {""config_name"": ""als"", ""data_files"": [{""split"": ""train"", ""path"": ""data/als/train.parquet""}, {""split"": ""validation"", ""path"": ""data/als/validation.parquet""}]}, {""config_name"": ""alt"", ""data_files"": [{""split"": ""train"", ""path"": ""data/alt/train.parquet""}, {""split"": ""validation"", ""path"": ""data/alt/validation.parquet""}]}, {""config_name"": ""am"", ""data_files"": [{""split"": ""train"", ""path"": ""data/am/train.parquet""}, {""split"": ""validation"", ""path"": ""data/am/validation.parquet""}]}, {""config_name"": ""ami"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ami/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ami/validation.parquet""}]}, {""config_name"": ""an"", ""data_files"": [{""split"": ""train"", ""path"": ""data/an/train.parquet""}, {""split"": ""validation"", ""path"": ""data/an/validation.parquet""}]}, {""config_name"": ""ang"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ang/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ang/validation.parquet""}]}, {""config_name"": ""anp"", ""data_files"": [{""split"": ""train"", ""path"": ""data/anp/train.parquet""}, {""split"": ""validation"", ""path"": ""data/anp/validation.parquet""}]}, {""config_name"": ""ar"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ar/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ar/validation.parquet""}]}, {""config_name"": ""arc"", ""data_files"": [{""split"": ""train"", ""path"": ""data/arc/train.parquet""}, {""split"": ""validation"", ""path"": ""data/arc/validation.parquet""}]}, {""config_name"": ""ary"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ary/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ary/validation.parquet""}]}, {""config_name"": ""arz"", ""data_files"": [{""split"": ""train"", ""path"": ""data/arz/train.parquet""}, {""split"": ""validation"", ""path"": ""data/arz/validation.parquet""}]}, {""config_name"": ""as"", ""data_files"": [{""split"": ""train"", ""path"": ""data/as/train.parquet""}, {""split"": ""validation"", ""path"": ""data/as/validation.parquet""}]}, {""config_name"": ""ast"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ast/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ast/validation.parquet""}]}, {""config_name"": ""atj"", ""data_files"": [{""split"": ""train"", ""path"": ""data/atj/train.parquet""}, {""split"": ""validation"", ""path"": ""data/atj/validation.parquet""}]}, {""config_name"": ""av"", ""data_files"": [{""split"": ""train"", ""path"": ""data/av/train.parquet""}, {""split"": ""validation"", ""path"": ""data/av/validation.parquet""}]}, {""config_name"": ""avk"", ""data_files"": [{""split"": ""train"", ""path"": ""data/avk/train.parquet""}, {""split"": ""validation"", ""path"": ""data/avk/validation.parquet""}]}, {""config_name"": ""awa"", ""data_files"": [{""split"": ""train"", ""path"": ""data/awa/train.parquet""}, {""split"": ""validation"", ""path"": ""data/awa/validation.parquet""}]}, {""config_name"": ""ay"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ay/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ay/validation.parquet""}]}, {""config_name"": ""az"", ""data_files"": [{""split"": ""train"", ""path"": ""data/az/train.parquet""}, {""split"": ""validation"", ""path"": ""data/az/validation.parquet""}]}, {""config_name"": ""azb"", ""data_files"": [{""split"": ""train"", ""path"": ""data/azb/train.parquet""}, {""split"": ""validation"", ""path"": ""data/azb/validation.parquet""}]}, {""config_name"": ""ba"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ba/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ba/validation.parquet""}]}, {""config_name"": ""ban"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ban/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ban/validation.parquet""}]}, {""config_name"": ""bar"", ""data_files"": [{""split"": ""train"", ""path"": ""data/bar/train.parquet""}, {""split"": ""validation"", ""path"": ""data/bar/validation.parquet""}]}, {""config_name"": ""bat_smg"", ""data_files"": [{""split"": ""train"", ""path"": ""data/bat_smg/train.parquet""}, {""split"": ""validation"", ""path"": ""data/bat_smg/validation.parquet""}]}, {""config_name"": ""bcl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/bcl/train.parquet""}, {""split"": ""validation"", ""path"": ""data/bcl/validation.parquet""}]}, {""config_name"": ""be"", ""data_files"": [{""split"": ""train"", ""path"": ""data/be/train.parquet""}, {""split"": ""validation"", ""path"": ""data/be/validation.parquet""}]}, {""config_name"": ""bg"", ""data_files"": [{""split"": ""train"", ""path"": ""data/bg/train.parquet""}, {""split"": ""validation"", ""path"": ""data/bg/validation.parquet""}]}, {""config_name"": ""bh"", ""data_files"": [{""split"": ""train"", ""path"": ""data/bh/train.parquet""}, {""split"": ""validation"", ""path"": ""data/bh/validation.parquet""}]}, {""config_name"": ""bi"", ""data_files"": [{""split"": ""train"", ""path"": ""data/bi/train.parquet""}, {""split"": ""validation"", ""path"": ""data/bi/validation.parquet""}]}, {""config_name"": ""bjn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/bjn/train.parquet""}, {""split"": ""validation"", ""path"": ""data/bjn/validation.parquet""}]}, {""config_name"": ""blk"", ""data_files"": [{""split"": ""train"", ""path"": ""data/blk/train.parquet""}, {""split"": ""validation"", ""path"": ""data/blk/validation.parquet""}]}, {""config_name"": ""bm"", ""data_files"": [{""split"": ""train"", ""path"": ""data/bm/train.parquet""}, {""split"": ""validation"", ""path"": ""data/bm/validation.parquet""}]}, {""config_name"": ""bn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/bn/train.parquet""}, {""split"": ""validation"", ""path"": ""data/bn/validation.parquet""}]}, {""config_name"": ""bo"", ""data_files"": [{""split"": ""train"", ""path"": ""data/bo/train.parquet""}, {""split"": ""validation"", ""path"": ""data/bo/validation.parquet""}]}, {""config_name"": ""bpy"", ""data_files"": [{""split"": ""train"", ""path"": ""data/bpy/train.parquet""}, {""split"": ""validation"", ""path"": ""data/bpy/validation.parquet""}]}, {""config_name"": ""br"", ""data_files"": [{""split"": ""train"", ""path"": ""data/br/train.parquet""}, {""split"": ""validation"", ""path"": ""data/br/validation.parquet""}]}, {""config_name"": ""bs"", ""data_files"": [{""split"": ""train"", ""path"": ""data/bs/train.parquet""}, {""split"": ""validation"", ""path"": ""data/bs/validation.parquet""}]}, {""config_name"": ""bug"", ""data_files"": [{""split"": ""train"", ""path"": ""data/bug/train.parquet""}, {""split"": ""validation"", ""path"": ""data/bug/validation.parquet""}]}, {""config_name"": ""bxr"", ""data_files"": [{""split"": ""train"", ""path"": ""data/bxr/train.parquet""}, {""split"": ""validation"", ""path"": ""data/bxr/validation.parquet""}]}, {""config_name"": ""ca"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ca/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ca/validation.parquet""}]}, {""config_name"": ""cbk_zam"", ""data_files"": [{""split"": ""train"", ""path"": ""data/cbk_zam/train.parquet""}, {""split"": ""validation"", ""path"": ""data/cbk_zam/validation.parquet""}]}, {""config_name"": ""cdo"", ""data_files"": [{""split"": ""train"", ""path"": ""data/cdo/train.parquet""}, {""split"": ""validation"", ""path"": ""data/cdo/validation.parquet""}]}, {""config_name"": ""ce"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ce/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ce/validation.parquet""}]}, {""config_name"": ""ceb"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ceb/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ceb/validation.parquet""}]}, {""config_name"": ""ch"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ch/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ch/validation.parquet""}]}, {""config_name"": ""chr"", ""data_files"": [{""split"": ""train"", ""path"": ""data/chr/train.parquet""}, {""split"": ""validation"", ""path"": ""data/chr/validation.parquet""}]}, {""config_name"": ""chy"", ""data_files"": [{""split"": ""train"", ""path"": ""data/chy/train.parquet""}, {""split"": ""validation"", ""path"": ""data/chy/validation.parquet""}]}, {""config_name"": ""ckb"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ckb/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ckb/validation.parquet""}]}, {""config_name"": ""co"", ""data_files"": [{""split"": ""train"", ""path"": ""data/co/train.parquet""}, {""split"": ""validation"", ""path"": ""data/co/validation.parquet""}]}, {""config_name"": ""cr"", ""data_files"": [{""split"": ""train"", ""path"": ""data/cr/train.parquet""}, {""split"": ""validation"", ""path"": ""data/cr/validation.parquet""}]}, {""config_name"": ""crh"", ""data_files"": [{""split"": ""train"", ""path"": ""data/crh/train.parquet""}, {""split"": ""validation"", ""path"": ""data/crh/validation.parquet""}]}, {""config_name"": ""cs"", ""data_files"": [{""split"": ""train"", ""path"": ""data/cs/train.parquet""}, {""split"": ""validation"", ""path"": ""data/cs/validation.parquet""}]}, {""config_name"": ""csb"", ""data_files"": [{""split"": ""train"", ""path"": ""data/csb/train.parquet""}, {""split"": ""validation"", ""path"": ""data/csb/validation.parquet""}]}, {""config_name"": ""cu"", ""data_files"": [{""split"": ""train"", ""path"": ""data/cu/train.parquet""}, {""split"": ""validation"", ""path"": ""data/cu/validation.parquet""}]}, {""config_name"": ""cv"", ""data_files"": [{""split"": ""train"", ""path"": ""data/cv/train.parquet""}, {""split"": ""validation"", ""path"": ""data/cv/validation.parquet""}]}, {""config_name"": ""cy"", ""data_files"": [{""split"": ""train"", ""path"": ""data/cy/train.parquet""}, {""split"": ""validation"", ""path"": ""data/cy/validation.parquet""}]}, {""config_name"": ""da"", ""data_files"": [{""split"": ""train"", ""path"": ""data/da/train.parquet""}, {""split"": ""validation"", ""path"": ""data/da/validation.parquet""}]}, {""config_name"": ""dag"", ""data_files"": [{""split"": ""train"", ""path"": ""data/dag/train.parquet""}, {""split"": ""validation"", ""path"": ""data/dag/validation.parquet""}]}, {""config_name"": ""de"", ""data_files"": [{""split"": ""train"", ""path"": ""data/de/train.parquet""}, {""split"": ""validation"", ""path"": ""data/de/validation.parquet""}]}, {""config_name"": ""din"", ""data_files"": [{""split"": ""train"", ""path"": ""data/din/train.parquet""}, {""split"": ""validation"", ""path"": ""data/din/validation.parquet""}]}, {""config_name"": ""diq"", ""data_files"": [{""split"": ""train"", ""path"": ""data/diq/train.parquet""}, {""split"": ""validation"", ""path"": ""data/diq/validation.parquet""}]}, {""config_name"": ""dsb"", ""data_files"": [{""split"": ""train"", ""path"": ""data/dsb/train.parquet""}, {""split"": ""validation"", ""path"": ""data/dsb/validation.parquet""}]}, {""config_name"": ""dty"", ""data_files"": [{""split"": ""train"", ""path"": ""data/dty/train.parquet""}, {""split"": ""validation"", ""path"": ""data/dty/validation.parquet""}]}, {""config_name"": ""dv"", ""data_files"": [{""split"": ""train"", ""path"": ""data/dv/train.parquet""}, {""split"": ""validation"", ""path"": ""data/dv/validation.parquet""}]}, {""config_name"": ""dz"", ""data_files"": [{""split"": ""train"", ""path"": ""data/dz/train.parquet""}, {""split"": ""validation"", ""path"": ""data/dz/validation.parquet""}]}, {""config_name"": ""ee"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ee/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ee/validation.parquet""}]}, {""config_name"": ""el"", ""data_files"": [{""split"": ""train"", ""path"": ""data/el/train.parquet""}, {""split"": ""validation"", ""path"": ""data/el/validation.parquet""}]}, {""config_name"": ""eml"", ""data_files"": [{""split"": ""train"", ""path"": ""data/eml/train.parquet""}, {""split"": ""validation"", ""path"": ""data/eml/validation.parquet""}]}, {""config_name"": ""en"", ""data_files"": [{""split"": ""train"", ""path"": ""data/en/train.parquet""}, {""split"": ""validation"", ""path"": ""data/en/validation.parquet""}]}, {""config_name"": ""eo"", ""data_files"": [{""split"": ""train"", ""path"": ""data/eo/train.parquet""}, {""split"": ""validation"", ""path"": ""data/eo/validation.parquet""}]}, {""config_name"": ""es"", ""data_files"": [{""split"": ""train"", ""path"": ""data/es/train.parquet""}, {""split"": ""validation"", ""path"": ""data/es/validation.parquet""}]}, {""config_name"": ""et"", ""data_files"": [{""split"": ""train"", ""path"": ""data/et/train.parquet""}, {""split"": ""validation"", ""path"": ""data/et/validation.parquet""}]}, {""config_name"": ""eu"", ""data_files"": [{""split"": ""train"", ""path"": ""data/eu/train.parquet""}, {""split"": ""validation"", ""path"": ""data/eu/validation.parquet""}]}, {""config_name"": ""ext"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ext/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ext/validation.parquet""}]}, {""config_name"": ""fa"", ""data_files"": [{""split"": ""train"", ""path"": ""data/fa/train.parquet""}, {""split"": ""validation"", ""path"": ""data/fa/validation.parquet""}]}, {""config_name"": ""fat"", ""data_files"": [{""split"": ""train"", ""path"": ""data/fat/train.parquet""}, {""split"": ""validation"", ""path"": ""data/fat/validation.parquet""}]}, {""config_name"": ""ff"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ff/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ff/validation.parquet""}]}, {""config_name"": ""fi"", ""data_files"": [{""split"": ""train"", ""path"": ""data/fi/train.parquet""}, {""split"": ""validation"", ""path"": ""data/fi/validation.parquet""}]}, {""config_name"": ""fiu_vro"", ""data_files"": [{""split"": ""train"", ""path"": ""data/fiu_vro/train.parquet""}, {""split"": ""validation"", ""path"": ""data/fiu_vro/validation.parquet""}]}, {""config_name"": ""fj"", ""data_files"": [{""split"": ""train"", ""path"": ""data/fj/train.parquet""}, {""split"": ""validation"", ""path"": ""data/fj/validation.parquet""}]}, {""config_name"": ""fo"", ""data_files"": [{""split"": ""train"", ""path"": ""data/fo/train.parquet""}, {""split"": ""validation"", ""path"": ""data/fo/validation.parquet""}]}, {""config_name"": ""fr"", ""data_files"": [{""split"": ""train"", ""path"": ""data/fr/train.parquet""}, {""split"": ""validation"", ""path"": ""data/fr/validation.parquet""}]}, {""config_name"": ""frp"", ""data_files"": [{""split"": ""train"", ""path"": ""data/frp/train.parquet""}, {""split"": ""validation"", ""path"": ""data/frp/validation.parquet""}]}, {""config_name"": ""frr"", ""data_files"": [{""split"": ""train"", ""path"": ""data/frr/train.parquet""}, {""split"": ""validation"", ""path"": ""data/frr/validation.parquet""}]}, {""config_name"": ""fur"", ""data_files"": [{""split"": ""train"", ""path"": ""data/fur/train.parquet""}, {""split"": ""validation"", ""path"": ""data/fur/validation.parquet""}]}, {""config_name"": ""fy"", ""data_files"": [{""split"": ""train"", ""path"": ""data/fy/train.parquet""}, {""split"": ""validation"", ""path"": ""data/fy/validation.parquet""}]}, {""config_name"": ""ga"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ga/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ga/validation.parquet""}]}, {""config_name"": ""gag"", ""data_files"": [{""split"": ""train"", ""path"": ""data/gag/train.parquet""}, {""split"": ""validation"", ""path"": ""data/gag/validation.parquet""}]}, {""config_name"": ""gan"", ""data_files"": [{""split"": ""train"", ""path"": ""data/gan/train.parquet""}, {""split"": ""validation"", ""path"": ""data/gan/validation.parquet""}]}, {""config_name"": ""gcr"", ""data_files"": [{""split"": ""train"", ""path"": ""data/gcr/train.parquet""}, {""split"": ""validation"", ""path"": ""data/gcr/validation.parquet""}]}, {""config_name"": ""gd"", ""data_files"": [{""split"": ""train"", ""path"": ""data/gd/train.parquet""}, {""split"": ""validation"", ""path"": ""data/gd/validation.parquet""}]}, {""config_name"": ""gl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/gl/train.parquet""}, {""split"": ""validation"", ""path"": ""data/gl/validation.parquet""}]}, {""config_name"": ""glk"", ""data_files"": [{""split"": ""train"", ""path"": ""data/glk/train.parquet""}, {""split"": ""validation"", ""path"": ""data/glk/validation.parquet""}]}, {""config_name"": ""gn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/gn/train.parquet""}, {""split"": ""validation"", ""path"": ""data/gn/validation.parquet""}]}, {""config_name"": ""gom"", ""data_files"": [{""split"": ""train"", ""path"": ""data/gom/train.parquet""}, {""split"": ""validation"", ""path"": ""data/gom/validation.parquet""}]}, {""config_name"": ""gor"", ""data_files"": [{""split"": ""train"", ""path"": ""data/gor/train.parquet""}, {""split"": ""validation"", ""path"": ""data/gor/validation.parquet""}]}, {""config_name"": ""got"", ""data_files"": [{""split"": ""train"", ""path"": ""data/got/train.parquet""}, {""split"": ""validation"", ""path"": ""data/got/validation.parquet""}]}, {""config_name"": ""gpe"", ""data_files"": [{""split"": ""train"", ""path"": ""data/gpe/train.parquet""}, {""split"": ""validation"", ""path"": ""data/gpe/validation.parquet""}]}, {""config_name"": ""gu"", ""data_files"": [{""split"": ""train"", ""path"": ""data/gu/train.parquet""}, {""split"": ""validation"", ""path"": ""data/gu/validation.parquet""}]}, {""config_name"": ""guc"", ""data_files"": [{""split"": ""train"", ""path"": ""data/guc/train.parquet""}, {""split"": ""validation"", ""path"": ""data/guc/validation.parquet""}]}, {""config_name"": ""gur"", ""data_files"": [{""split"": ""train"", ""path"": ""data/gur/train.parquet""}, {""split"": ""validation"", ""path"": ""data/gur/validation.parquet""}]}, {""config_name"": ""guw"", ""data_files"": [{""split"": ""train"", ""path"": ""data/guw/train.parquet""}, {""split"": ""validation"", ""path"": ""data/guw/validation.parquet""}]}, {""config_name"": ""gv"", ""data_files"": [{""split"": ""train"", ""path"": ""data/gv/train.parquet""}, {""split"": ""validation"", ""path"": ""data/gv/validation.parquet""}]}, {""config_name"": ""ha"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ha/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ha/validation.parquet""}]}, {""config_name"": ""hak"", ""data_files"": [{""split"": ""train"", ""path"": ""data/hak/train.parquet""}, {""split"": ""validation"", ""path"": ""data/hak/validation.parquet""}]}, {""config_name"": ""haw"", ""data_files"": [{""split"": ""train"", ""path"": ""data/haw/train.parquet""}, {""split"": ""validation"", ""path"": ""data/haw/validation.parquet""}]}, {""config_name"": ""he"", ""data_files"": [{""split"": ""train"", ""path"": ""data/he/train.parquet""}, {""split"": ""validation"", ""path"": ""data/he/validation.parquet""}]}, {""config_name"": ""hi"", ""data_files"": [{""split"": ""train"", ""path"": ""data/hi/train.parquet""}, {""split"": ""validation"", ""path"": ""data/hi/validation.parquet""}]}, {""config_name"": ""hif"", ""data_files"": [{""split"": ""train"", ""path"": ""data/hif/train.parquet""}, {""split"": ""validation"", ""path"": ""data/hif/validation.parquet""}]}, {""config_name"": ""hr"", ""data_files"": [{""split"": ""train"", ""path"": ""data/hr/train.parquet""}, {""split"": ""validation"", ""path"": ""data/hr/validation.parquet""}]}, {""config_name"": ""hsb"", ""data_files"": [{""split"": ""train"", ""path"": ""data/hsb/train.parquet""}, {""split"": ""validation"", ""path"": ""data/hsb/validation.parquet""}]}, {""config_name"": ""ht"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ht/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ht/validation.parquet""}]}, {""config_name"": ""hu"", ""data_files"": [{""split"": ""train"", ""path"": ""data/hu/train.parquet""}, {""split"": ""validation"", ""path"": ""data/hu/validation.parquet""}]}, {""config_name"": ""hy"", ""data_files"": [{""split"": ""train"", ""path"": ""data/hy/train.parquet""}, {""split"": ""validation"", ""path"": ""data/hy/validation.parquet""}]}, {""config_name"": ""hyw"", ""data_files"": [{""split"": ""train"", ""path"": ""data/hyw/train.parquet""}, {""split"": ""validation"", ""path"": ""data/hyw/validation.parquet""}]}, {""config_name"": ""ia"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ia/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ia/validation.parquet""}]}, {""config_name"": ""id"", ""data_files"": [{""split"": ""train"", ""path"": ""data/id/train.parquet""}, {""split"": ""validation"", ""path"": ""data/id/validation.parquet""}]}, {""config_name"": ""ie"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ie/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ie/validation.parquet""}]}, {""config_name"": ""ig"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ig/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ig/validation.parquet""}]}, {""config_name"": ""ik"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ik/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ik/validation.parquet""}]}, {""config_name"": ""ilo"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ilo/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ilo/validation.parquet""}]}, {""config_name"": ""inh"", ""data_files"": [{""split"": ""train"", ""path"": ""data/inh/train.parquet""}, {""split"": ""validation"", ""path"": ""data/inh/validation.parquet""}]}, {""config_name"": ""io"", ""data_files"": [{""split"": ""train"", ""path"": ""data/io/train.parquet""}, {""split"": ""validation"", ""path"": ""data/io/validation.parquet""}]}, {""config_name"": ""is"", ""data_files"": [{""split"": ""train"", ""path"": ""data/is/train.parquet""}, {""split"": ""validation"", ""path"": ""data/is/validation.parquet""}]}, {""config_name"": ""it"", ""data_files"": [{""split"": ""train"", ""path"": ""data/it/train.parquet""}, {""split"": ""validation"", ""path"": ""data/it/validation.parquet""}]}, {""config_name"": ""iu"", ""data_files"": [{""split"": ""train"", ""path"": ""data/iu/train.parquet""}, {""split"": ""validation"", ""path"": ""data/iu/validation.parquet""}]}, {""config_name"": ""ja"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ja/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ja/validation.parquet""}]}, {""config_name"": ""jam"", ""data_files"": [{""split"": ""train"", ""path"": ""data/jam/train.parquet""}, {""split"": ""validation"", ""path"": ""data/jam/validation.parquet""}]}, {""config_name"": ""jbo"", ""data_files"": [{""split"": ""train"", ""path"": ""data/jbo/train.parquet""}, {""split"": ""validation"", ""path"": ""data/jbo/validation.parquet""}]}, {""config_name"": ""jv"", ""data_files"": [{""split"": ""train"", ""path"": ""data/jv/train.parquet""}, {""split"": ""validation"", ""path"": ""data/jv/validation.parquet""}]}, {""config_name"": ""ka"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ka/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ka/validation.parquet""}]}, {""config_name"": ""kaa"", ""data_files"": [{""split"": ""train"", ""path"": ""data/kaa/train.parquet""}, {""split"": ""validation"", ""path"": ""data/kaa/validation.parquet""}]}, {""config_name"": ""kab"", ""data_files"": [{""split"": ""train"", ""path"": ""data/kab/train.parquet""}, {""split"": ""validation"", ""path"": ""data/kab/validation.parquet""}]}, {""config_name"": ""kbd"", ""data_files"": [{""split"": ""train"", ""path"": ""data/kbd/train.parquet""}, {""split"": ""validation"", ""path"": ""data/kbd/validation.parquet""}]}, {""config_name"": ""kbp"", ""data_files"": [{""split"": ""train"", ""path"": ""data/kbp/train.parquet""}, {""split"": ""validation"", ""path"": ""data/kbp/validation.parquet""}]}, {""config_name"": ""kcg"", ""data_files"": [{""split"": ""train"", ""path"": ""data/kcg/train.parquet""}, {""split"": ""validation"", ""path"": ""data/kcg/validation.parquet""}]}, {""config_name"": ""kg"", ""data_files"": [{""split"": ""train"", ""path"": ""data/kg/train.parquet""}, {""split"": ""validation"", ""path"": ""data/kg/validation.parquet""}]}, {""config_name"": ""ki"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ki/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ki/validation.parquet""}]}, {""config_name"": ""kk"", ""data_files"": [{""split"": ""train"", ""path"": ""data/kk/train.parquet""}, {""split"": ""validation"", ""path"": ""data/kk/validation.parquet""}]}, {""config_name"": ""kl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/kl/train.parquet""}, {""split"": ""validation"", ""path"": ""data/kl/validation.parquet""}]}, {""config_name"": ""km"", ""data_files"": [{""split"": ""train"", ""path"": ""data/km/train.parquet""}, {""split"": ""validation"", ""path"": ""data/km/validation.parquet""}]}, {""config_name"": ""kn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/kn/train.parquet""}, {""split"": ""validation"", ""path"": ""data/kn/validation.parquet""}]}, {""config_name"": ""ko"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ko/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ko/validation.parquet""}]}, {""config_name"": ""koi"", ""data_files"": [{""split"": ""train"", ""path"": ""data/koi/train.parquet""}, {""split"": ""validation"", ""path"": ""data/koi/validation.parquet""}]}, {""config_name"": ""krc"", ""data_files"": [{""split"": ""train"", ""path"": ""data/krc/train.parquet""}, {""split"": ""validation"", ""path"": ""data/krc/validation.parquet""}]}, {""config_name"": ""ks"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ks/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ks/validation.parquet""}]}, {""config_name"": ""ksh"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ksh/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ksh/validation.parquet""}]}, {""config_name"": ""ku"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ku/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ku/validation.parquet""}]}, {""config_name"": ""kv"", ""data_files"": [{""split"": ""train"", ""path"": ""data/kv/train.parquet""}, {""split"": ""validation"", ""path"": ""data/kv/validation.parquet""}]}, {""config_name"": ""kw"", ""data_files"": [{""split"": ""train"", ""path"": ""data/kw/train.parquet""}, {""split"": ""validation"", ""path"": ""data/kw/validation.parquet""}]}, {""config_name"": ""ky"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ky/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ky/validation.parquet""}]}, {""config_name"": ""la"", ""data_files"": [{""split"": ""train"", ""path"": ""data/la/train.parquet""}, {""split"": ""validation"", ""path"": ""data/la/validation.parquet""}]}, {""config_name"": ""lad"", ""data_files"": [{""split"": ""train"", ""path"": ""data/lad/train.parquet""}, {""split"": ""validation"", ""path"": ""data/lad/validation.parquet""}]}, {""config_name"": ""lb"", ""data_files"": [{""split"": ""train"", ""path"": ""data/lb/train.parquet""}, {""split"": ""validation"", ""path"": ""data/lb/validation.parquet""}]}, {""config_name"": ""lbe"", ""data_files"": [{""split"": ""train"", ""path"": ""data/lbe/train.parquet""}, {""split"": ""validation"", ""path"": ""data/lbe/validation.parquet""}]}, {""config_name"": ""lez"", ""data_files"": [{""split"": ""train"", ""path"": ""data/lez/train.parquet""}, {""split"": ""validation"", ""path"": ""data/lez/validation.parquet""}]}, {""config_name"": ""lfn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/lfn/train.parquet""}, {""split"": ""validation"", ""path"": ""data/lfn/validation.parquet""}]}, {""config_name"": ""lg"", ""data_files"": [{""split"": ""train"", ""path"": ""data/lg/train.parquet""}, {""split"": ""validation"", ""path"": ""data/lg/validation.parquet""}]}, {""config_name"": ""li"", ""data_files"": [{""split"": ""train"", ""path"": ""data/li/train.parquet""}, {""split"": ""validation"", ""path"": ""data/li/validation.parquet""}]}, {""config_name"": ""lij"", ""data_files"": [{""split"": ""train"", ""path"": ""data/lij/train.parquet""}, {""split"": ""validation"", ""path"": ""data/lij/validation.parquet""}]}, {""config_name"": ""lld"", ""data_files"": [{""split"": ""train"", ""path"": ""data/lld/train.parquet""}, {""split"": ""validation"", ""path"": ""data/lld/validation.parquet""}]}, {""config_name"": ""lmo"", ""data_files"": [{""split"": ""train"", ""path"": ""data/lmo/train.parquet""}, {""split"": ""validation"", ""path"": ""data/lmo/validation.parquet""}]}, {""config_name"": ""ln"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ln/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ln/validation.parquet""}]}, {""config_name"": ""lo"", ""data_files"": [{""split"": ""train"", ""path"": ""data/lo/train.parquet""}, {""split"": ""validation"", ""path"": ""data/lo/validation.parquet""}]}, {""config_name"": ""lt"", ""data_files"": [{""split"": ""train"", ""path"": ""data/lt/train.parquet""}, {""split"": ""validation"", ""path"": ""data/lt/validation.parquet""}]}, {""config_name"": ""ltg"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ltg/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ltg/validation.parquet""}]}, {""config_name"": ""lv"", ""data_files"": [{""split"": ""train"", ""path"": ""data/lv/train.parquet""}, {""split"": ""validation"", ""path"": ""data/lv/validation.parquet""}]}, {""config_name"": ""mad"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mad/train.parquet""}, {""split"": ""validation"", ""path"": ""data/mad/validation.parquet""}]}, {""config_name"": ""mai"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mai/train.parquet""}, {""split"": ""validation"", ""path"": ""data/mai/validation.parquet""}]}, {""config_name"": ""map_bms"", ""data_files"": [{""split"": ""train"", ""path"": ""data/map_bms/train.parquet""}, {""split"": ""validation"", ""path"": ""data/map_bms/validation.parquet""}]}, {""config_name"": ""mdf"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mdf/train.parquet""}, {""split"": ""validation"", ""path"": ""data/mdf/validation.parquet""}]}, {""config_name"": ""mg"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mg/train.parquet""}, {""split"": ""validation"", ""path"": ""data/mg/validation.parquet""}]}, {""config_name"": ""mhr"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mhr/train.parquet""}, {""split"": ""validation"", ""path"": ""data/mhr/validation.parquet""}]}, {""config_name"": ""mi"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mi/train.parquet""}, {""split"": ""validation"", ""path"": ""data/mi/validation.parquet""}]}, {""config_name"": ""min"", ""data_files"": [{""split"": ""train"", ""path"": ""data/min/train.parquet""}, {""split"": ""validation"", ""path"": ""data/min/validation.parquet""}]}, {""config_name"": ""mk"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mk/train.parquet""}, {""split"": ""validation"", ""path"": ""data/mk/validation.parquet""}]}, {""config_name"": ""ml"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ml/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ml/validation.parquet""}]}, {""config_name"": ""mn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mn/train.parquet""}, {""split"": ""validation"", ""path"": ""data/mn/validation.parquet""}]}, {""config_name"": ""mni"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mni/train.parquet""}, {""split"": ""validation"", ""path"": ""data/mni/validation.parquet""}]}, {""config_name"": ""mnw"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mnw/train.parquet""}, {""split"": ""validation"", ""path"": ""data/mnw/validation.parquet""}]}, {""config_name"": ""mr"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mr/train.parquet""}, {""split"": ""validation"", ""path"": ""data/mr/validation.parquet""}]}, {""config_name"": ""mrj"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mrj/train.parquet""}, {""split"": ""validation"", ""path"": ""data/mrj/validation.parquet""}]}, {""config_name"": ""ms"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ms/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ms/validation.parquet""}]}, {""config_name"": ""mt"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mt/train.parquet""}, {""split"": ""validation"", ""path"": ""data/mt/validation.parquet""}]}, {""config_name"": ""mwl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mwl/train.parquet""}, {""split"": ""validation"", ""path"": ""data/mwl/validation.parquet""}]}, {""config_name"": ""my"", ""data_files"": [{""split"": ""train"", ""path"": ""data/my/train.parquet""}, {""split"": ""validation"", ""path"": ""data/my/validation.parquet""}]}, {""config_name"": ""myv"", ""data_files"": [{""split"": ""train"", ""path"": ""data/myv/train.parquet""}, {""split"": ""validation"", ""path"": ""data/myv/validation.parquet""}]}, {""config_name"": ""mzn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/mzn/train.parquet""}, {""split"": ""validation"", ""path"": ""data/mzn/validation.parquet""}]}, {""config_name"": ""nah"", ""data_files"": [{""split"": ""train"", ""path"": ""data/nah/train.parquet""}, {""split"": ""validation"", ""path"": ""data/nah/validation.parquet""}]}, {""config_name"": ""nap"", ""data_files"": [{""split"": ""train"", ""path"": ""data/nap/train.parquet""}, {""split"": ""validation"", ""path"": ""data/nap/validation.parquet""}]}, {""config_name"": ""nds"", ""data_files"": [{""split"": ""train"", ""path"": ""data/nds/train.parquet""}, {""split"": ""validation"", ""path"": ""data/nds/validation.parquet""}]}, {""config_name"": ""nds_nl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/nds_nl/train.parquet""}, {""split"": ""validation"", ""path"": ""data/nds_nl/validation.parquet""}]}, {""config_name"": ""ne"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ne/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ne/validation.parquet""}]}, {""config_name"": ""new"", ""data_files"": [{""split"": ""train"", ""path"": ""data/new/train.parquet""}, {""split"": ""validation"", ""path"": ""data/new/validation.parquet""}]}, {""config_name"": ""nia"", ""data_files"": [{""split"": ""train"", ""path"": ""data/nia/train.parquet""}, {""split"": ""validation"", ""path"": ""data/nia/validation.parquet""}]}, {""config_name"": ""nl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/nl/train.parquet""}, {""split"": ""validation"", ""path"": ""data/nl/validation.parquet""}]}, {""config_name"": ""nn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/nn/train.parquet""}, {""split"": ""validation"", ""path"": ""data/nn/validation.parquet""}]}, {""config_name"": ""no"", ""data_files"": [{""split"": ""train"", ""path"": ""data/no/train.parquet""}, {""split"": ""validation"", ""path"": ""data/no/validation.parquet""}]}, {""config_name"": ""nov"", ""data_files"": [{""split"": ""train"", ""path"": ""data/nov/train.parquet""}, {""split"": ""validation"", ""path"": ""data/nov/validation.parquet""}]}, {""config_name"": ""nqo"", ""data_files"": [{""split"": ""train"", ""path"": ""data/nqo/train.parquet""}, {""split"": ""validation"", ""path"": ""data/nqo/validation.parquet""}]}, {""config_name"": ""nrm"", ""data_files"": [{""split"": ""train"", ""path"": ""data/nrm/train.parquet""}, {""split"": ""validation"", ""path"": ""data/nrm/validation.parquet""}]}, {""config_name"": ""nso"", ""data_files"": [{""split"": ""train"", ""path"": ""data/nso/train.parquet""}, {""split"": ""validation"", ""path"": ""data/nso/validation.parquet""}]}, {""config_name"": ""nv"", ""data_files"": [{""split"": ""train"", ""path"": ""data/nv/train.parquet""}, {""split"": ""validation"", ""path"": ""data/nv/validation.parquet""}]}, {""config_name"": ""ny"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ny/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ny/validation.parquet""}]}, {""config_name"": ""oc"", ""data_files"": [{""split"": ""train"", ""path"": ""data/oc/train.parquet""}, {""split"": ""validation"", ""path"": ""data/oc/validation.parquet""}]}, {""config_name"": ""olo"", ""data_files"": [{""split"": ""train"", ""path"": ""data/olo/train.parquet""}, {""split"": ""validation"", ""path"": ""data/olo/validation.parquet""}]}, {""config_name"": ""om"", ""data_files"": [{""split"": ""train"", ""path"": ""data/om/train.parquet""}, {""split"": ""validation"", ""path"": ""data/om/validation.parquet""}]}, {""config_name"": ""or"", ""data_files"": [{""split"": ""train"", ""path"": ""data/or/train.parquet""}, {""split"": ""validation"", ""path"": ""data/or/validation.parquet""}]}, {""config_name"": ""os"", ""data_files"": [{""split"": ""train"", ""path"": ""data/os/train.parquet""}, {""split"": ""validation"", ""path"": ""data/os/validation.parquet""}]}, {""config_name"": ""pa"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pa/train.parquet""}, {""split"": ""validation"", ""path"": ""data/pa/validation.parquet""}]}, {""config_name"": ""pag"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pag/train.parquet""}, {""split"": ""validation"", ""path"": ""data/pag/validation.parquet""}]}, {""config_name"": ""pam"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pam/train.parquet""}, {""split"": ""validation"", ""path"": ""data/pam/validation.parquet""}]}, {""config_name"": ""pap"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pap/train.parquet""}, {""split"": ""validation"", ""path"": ""data/pap/validation.parquet""}]}, {""config_name"": ""pcd"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pcd/train.parquet""}, {""split"": ""validation"", ""path"": ""data/pcd/validation.parquet""}]}, {""config_name"": ""pcm"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pcm/train.parquet""}, {""split"": ""validation"", ""path"": ""data/pcm/validation.parquet""}]}, {""config_name"": ""pdc"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pdc/train.parquet""}, {""split"": ""validation"", ""path"": ""data/pdc/validation.parquet""}]}, {""config_name"": ""pfl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pfl/train.parquet""}, {""split"": ""validation"", ""path"": ""data/pfl/validation.parquet""}]}, {""config_name"": ""pi"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pi/train.parquet""}, {""split"": ""validation"", ""path"": ""data/pi/validation.parquet""}]}, {""config_name"": ""pih"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pih/train.parquet""}, {""split"": ""validation"", ""path"": ""data/pih/validation.parquet""}]}, {""config_name"": ""pl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pl/train.parquet""}, {""split"": ""validation"", ""path"": ""data/pl/validation.parquet""}]}, {""config_name"": ""pms"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pms/train.parquet""}, {""split"": ""validation"", ""path"": ""data/pms/validation.parquet""}]}, {""config_name"": ""pnb"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pnb/train.parquet""}, {""split"": ""validation"", ""path"": ""data/pnb/validation.parquet""}]}, {""config_name"": ""pnt"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pnt/train.parquet""}, {""split"": ""validation"", ""path"": ""data/pnt/validation.parquet""}]}, {""config_name"": ""ps"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ps/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ps/validation.parquet""}]}, {""config_name"": ""pt"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pt/train.parquet""}, {""split"": ""validation"", ""path"": ""data/pt/validation.parquet""}]}, {""config_name"": ""pwn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/pwn/train.parquet""}, {""split"": ""validation"", ""path"": ""data/pwn/validation.parquet""}]}, {""config_name"": ""qu"", ""data_files"": [{""split"": ""train"", ""path"": ""data/qu/train.parquet""}, {""split"": ""validation"", ""path"": ""data/qu/validation.parquet""}]}, {""config_name"": ""rm"", ""data_files"": [{""split"": ""train"", ""path"": ""data/rm/train.parquet""}, {""split"": ""validation"", ""path"": ""data/rm/validation.parquet""}]}, {""config_name"": ""rmy"", ""data_files"": [{""split"": ""train"", ""path"": ""data/rmy/train.parquet""}, {""split"": ""validation"", ""path"": ""data/rmy/validation.parquet""}]}, {""config_name"": ""rn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/rn/train.parquet""}, {""split"": ""validation"", ""path"": ""data/rn/validation.parquet""}]}, {""config_name"": ""ro"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ro/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ro/validation.parquet""}]}, {""config_name"": ""roa_rup"", ""data_files"": [{""split"": ""train"", ""path"": ""data/roa_rup/train.parquet""}, {""split"": ""validation"", ""path"": ""data/roa_rup/validation.parquet""}]}, {""config_name"": ""roa_tara"", ""data_files"": [{""split"": ""train"", ""path"": ""data/roa_tara/train.parquet""}, {""split"": ""validation"", ""path"": ""data/roa_tara/validation.parquet""}]}, {""config_name"": ""ru"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ru/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ru/validation.parquet""}]}, {""config_name"": ""rue"", ""data_files"": [{""split"": ""train"", ""path"": ""data/rue/train.parquet""}, {""split"": ""validation"", ""path"": ""data/rue/validation.parquet""}]}, {""config_name"": ""rw"", ""data_files"": [{""split"": ""train"", ""path"": ""data/rw/train.parquet""}, {""split"": ""validation"", ""path"": ""data/rw/validation.parquet""}]}, {""config_name"": ""sa"", ""data_files"": [{""split"": ""train"", ""path"": ""data/sa/train.parquet""}, {""split"": ""validation"", ""path"": ""data/sa/validation.parquet""}]}, {""config_name"": ""sah"", ""data_files"": [{""split"": ""train"", ""path"": ""data/sah/train.parquet""}, {""split"": ""validation"", ""path"": ""data/sah/validation.parquet""}]}, {""config_name"": ""sat"", ""data_files"": [{""split"": ""train"", ""path"": ""data/sat/train.parquet""}, {""split"": ""validation"", ""path"": ""data/sat/validation.parquet""}]}, {""config_name"": ""sc"", ""data_files"": [{""split"": ""train"", ""path"": ""data/sc/train.parquet""}, {""split"": ""validation"", ""path"": ""data/sc/validation.parquet""}]}, {""config_name"": ""scn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/scn/train.parquet""}, {""split"": ""validation"", ""path"": ""data/scn/validation.parquet""}]}, {""config_name"": ""sco"", ""data_files"": [{""split"": ""train"", ""path"": ""data/sco/train.parquet""}, {""split"": ""validation"", ""path"": ""data/sco/validation.parquet""}]}, {""config_name"": ""sd"", ""data_files"": [{""split"": ""train"", ""path"": ""data/sd/train.parquet""}, {""split"": ""validation"", ""path"": ""data/sd/validation.parquet""}]}, {""config_name"": ""se"", ""data_files"": [{""split"": ""train"", ""path"": ""data/se/train.parquet""}, {""split"": ""validation"", ""path"": ""data/se/validation.parquet""}]}, {""config_name"": ""sg"", ""data_files"": [{""split"": ""train"", ""path"": ""data/sg/train.parquet""}, {""split"": ""validation"", ""path"": ""data/sg/validation.parquet""}]}, {""config_name"": ""sh"", ""data_files"": [{""split"": ""train"", ""path"": ""data/sh/train.parquet""}, {""split"": ""validation"", ""path"": ""data/sh/validation.parquet""}]}, {""config_name"": ""shi"", ""data_files"": [{""split"": ""train"", ""path"": ""data/shi/train.parquet""}, {""split"": ""validation"", ""path"": ""data/shi/validation.parquet""}]}, {""config_name"": ""shn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/shn/train.parquet""}, {""split"": ""validation"", ""path"": ""data/shn/validation.parquet""}]}, {""config_name"": ""si"", ""data_files"": [{""split"": ""train"", ""path"": ""data/si/train.parquet""}, {""split"": ""validation"", ""path"": ""data/si/validation.parquet""}]}, {""config_name"": ""simple"", ""data_files"": [{""split"": ""train"", ""path"": ""data/simple/train.parquet""}, {""split"": ""validation"", ""path"": ""data/simple/validation.parquet""}]}, {""config_name"": ""sk"", ""data_files"": [{""split"": ""train"", ""path"": ""data/sk/train.parquet""}, {""split"": ""validation"", ""path"": ""data/sk/validation.parquet""}]}, {""config_name"": ""skr"", ""data_files"": [{""split"": ""train"", ""path"": ""data/skr/train.parquet""}, {""split"": ""validation"", ""path"": ""data/skr/validation.parquet""}]}, {""config_name"": ""sl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/sl/train.parquet""}, {""split"": ""validation"", ""path"": ""data/sl/validation.parquet""}]}, {""config_name"": ""sm"", ""data_files"": [{""split"": ""train"", ""path"": ""data/sm/train.parquet""}, {""split"": ""validation"", ""path"": ""data/sm/validation.parquet""}]}, {""config_name"": ""smn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/smn/train.parquet""}, {""split"": ""validation"", ""path"": ""data/smn/validation.parquet""}]}, {""config_name"": ""sn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/sn/train.parquet""}, {""split"": ""validation"", ""path"": ""data/sn/validation.parquet""}]}, {""config_name"": ""so"", ""data_files"": [{""split"": ""train"", ""path"": ""data/so/train.parquet""}, {""split"": ""validation"", ""path"": ""data/so/validation.parquet""}]}, {""config_name"": ""sq"", ""data_files"": [{""split"": ""train"", ""path"": ""data/sq/train.parquet""}, {""split"": ""validation"", ""path"": ""data/sq/validation.parquet""}]}, {""config_name"": ""sr"", ""data_files"": [{""split"": ""train"", ""path"": ""data/sr/train.parquet""}, {""split"": ""validation"", ""path"": ""data/sr/validation.parquet""}]}, {""config_name"": ""srn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/srn/train.parquet""}, {""split"": ""validation"", ""path"": ""data/srn/validation.parquet""}]}, {""config_name"": ""ss"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ss/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ss/validation.parquet""}]}, {""config_name"": ""st"", ""data_files"": [{""split"": ""train"", ""path"": ""data/st/train.parquet""}, {""split"": ""validation"", ""path"": ""data/st/validation.parquet""}]}, {""config_name"": ""stq"", ""data_files"": [{""split"": ""train"", ""path"": ""data/stq/train.parquet""}, {""split"": ""validation"", ""path"": ""data/stq/validation.parquet""}]}, {""config_name"": ""su"", ""data_files"": [{""split"": ""train"", ""path"": ""data/su/train.parquet""}, {""split"": ""validation"", ""path"": ""data/su/validation.parquet""}]}, {""config_name"": ""sv"", ""data_files"": [{""split"": ""train"", ""path"": ""data/sv/train.parquet""}, {""split"": ""validation"", ""path"": ""data/sv/validation.parquet""}]}, {""config_name"": ""sw"", ""data_files"": [{""split"": ""train"", ""path"": ""data/sw/train.parquet""}, {""split"": ""validation"", ""path"": ""data/sw/validation.parquet""}]}, {""config_name"": ""szl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/szl/train.parquet""}, {""split"": ""validation"", ""path"": ""data/szl/validation.parquet""}]}, {""config_name"": ""szy"", ""data_files"": [{""split"": ""train"", ""path"": ""data/szy/train.parquet""}, {""split"": ""validation"", ""path"": ""data/szy/validation.parquet""}]}, {""config_name"": ""ta"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ta/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ta/validation.parquet""}]}, {""config_name"": ""tay"", ""data_files"": [{""split"": ""train"", ""path"": ""data/tay/train.parquet""}, {""split"": ""validation"", ""path"": ""data/tay/validation.parquet""}]}, {""config_name"": ""tcy"", ""data_files"": [{""split"": ""train"", ""path"": ""data/tcy/train.parquet""}, {""split"": ""validation"", ""path"": ""data/tcy/validation.parquet""}]}, {""config_name"": ""te"", ""data_files"": [{""split"": ""train"", ""path"": ""data/te/train.parquet""}, {""split"": ""validation"", ""path"": ""data/te/validation.parquet""}]}, {""config_name"": ""tet"", ""data_files"": [{""split"": ""train"", ""path"": ""data/tet/train.parquet""}, {""split"": ""validation"", ""path"": ""data/tet/validation.parquet""}]}, {""config_name"": ""tg"", ""data_files"": [{""split"": ""train"", ""path"": ""data/tg/train.parquet""}, {""split"": ""validation"", ""path"": ""data/tg/validation.parquet""}]}, {""config_name"": ""th"", ""data_files"": [{""split"": ""train"", ""path"": ""data/th/train.parquet""}, {""split"": ""validation"", ""path"": ""data/th/validation.parquet""}]}, {""config_name"": ""ti"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ti/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ti/validation.parquet""}]}, {""config_name"": ""tk"", ""data_files"": [{""split"": ""train"", ""path"": ""data/tk/train.parquet""}, {""split"": ""validation"", ""path"": ""data/tk/validation.parquet""}]}, {""config_name"": ""tl"", ""data_files"": [{""split"": ""train"", ""path"": ""data/tl/train.parquet""}, {""split"": ""validation"", ""path"": ""data/tl/validation.parquet""}]}, {""config_name"": ""tn"", ""data_files"": [{""split"": ""train"", ""path"": ""data/tn/train.parquet""}, {""split"": ""validation"", ""path"": ""data/tn/validation.parquet""}]}, {""config_name"": ""to"", ""data_files"": [{""split"": ""train"", ""path"": ""data/to/train.parquet""}, {""split"": ""validation"", ""path"": ""data/to/validation.parquet""}]}, {""config_name"": ""tpi"", ""data_files"": [{""split"": ""train"", ""path"": ""data/tpi/train.parquet""}, {""split"": ""validation"", ""path"": ""data/tpi/validation.parquet""}]}, {""config_name"": ""tr"", ""data_files"": [{""split"": ""train"", ""path"": ""data/tr/train.parquet""}, {""split"": ""validation"", ""path"": ""data/tr/validation.parquet""}]}, {""config_name"": ""trv"", ""data_files"": [{""split"": ""train"", ""path"": ""data/trv/train.parquet""}, {""split"": ""validation"", ""path"": ""data/trv/validation.parquet""}]}, {""config_name"": ""ts"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ts/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ts/validation.parquet""}]}, {""config_name"": ""tt"", ""data_files"": [{""split"": ""train"", ""path"": ""data/tt/train.parquet""}, {""split"": ""validation"", ""path"": ""data/tt/validation.parquet""}]}, {""config_name"": ""tum"", ""data_files"": [{""split"": ""train"", ""path"": ""data/tum/train.parquet""}, {""split"": ""validation"", ""path"": ""data/tum/validation.parquet""}]}, {""config_name"": ""tw"", ""data_files"": [{""split"": ""train"", ""path"": ""data/tw/train.parquet""}, {""split"": ""validation"", ""path"": ""data/tw/validation.parquet""}]}, {""config_name"": ""ty"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ty/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ty/validation.parquet""}]}, {""config_name"": ""tyv"", ""data_files"": [{""split"": ""train"", ""path"": ""data/tyv/train.parquet""}, {""split"": ""validation"", ""path"": ""data/tyv/validation.parquet""}]}, {""config_name"": ""udm"", ""data_files"": [{""split"": ""train"", ""path"": ""data/udm/train.parquet""}, {""split"": ""validation"", ""path"": ""data/udm/validation.parquet""}]}, {""config_name"": ""ug"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ug/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ug/validation.parquet""}]}, {""config_name"": ""uk"", ""data_files"": [{""split"": ""train"", ""path"": ""data/uk/train.parquet""}, {""split"": ""validation"", ""path"": ""data/uk/validation.parquet""}]}, {""config_name"": ""ur"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ur/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ur/validation.parquet""}]}, {""config_name"": ""uz"", ""data_files"": [{""split"": ""train"", ""path"": ""data/uz/train.parquet""}, {""split"": ""validation"", ""path"": ""data/uz/validation.parquet""}]}, {""config_name"": ""ve"", ""data_files"": [{""split"": ""train"", ""path"": ""data/ve/train.parquet""}, {""split"": ""validation"", ""path"": ""data/ve/validation.parquet""}]}, {""config_name"": ""vec"", ""data_files"": [{""split"": ""train"", ""path"": ""data/vec/train.parquet""}, {""split"": ""validation"", ""path"": ""data/vec/validation.parquet""}]}, {""config_name"": ""vep"", ""data_files"": [{""split"": ""train"", ""path"": ""data/vep/train.parquet""}, {""split"": ""validation"", ""path"": ""data/vep/validation.parquet""}]}, {""config_name"": ""vi"", ""data_files"": [{""split"": ""train"", ""path"": ""data/vi/train.parquet""}, {""split"": ""validation"", ""path"": ""data/vi/validation.parquet""}]}, {""config_name"": ""vls"", ""data_files"": [{""split"": ""train"", ""path"": ""data/vls/train.parquet""}, {""split"": ""validation"", ""path"": ""data/vls/validation.parquet""}]}, {""config_name"": ""vo"", ""data_files"": [{""split"": ""train"", ""path"": ""data/vo/train.parquet""}, {""split"": ""validation"", ""path"": ""data/vo/validation.parquet""}]}, {""config_name"": ""wa"", ""data_files"": [{""split"": ""train"", ""path"": ""data/wa/train.parquet""}, {""split"": ""validation"", ""path"": ""data/wa/validation.parquet""}]}, {""config_name"": ""war"", ""data_files"": [{""split"": ""train"", ""path"": ""data/war/train.parquet""}, {""split"": ""validation"", ""path"": ""data/war/validation.parquet""}]}, {""config_name"": ""wo"", ""data_files"": [{""split"": ""train"", ""path"": ""data/wo/train.parquet""}, {""split"": ""validation"", ""path"": ""data/wo/validation.parquet""}]}, {""config_name"": ""wuu"", ""data_files"": [{""split"": ""train"", ""path"": ""data/wuu/train.parquet""}, {""split"": ""validation"", ""path"": ""data/wuu/validation.parquet""}]}, {""config_name"": ""xal"", ""data_files"": [{""split"": ""train"", ""path"": ""data/xal/train.parquet""}, {""split"": ""validation"", ""path"": ""data/xal/validation.parquet""}]}, {""config_name"": ""xh"", ""data_files"": [{""split"": ""train"", ""path"": ""data/xh/train.parquet""}, {""split"": ""validation"", ""path"": ""data/xh/validation.parquet""}]}, {""config_name"": ""xmf"", ""data_files"": [{""split"": ""train"", ""path"": ""data/xmf/train.parquet""}, {""split"": ""validation"", ""path"": ""data/xmf/validation.parquet""}]}, {""config_name"": ""yi"", ""data_files"": [{""split"": ""train"", ""path"": ""data/yi/train.parquet""}, {""split"": ""validation"", ""path"": ""data/yi/validation.parquet""}]}, {""config_name"": ""yo"", ""data_files"": [{""split"": ""train"", ""path"": ""data/yo/train.parquet""}, {""split"": ""validation"", ""path"": ""data/yo/validation.parquet""}]}, {""config_name"": ""za"", ""data_files"": [{""split"": ""train"", ""path"": ""data/za/train.parquet""}, {""split"": ""validation"", ""path"": ""data/za/validation.parquet""}]}, {""config_name"": ""zea"", ""data_files"": [{""split"": ""train"", ""path"": ""data/zea/train.parquet""}, {""split"": ""validation"", ""path"": ""data/zea/validation.parquet""}]}, {""config_name"": ""zh"", ""data_files"": [{""split"": ""train"", ""path"": ""data/zh/train.parquet""}, {""split"": ""validation"", ""path"": ""data/zh/validation.parquet""}]}, {""config_name"": ""zh_classical"", ""data_files"": [{""split"": ""train"", ""path"": ""data/zh_classical/train.parquet""}, {""split"": ""validation"", ""path"": ""data/zh_classical/validation.parquet""}]}, {""config_name"": ""zh_min_nan"", ""data_files"": [{""split"": ""train"", ""path"": ""data/zh_min_nan/train.parquet""}, {""split"": ""validation"", ""path"": ""data/zh_min_nan/validation.parquet""}]}, {""config_name"": ""zh_yue"", ""data_files"": [{""split"": ""train"", ""path"": ""data/zh_yue/train.parquet""}, {""split"": ""validation"", ""path"": ""data/zh_yue/validation.parquet""}]}, {""config_name"": ""zu"", ""data_files"": [{""split"": ""train"", ""path"": ""data/zu/train.parquet""}, {""split"": ""validation"", ""path"": ""data/zu/validation.parquet""}]}]}","# Dataset Card for WikiAnc + +## Table of Contents +- [Dataset Description](#dataset-description) + - [Dataset Summary](#dataset-summary) + - [Supported Tasks](#supported-tasks) + - [Languages](#languages) +- [Dataset Structure](#dataset-structure) + - [Data Instances](#data-instances) + - [Data Fields](#data-fields) + - [Data Splits](#data-splits) +- [Additional Information](#additional-information) + - [Licensing Information](#licensing-information) + +## Dataset Description + +- **Repository:** [WikiAnc repository](https://github.com/cyanic-selkie/wikianc) + +### Dataset Summary + +The WikiAnc dataset is an automatically generated dataset from Wikipedia (all languages) and Wikidata dumps (August, 2023). + +The code for generating the dataset can be found [here](https://github.com/cyanic-selkie/wikianc). + +### Supported Tasks + +- `wikificiation`: The dataset can be used to train a model for Wikification. +- `named-entity-linking`: The dataset can be used to train a model for Named Entity Linking. + +### Languages + +The text in the dataset is in all 320 Wikipedia languages. The full list can be found in the table below. + +## Dataset Structure + +### Data Instances + +A typical data point represents a paragraph in a Wikipedia article. + +The `paragraph_text` field contains the original text in an NFC normalized, UTF-8 encoded string. + +The `paragraph_anchors` field contains a list of anchors, each represented by a struct with the inclusive starting UTF-8 code point `start` field, exclusive ending UTF-8 code point `end` field, a nullable `qid` field, a nullable `pageid` field, and an NFC normalized, UTF-8 encoded `title` (Wikipedia) field. + +Additionally, each paragraph has `article_title`, `article_pageid`, and (nullable) `article_qid` fields referring to the article the paragraph came from. + +There is also a nullable, NFC normalized, UTF-8 encoded `section_heading` field, and an integer `section_level` field referring to the heading (if it exists) of the article section, and the level in the section hierarchy that the paragraph came from. + +The `qid` fields refers to Wikidata's QID identifiers, while the `pageid` and `title` fields refer to Wikipedia's pageID and title identifiers (there is a one-to-one mapping between pageIDs and titles). + +**NOTE:** An anchor will always have a `title`, but that doesn't mean it has to have a `pageid`. This is because Wikipedia allows defining anchors to nonexistent articles. + +An example from the WikiAnc EN test set looks as follows: + +``` +{ + ""uuid"": ""5f74e678-944f-4761-a5e0-b6426f6f61b8"", + ""article_title"": ""Climatius"", + ""article_pageid"": 5394373, + ""article_qid"": 867987, + ""section_heading"": null, + ""section_level"": 0, + ""paragraph_text"": ""It was a small fish, at 7.5 cm, and to discourage predators, Climatius sported fifteen sharp spines. There was one spine each on the paired pelvic and pectoral fins, and on the aingle anal and two dorsal fins, and a four pairs without fins on the fish's underside."", + ""paragraph_anchors"": [ + { + ""start"": 140, + ""end"": 146, + ""qid"": 3335089, + ""pageid"": 56849833, + ""title"": ""Pelvic_fin"" + }, + { + ""start"": 151, + ""end"": 159, + ""qid"": 4162555, + ""pageid"": 331956, + ""title"": ""Pectoral_fin"" + }, + { + ""start"": 184, + ""end"": 188, + ""qid"": 4162555, + ""pageid"": 331958, + ""title"": ""Anal_fin"" + }, + { + ""start"": 197, + ""end"": 208, + ""qid"": 1568355, + ""pageid"": 294244, + ""title"": ""Dorsal_fin"" + } + ] +} +``` + +### Data Fields + +- `uuid`: a UTF-8 encoded string representing a v4 UUID that uniquely identifies the example +- `article_title`: an NFC normalized, UTF-8 encoded Wikipedia title of the article; spaces are replaced with underscores +- `article_pageid`: an integer representing the Wikipedia pageID of the article +- `article_qid`: an integer representing the Wikidata QID this article refers to; it can be null if the entity didn't exist in Wikidata at the time of the creation of the original dataset +- `section_heading`: a nullable, NFC normalized, UTF-8 encoded string representing the section heading +- `section_level`: an integer representing the level of the section in the section hierarchy +- `paragraph_text`: an NFC normalized, UTF-8 encoded string representing the paragraph +- `paragraph_anchors`: a list of structs representing anchors, each anchor has: + - `start`: an integer representing the inclusive starting UTF-8 code point of the anchors + - `end`: an integer representing the exclusive ending UTF-8 code point of the anchor + - `qid`: a nullable integer representing the Wikidata QID this anchor refers to; it can be null if the entity didn't exist in Wikidata at the time of the creation of the original dataset + - `pageid`: a nullable integer representing the Wikipedia pageID of the anchor; it can be null if the article didn't exist in Wikipedia at the time of the creation of the original dataset + - `title`: an NFC normalized, UTF-8 encoded string representing the Wikipedia title of the anchor; spaces are replaced with underscores; can refer to a nonexistent Wikipedia article + +### Data Splits + +The data is split into training, validation and test sets; paragraphs belonging to the same article aren't necessarily in the same split. The final split sizes are as follows: + +#### Train + +| | Articles | Paragraphs | Anchors | Anchors with QIDs | Anchors with PageIDs | +| :-- | --: | --: | --: | --: | --: | +| ab | 2378 | 5678 | 10515 | 3649 | 3650 | +| ace | 12591 | 23969 | 48638 | 25150 | 25175 | +| ady | 596 | 1662 | 2694 | 1593 | 1606 | +| af | 104470 | 399038 | 985640 | 900596 | 900967 | +| als | 27999 | 165085 | 402049 | 294742 | 294744 | +| alt | 1043 | 7468 | 9158 | 5446 | 5452 | +| am | 13576 | 46318 | 90051 | 51915 | 52173 | +| ami | 1582 | 12428 | 6080 | 1505 | 2579 | +| an | 40179 | 121367 | 669830 | 516248 | 516822 | +| ang | 3833 | 9664 | 24297 | 10189 | 10229 | +| anp | 2506 | 6865 | 14560 | 3825 | 5061 | +| ar | 1132271 | 3617491 | 11657228 | 11240112 | 11244160 | +| arc | 1844 | 3766 | 9232 | 5460 | 5545 | +| ary | 6736 | 17049 | 50185 | 34193 | 34227 | +| arz | 1579782 | 3693549 | 7879303 | 6906799 | 6917393 | +| as | 11947 | 77835 | 122760 | 67594 | 67720 | +| ast | 126992 | 877278 | 2952000 | 1775764 | 1777383 | +| atj | 1872 | 3820 | 6544 | 3247 | 3365 | +| av | 3048 | 8542 | 16115 | 8895 | 9000 | +| avk | 27577 | 85219 | 106100 | 32260 | 33491 | +| awa | 3396 | 5802 | 6617 | 1679 | 2370 | +| ay | 5102 | 15125 | 22802 | 13930 | 13933 | +| az | 180810 | 789902 | 1570889 | 1377797 | 1380325 | +| azb | 240990 | 585386 | 1241661 | 749575 | 753318 | +| ba | 62269 | 391926 | 625645 | 562730 | 563181 | +| ban | 18955 | 44138 | 86239 | 66213 | 66412 | +| bar | 26057 | 83298 | 185158 | 109082 | 109091 | +| bat_smg | 17013 | 41951 | 77417 | 51701 | 51733 | +| bcl | 13783 | 45457 | 78963 | 47819 | 47861 | +| be | 222883 | 821135 | 2499258 | 2204062 | 2204117 | +| bg | 285156 | 1336530 | 3967713 | 3618800 | 3627798 | +| bh | 7658 | 17052 | 29110 | 22157 | 22217 | +| bi | 1403 | 1712 | 3172 | 1991 | 1995 | +| bjn | 9672 | 19007 | 58660 | 32538 | 33071 | +| blk | 2786 | 11825 | 11341 | 5979 | 6129 | +| bm | 1111 | 2421 | 2451 | 1217 | 1218 | +| bn | 136921 | 736388 | 1530942 | 1161967 | 1162761 | +| bo | 11843 | 37121 | 8241 | 6265 | 6359 | +| bpy | 24742 | 115606 | 166906 | 86166 | 86170 | +| br | 78524 | 214128 | 657375 | 527295 | 527606 | +| bs | 86407 | 382114 | 1246030 | 965782 | 966511 | +| bug | 14231 | 14484 | 53879 | 14787 | 15146 | +| bxr | 2730 | 9571 | 27853 | 11560 | 11567 | +| ca | 691444 | 3596667 | 11359870 | 10236358 | 10237666 | +| cbk_zam | 2989 | 8322 | 9939 | 2790 | 2847 | +| cdo | 15922 | 30059 | 63474 | 29659 | 29705 | +| ce | 597137 | 2121587 | 3097393 | 1507129 | 1507806 | +| ceb | 5888811 | 11920613 | 37969424 | 33678489 | 33962205 | +| ch | 574 | 1166 | 2290 | 492 | 601 | +| chr | 980 | 1110 | 1311 | 779 | 790 | +| chy | 711 | 753 | 494 | 428 | 428 | +| ckb | 48903 | 163599 | 435662 | 224749 | 226749 | +| co | 6719 | 22954 | 46391 | 24149 | 24229 | +| cr | 158 | 216 | 209 | 94 | 94 | +| crh | 24117 | 29781 | 98534 | 70231 | 70235 | +| cs | 516037 | 2679537 | 9917806 | 8763103 | 8763291 | +| csb | 5315 | 14009 | 31294 | 16820 | 16820 | +| cu | 1171 | 2796 | 5283 | 2346 | 2349 | +| cv | 50525 | 157542 | 375399 | 166889 | 167497 | +| cy | 276031 | 992900 | 2011030 | 1613064 | 1620632 | +| da | 284765 | 1167917 | 4352733 | 3854239 | 3854549 | +| dag | 9248 | 29213 | 46084 | 10981 | 14213 | +| de | 2780056 | 16093948 | 52497421 | 50480495 | 50480548 | +| din | 485 | 1551 | 1096 | 197 | 197 | +| diq | 37565 | 70969 | 155656 | 141636 | 141695 | +| dsb | 3083 | 8760 | 19397 | 9652 | 9652 | +| dty | 3339 | 6219 | 7505 | 4417 | 4447 | +| dv | 4190 | 16809 | 7906 | 3612 | 3620 | +| dz | 652 | 2623 | 272 | 94 | 100 | +| ee | 1075 | 2326 | 1823 | 861 | 926 | +| el | 224207 | 1527561 | 4181433 | 3119952 | 3121967 | +| eml | 12169 | 53861 | 115729 | 65775 | 65940 | +| en | 6514924 | 40656507 | 109681826 | 107761324 | 107768438 | +| eo | 330486 | 1116191 | 4257655 | 3975927 | 3979379 | +| es | 1792062 | 10890435 | 33729712 | 31581851 | 31648945 | +| et | 233078 | 1110906 | 3558448 | 2879595 | 2886824 | +| eu | 386029 | 1405747 | 3398477 | 3025183 | 3030635 | +| ext | 3472 | 9626 | 20554 | 11966 | 11978 | +| fa | 901254 | 2357271 | 6189352 | 5862106 | 5870803 | +| fat | 1044 | 6092 | 1717 | 120 | 857 | +| ff | 1763 | 4103 | 3483 | 2304 | 2413 | +| fi | 373226 | 1667296 | 5221239 | 4658292 | 4663471 | +| fiu_vro | 6417 | 19897 | 40418 | 23563 | 23609 | +| fj | 1157 | 1782 | 4852 | 1910 | 1911 | +| fo | 11809 | 30828 | 119267 | 95117 | 95259 | +| fr | 2432972 | 15252697 | 43564517 | 42573624 | 42589064 | +| frp | 5341 | 10574 | 36358 | 24905 | 24926 | +| frr | 16038 | 30821 | 80265 | 68184 | 68315 | +| fur | 3665 | 10651 | 29516 | 16249 | 16278 | +| fy | 46011 | 206153 | 1271339 | 985227 | 985511 | +| ga | 52168 | 130535 | 347037 | 288261 | 288309 | +| gag | 2408 | 4844 | 8551 | 4520 | 4520 | +| gan | 4219 | 9689 | 18994 | 14119 | 14128 | +| gcr | 2227 | 5163 | 2763 | 1186 | 1186 | +| gd | 15850 | 48217 | 141290 | 95557 | 95562 | +| gl | 190419 | 910543 | 3674404 | 2937660 | 2938634 | +| glk | 6484 | 15344 | 32631 | 21395 | 21447 | +| gn | 5064 | 15481 | 40641 | 30389 | 30440 | +| gom | 4192 | 37508 | 14192 | 2369 | 2382 | +| gor | 14388 | 28133 | 107341 | 66191 | 67016 | +| got | 960 | 2186 | 4093 | 1404 | 1415 | +| gpe | 899 | 3383 | 1199 | 796 | 815 | +| gu | 30025 | 114805 | 459063 | 348651 | 348731 | +| guc | 546 | 2545 | 2300 | 1025 | 1138 | +| gur | 1010 | 5043 | 1761 | 227 | 244 | +| guw | 1263 | 3719 | 7474 | 3116 | 5375 | +| gv | 5036 | 12213 | 48801 | 19659 | 19663 | +| ha | 31977 | 149096 | 115029 | 97167 | 98184 | +| hak | 8694 | 11505 | 39744 | 28150 | 28152 | +| haw | 2470 | 5810 | 11169 | 5700 | 5705 | +| he | 323472 | 2648617 | 10904148 | 10367532 | 10379886 | +| hi | 150121 | 538451 | 964251 | 795726 | 798254 | +| hif | 10534 | 21169 | 43463 | 23970 | 24316 | +| hr | 189415 | 876107 | 3210326 | 2752205 | 2758602 | +| hsb | 13183 | 40760 | 91863 | 66632 | 66633 | +| ht | 64850 | 154160 | 201547 | 166206 | 167961 | +| hu | 346711 | 1859683 | 5267990 | 4707580 | 4710525 | +| hy | 298066 | 1542920 | 3767938 | 2689014 | 2690466 | +| hyw | 11358 | 83640 | 161227 | 82218 | 84817 | +| ia | 24581 | 43289 | 129914 | 96517 | 96595 | +| id | 620895 | 2138237 | 6589957 | 5629372 | 5644832 | +| ie | 11020 | 22342 | 60890 | 46054 | 46122 | +| ig | 19448 | 110907 | 57963 | 31022 | 31298 | +| ik | 737 | 1016 | 848 | 551 | 580 | +| ilo | 14135 | 74304 | 126533 | 75701 | 75705 | +| inh | 1754 | 4640 | 13284 | 5770 | 6011 | +| io | 36312 | 101555 | 303765 | 258933 | 259001 | +| is | 54348 | 170321 | 574897 | 436767 | 437784 | +| it | 1610989 | 8718610 | 27447754 | 26116131 | 26126157 | +| iu | 502 | 757 | 536 | 414 | 418 | +| ja | 1355269 | 9276459 | 29002111 | 27752954 | 27801000 | +| jam | 1571 | 2260 | 5887 | 3588 | 3590 | +| jbo | 1287 | 3088 | 5831 | 546 | 546 | +| jv | 66323 | 148710 | 547010 | 381682 | 382052 | +| ka | 167161 | 695865 | 2275552 | 422090 | 422095 | +| kaa | 3540 | 9814 | 12930 | 5312 | 5752 | +| kab | 5346 | 14709 | 36889 | 22000 | 22050 | +| kbd | 1549 | 6348 | 14594 | 5277 | 5280 | +| kbp | 1846 | 6005 | 7119 | 6875 | 6880 | +| kcg | 871 | 1839 | 2953 | 1857 | 1871 | +| kg | 1187 | 1933 | 3835 | 2292 | 2295 | +| ki | 1482 | 2899 | 2035 | 1386 | 1649 | +| kk | 235740 | 889990 | 1840304 | 1143049 | 1151399 | +| kl | 282 | 1024 | 1337 | 302 | 302 | +| km | 11422 | 84697 | 111378 | 40954 | 41529 | +| kn | 30729 | 261724 | 432994 | 188536 | 188807 | +| ko | 606386 | 2159706 | 6217786 | 5715559 | 5725614 | +| koi | 3260 | 9065 | 17068 | 10628 | 10628 | +| krc | 1465 | 6234 | 18092 | 7294 | 7311 | +| ks | 4176 | 9446 | 15252 | 5917 | 6226 | +| ksh | 2836 | 11043 | 26577 | 9484 | 9496 | +| ku | 55166 | 112840 | 269080 | 208679 | 210304 | +| kv | 5236 | 13396 | 32141 | 26727 | 26744 | +| kw | 6884 | 18901 | 49462 | 28074 | 28194 | +| ky | 75426 | 191772 | 271376 | 189656 | 190133 | +| la | 124150 | 240343 | 1456464 | 1283285 | 1283728 | +| lad | 3538 | 11910 | 37456 | 19124 | 19124 | +| lb | 57747 | 178507 | 573528 | 443583 | 444601 | +| lbe | 1205 | 2249 | 4470 | 2543 | 2543 | +| lez | 4067 | 16675 | 36970 | 25834 | 25842 | +| lfn | 4506 | 21746 | 29785 | 14554 | 14560 | +| lg | 3814 | 23386 | 15539 | 2088 | 2724 | +| li | 14134 | 58711 | 212772 | 137110 | 137367 | +| lij | 8092 | 23366 | 61410 | 34939 | 34940 | +| lld | 152613 | 158049 | 578033 | 443976 | 458150 | +| lmo | 67387 | 136650 | 373890 | 274174 | 274612 | +| ln | 3132 | 6066 | 11086 | 7838 | 7874 | +| lo | 4734 | 15005 | 27132 | 8562 | 8799 | +| lt | 204135 | 775863 | 2687983 | 2406710 | 2414909 | +| ltg | 1018 | 2979 | 5815 | 2190 | 2193 | +| lv | 118530 | 437086 | 1458341 | 1244609 | 1247181 | +| mad | 1113 | 3500 | 3762 | 1149 | 1157 | +| mai | 13285 | 22572 | 53246 | 38119 | 38128 | +| map_bms | 10875 | 16411 | 67964 | 51125 | 51137 | +| mdf | 4002 | 11043 | 21658 | 9178 | 9183 | +| mg | 92227 | 213580 | 328751 | 265931 | 267633 | +| mhr | 11010 | 33013 | 60771 | 38153 | 38220 | +| mi | 7274 | 10154 | 29052 | 24854 | 25216 | +| min | 223075 | 422381 | 1315030 | 513108 | 515548 | +| mk | 131522 | 695456 | 1984109 | 1639280 | 1640744 | +| ml | 84334 | 415940 | 797903 | 485482 | 486324 | +| mn | 23434 | 124485 | 295548 | 142014 | 142984 | +| mni | 10354 | 18872 | 29474 | 18810 | 19876 | +| mnw | 3136 | 34165 | 9342 | 1908 | 2387 | +| mr | 92464 | 326662 | 633452 | 383501 | 392709 | +| mrj | 10156 | 20132 | 48416 | 24098 | 24098 | +| ms | 344459 | 988647 | 2424535 | 1932685 | 1937647 | +| mt | 5381 | 49856 | 104636 | 51251 | 51278 | +| mwl | 4402 | 37271 | 127176 | 25729 | 26366 | +| my | 103938 | 334243 | 445026 | 300567 | 303288 | +| myv | 7515 | 21592 | 36762 | 26570 | 26591 | +| mzn | 17364 | 39937 | 89805 | 46962 | 47020 | +| nah | 5934 | 12478 | 30805 | 13093 | 14364 | +| nap | 11235 | 22336 | 41891 | 20798 | 20804 | +| nds | 79228 | 242004 | 583941 | 305374 | 305422 | +| nds_nl | 6484 | 28252 | 94875 | 51767 | 51785 | +| ne | 30359 | 91033 | 153937 | 124841 | 125078 | +| new | 71653 | 245033 | 454251 | 289444 | 289912 | +| nia | 1496 | 4047 | 4524 | 2258 | 2812 | +| nl | 1948842 | 5867108 | 17953497 | 16886996 | 16893078 | +| nn | 160106 | 549454 | 1751481 | 1375622 | 1376155 | +| no | 591000 | 2213493 | 7050421 | 6471776 | 6476157 | +| nov | 1341 | 3711 | 7466 | 3948 | 3955 | +| nqo | 1489 | 9858 | 23633 | 6056 | 6981 | +| nrm | 4571 | 14279 | 38935 | 33295 | 33321 | +| nso | 7618 | 9505 | 36826 | 35621 | 35623 | +| nv | 21911 | 57663 | 123762 | 107139 | 107139 | +| ny | 1060 | 3164 | 4750 | 1455 | 1490 | +| oc | 85099 | 303185 | 1035051 | 791403 | 792043 | +| olo | 4348 | 14334 | 18704 | 8634 | 8647 | +| om | 1710 | 7496 | 8222 | 4333 | 4416 | +| or | 17027 | 76677 | 137274 | 57023 | 57064 | +| os | 17468 | 40488 | 80943 | 48124 | 48414 | +| pa | 50421 | 226354 | 344239 | 197594 | 198080 | +| pag | 2533 | 41416 | 4150 | 2907 | 2907 | +| pam | 7816 | 16493 | 53785 | 29375 | 29715 | +| pap | 3153 | 12086 | 22157 | 18161 | 18233 | +| pcd | 5272 | 12203 | 15602 | 12319 | 12360 | +| pcm | 1019 | 4631 | 4161 | 1160 | 1261 | +| pdc | 2009 | 5406 | 8151 | 4122 | 4144 | +| pfl | 2717 | 14024 | 26150 | 10291 | 10294 | +| pi | 2972 | 5959 | 7773 | 201 | 201 | +| pih | 829 | 1065 | 2857 | 2016 | 2018 | +| pl | 1468194 | 5599437 | 19364191 | 18389560 | 18405120 | +| pms | 66552 | 170133 | 369956 | 308593 | 314917 | +| pnb | 67534 | 402101 | 937247 | 525105 | 533265 | +| pnt | 497 | 1467 | 3553 | 1715 | 1716 | +| ps | 19254 | 134868 | 72493 | 36348 | 36899 | +| pt | 1048823 | 5226543 | 16811382 | 15714686 | 15714890 | +| pwn | 328 | 1825 | 990 | 428 | 430 | +| qu | 22365 | 47078 | 133032 | 106686 | 106708 | +| rm | 3569 | 27345 | 47169 | 20460 | 20490 | +| rmy | 911 | 2221 | 4235 | 1854 | 1965 | +| rn | 726 | 1641 | 1436 | 594 | 601 | +| ro | 417630 | 1518438 | 4282072 | 3764830 | 3765626 | +| roa_rup | 1270 | 2751 | 4641 | 2527 | 2537 | +| roa_tara | 8407 | 18031 | 42040 | 14330 | 14331 | +| ru | 1889271 | 12344758 | 30796034 | 29268121 | 29288089 | +| rue | 7369 | 21429 | 61022 | 43241 | 43256 | +| rw | 7793 | 35619 | 38066 | 19821 | 20967 | +| sa | 12069 | 78188 | 104193 | 40307 | 41518 | +| sah | 16007 | 76450 | 82154 | 61041 | 61412 | +| sat | 8655 | 43624 | 57493 | 28497 | 28820 | +| sc | 6919 | 24434 | 66719 | 44707 | 44733 | +| scn | 21990 | 49686 | 132583 | 102735 | 102774 | +| sco | 34097 | 86464 | 301450 | 148184 | 148406 | +| sd | 16228 | 48679 | 79392 | 34572 | 35729 | +| se | 6101 | 10531 | 25844 | 17978 | 18010 | +| sg | 473 | 537 | 318 | 184 | 184 | +| sh | 445218 | 1213741 | 4337559 | 3858400 | 3860253 | +| shi | 1650 | 6036 | 10364 | 4715 | 4926 | +| shn | 10653 | 51542 | 46976 | 29925 | 29993 | +| si | 21959 | 132932 | 146935 | 55158 | 56422 | +| simple | 224811 | 618711 | 2014692 | 1689101 | 1689185 | +| sk | 230073 | 845501 | 2867955 | 2468707 | 2469129 | +| skr | 5505 | 62742 | 38412 | 15004 | 21015 | +| sl | 175804 | 810714 | 2597824 | 2067682 | 2068522 | +| sm | 995 | 1591 | 3838 | 2515 | 2523 | +| smn | 5004 | 12483 | 37008 | 22440 | 22492 | +| sn | 10159 | 19527 | 40437 | 31573 | 32763 | +| so | 8540 | 36173 | 53012 | 42913 | 43548 | +| sq | 94941 | 371562 | 699210 | 520709 | 522241 | +| sr | 657766 | 2331205 | 6562651 | 5257496 | 5264077 | +| srn | 1171 | 3050 | 6637 | 1752 | 1941 | +| ss | 783 | 2124 | 2382 | 1127 | 1139 | +| st | 982 | 1971 | 2510 | 1689 | 1701 | +| stq | 3648 | 10972 | 29713 | 15919 | 15920 | +| su | 57552 | 122590 | 496201 | 384518 | 384891 | +| sv | 2418380 | 5019466 | 22263222 | 21445193 | 21445441 | +| sw | 75109 | 218219 | 798980 | 688743 | 692052 | +| szl | 56229 | 109496 | 473528 | 129434 | 129479 | +| szy | 4628 | 49166 | 18867 | 2419 | 3187 | +| ta | 157642 | 780711 | 1642095 | 1141032 | 1142372 | +| tay | 2643 | 15831 | 10104 | 1496 | 5312 | +| tcy | 2135 | 9932 | 11073 | 4680 | 4745 | +| te | 83866 | 719826 | 822054 | 619184 | 622092 | +| tet | 1323 | 3797 | 8047 | 4093 | 4095 | +| tg | 108598 | 279635 | 761826 | 330974 | 331423 | +| th | 153075 | 715083 | 1723394 | 1395935 | 1398891 | +| ti | 388 | 987 | 1191 | 325 | 326 | +| tk | 4739 | 23629 | 18964 | 9717 | 9760 | +| tl | 43388 | 150141 | 447293 | 296084 | 296634 | +| tn | 1090 | 3960 | 3976 | 2008 | 2010 | +| to | 1512 | 2754 | 3542 | 2029 | 2080 | +| tpi | 1278 | 2055 | 3897 | 2193 | 2198 | +| tr | 500435 | 1806253 | 4476004 | 3964449 | 3965589 | +| trv | 1770 | 16650 | 3814 | 504 | 969 | +| ts | 674 | 1798 | 1557 | 903 | 909 | +| tt | 484761 | 1196573 | 2064576 | 1675637 | 1676579 | +| tum | 16778 | 31383 | 57382 | 28399 | 37107 | +| tw | 3568 | 16807 | 15312 | 10912 | 11495 | +| ty | 1175 | 1364 | 1563 | 1095 | 1095 | +| tyv | 3399 | 21968 | 21004 | 5535 | 5557 | +| udm | 5066 | 11432 | 24875 | 17709 | 17715 | +| ug | 8102 | 58982 | 23654 | 12671 | 12874 | +| uk | 522709 | 2867475 | 6800045 | 6445628 | 6451294 | +| ur | 194948 | 676227 | 1870488 | 910419 | 914840 | +| uz | 232879 | 859793 | 1344790 | 1073065 | 1084092 | +| ve | 764 | 1359 | 2524 | 2366 | 2366 | +| vec | 62729 | 98987 | 275972 | 194424 | 194447 | +| vep | 6853 | 43014 | 93864 | 39225 | 39228 | +| vi | 1300753 | 4103594 | 10852870 | 6884928 | 6892519 | +| vls | 7272 | 26374 | 61885 | 49639 | 49653 | +| vo | 32133 | 78015 | 125495 | 101612 | 101629 | +| wa | 11104 | 56305 | 116752 | 79686 | 80037 | +| war | 1158901 | 1342594 | 6654010 | 6009636 | 6009641 | +| wo | 1659 | 7693 | 10828 | 4057 | 4103 | +| wuu | 37170 | 58227 | 121928 | 82184 | 82237 | +| xal | 2008 | 4309 | 4582 | 2112 | 2113 | +| xh | 1502 | 4448 | 6733 | 2128 | 2186 | +| xmf | 19201 | 49944 | 179291 | 21189 | 22041 | +| yi | 14164 | 68937 | 172645 | 116102 | 116325 | +| yo | 29938 | 52231 | 85171 | 46928 | 47346 | +| za | 2388 | 3917 | 7463 | 4613 | 4665 | +| zea | 5445 | 16648 | 36161 | 23532 | 23578 | +| zh | 1310818 | 5501834 | 16397675 | 14380752 | 14421795 | +| zh_classical | 11775 | 44053 | 140340 | 71576 | 71692 | +| zh_min_nan | 425676 | 853753 | 2627115 | 2053956 | 2054838 | +| zh_yue | 121401 | 273459 | 844047 | 683130 | 683226 | +| zu | 10387 | 18211 | 22569 | 20193 | 20238 | + +#### Validation + +| | Articles | Paragraphs | Anchors | Anchors with QIDs | Anchors with PageIDs | +| :-- | --: | --: | --: | --: | --: | +| ab | 475 | 601 | 1061 | 399 | 399 | +| ace | 2443 | 2668 | 5197 | 2583 | 2587 | +| ady | 142 | 183 | 248 | 150 | 151 | +| af | 27383 | 44157 | 109108 | 100078 | 100123 | +| als | 11998 | 18277 | 44634 | 32874 | 32874 | +| alt | 481 | 827 | 1020 | 621 | 621 | +| am | 3746 | 5234 | 10111 | 5731 | 5756 | +| ami | 749 | 1431 | 744 | 179 | 304 | +| an | 10526 | 13588 | 74808 | 58195 | 58259 | +| ang | 826 | 1099 | 2647 | 1099 | 1102 | +| anp | 504 | 751 | 1698 | 437 | 581 | +| ar | 265368 | 401215 | 1295968 | 1249666 | 1250103 | +| arc | 377 | 418 | 1061 | 610 | 617 | +| ary | 1447 | 1870 | 5702 | 3885 | 3887 | +| arz | 367206 | 410487 | 876531 | 767742 | 768942 | +| as | 5463 | 8589 | 13953 | 7719 | 7732 | +| ast | 48345 | 97904 | 329690 | 197832 | 198042 | +| atj | 399 | 440 | 774 | 406 | 416 | +| av | 719 | 961 | 1918 | 1043 | 1053 | +| avk | 8056 | 9538 | 11816 | 3633 | 3772 | +| awa | 515 | 645 | 721 | 213 | 287 | +| ay | 1391 | 1653 | 2616 | 1481 | 1483 | +| az | 57070 | 88136 | 177151 | 155596 | 155858 | +| azb | 57642 | 64997 | 137053 | 83336 | 83778 | +| ba | 25690 | 43460 | 69052 | 61624 | 61666 | +| ban | 4053 | 4840 | 9581 | 7374 | 7385 | +| bar | 6905 | 9377 | 20546 | 12164 | 12164 | +| bat_smg | 4149 | 4706 | 8787 | 5820 | 5823 | +| bcl | 3355 | 5058 | 8759 | 5080 | 5083 | +| be | 64203 | 91174 | 276525 | 244114 | 244122 | +| bg | 98148 | 148234 | 438687 | 400356 | 401330 | +| bh | 1535 | 1891 | 3464 | 2630 | 2635 | +| bi | 154 | 159 | 251 | 151 | 151 | +| bjn | 1764 | 2166 | 6458 | 3694 | 3775 | +| blk | 887 | 1374 | 1538 | 821 | 839 | +| bm | 196 | 272 | 317 | 146 | 146 | +| bn | 50495 | 81841 | 169097 | 128508 | 128609 | +| bo | 2198 | 4079 | 934 | 746 | 752 | +| bpy | 10057 | 12879 | 18710 | 9693 | 9693 | +| br | 18687 | 23734 | 73278 | 59024 | 59056 | +| bs | 28533 | 42574 | 138483 | 107760 | 107846 | +| bug | 1636 | 1655 | 6141 | 1682 | 1731 | +| bxr | 754 | 1003 | 2930 | 1211 | 1211 | +| ca | 251952 | 399403 | 1265187 | 1140208 | 1140359 | +| cbk_zam | 460 | 932 | 1040 | 268 | 272 | +| cdo | 2953 | 3237 | 6938 | 3273 | 3281 | +| ce | 197899 | 234617 | 341843 | 166126 | 166206 | +| ceb | 1221405 | 1324624 | 4218179 | 3742385 | 3773844 | +| ch | 123 | 131 | 239 | 64 | 73 | +| chr | 124 | 134 | 175 | 100 | 100 | +| chy | 67 | 67 | 47 | 42 | 42 | +| ckb | 13511 | 18279 | 48490 | 25365 | 25540 | +| co | 1723 | 2587 | 5286 | 2729 | 2737 | +| cr | 22 | 23 | 22 | 13 | 13 | +| crh | 2978 | 3246 | 11005 | 7899 | 7899 | +| cs | 189136 | 297000 | 1101343 | 974485 | 974505 | +| csb | 1307 | 1533 | 3341 | 1851 | 1851 | +| cu | 250 | 275 | 540 | 229 | 229 | +| cv | 14374 | 17462 | 42486 | 19049 | 19114 | +| cy | 89897 | 110225 | 222476 | 177842 | 178698 | +| da | 87765 | 129990 | 482701 | 427333 | 427374 | +| dag | 2215 | 3237 | 4935 | 1169 | 1498 | +| de | 1120553 | 1788057 | 5831103 | 5607963 | 5607963 | +| din | 149 | 177 | 128 | 15 | 15 | +| diq | 6660 | 7883 | 17684 | 15853 | 15861 | +| dsb | 781 | 1032 | 2476 | 1301 | 1301 | +| dty | 554 | 659 | 861 | 480 | 483 | +| dv | 1227 | 1898 | 870 | 406 | 406 | +| dz | 215 | 303 | 21 | 8 | 8 | +| ee | 203 | 242 | 183 | 66 | 74 | +| el | 99725 | 169395 | 461747 | 344216 | 344456 | +| eml | 4387 | 6114 | 13938 | 8193 | 8214 | +| en | 2503257 | 4516442 | 12185882 | 11974436 | 11975194 | +| eo | 90949 | 123848 | 474727 | 442357 | 442772 | +| es | 701171 | 1209944 | 3752765 | 3514968 | 3522213 | +| et | 80911 | 123354 | 395877 | 319773 | 320587 | +| eu | 104388 | 156552 | 378553 | 337331 | 337944 | +| ext | 804 | 1045 | 2269 | 1344 | 1345 | +| fa | 191532 | 262121 | 688824 | 652200 | 653219 | +| fat | 446 | 709 | 214 | 3 | 97 | +| ff | 361 | 459 | 378 | 222 | 234 | +| fi | 123327 | 184244 | 576163 | 514419 | 514915 | +| fiu_vro | 1738 | 2263 | 4622 | 2623 | 2628 | +| fj | 168 | 213 | 604 | 214 | 214 | +| fo | 2625 | 3398 | 13383 | 10599 | 10617 | +| fr | 954388 | 1695419 | 4847588 | 4738268 | 4740047 | +| frp | 1018 | 1181 | 4089 | 2862 | 2862 | +| frr | 2968 | 3419 | 9609 | 7996 | 8011 | +| fur | 884 | 1168 | 3225 | 1833 | 1839 | +| fy | 15980 | 22974 | 139530 | 108300 | 108337 | +| ga | 10781 | 14493 | 38848 | 32343 | 32352 | +| gag | 440 | 551 | 961 | 465 | 465 | +| gan | 731 | 1045 | 2071 | 1536 | 1537 | +| gcr | 480 | 567 | 297 | 122 | 122 | +| gd | 4393 | 5296 | 15544 | 10458 | 10458 | +| gl | 62030 | 101112 | 407821 | 325854 | 325960 | +| glk | 1383 | 1747 | 3723 | 2435 | 2443 | +| gn | 1164 | 1728 | 4751 | 3521 | 3528 | +| gom | 2106 | 4116 | 1511 | 251 | 251 | +| gor | 2844 | 3082 | 11826 | 7315 | 7411 | +| got | 216 | 245 | 514 | 190 | 190 | +| gpe | 265 | 355 | 93 | 71 | 73 | +| gu | 8437 | 13008 | 50956 | 38242 | 38251 | +| guc | 198 | 279 | 312 | 141 | 162 | +| gur | 369 | 565 | 145 | 25 | 27 | +| guw | 332 | 393 | 827 | 313 | 616 | +| gv | 957 | 1324 | 5652 | 2252 | 2253 | +| ha | 10666 | 16571 | 12853 | 10862 | 10993 | +| hak | 1179 | 1302 | 4628 | 3155 | 3155 | +| haw | 541 | 650 | 1238 | 616 | 618 | +| he | 165541 | 295188 | 1213939 | 1153986 | 1155384 | +| hi | 36229 | 60184 | 108382 | 89102 | 89340 | +| hif | 2107 | 2369 | 5015 | 2648 | 2680 | +| hr | 62673 | 97103 | 354392 | 304964 | 305664 | +| hsb | 3599 | 4379 | 10001 | 7239 | 7240 | +| ht | 14693 | 17294 | 23011 | 18721 | 18928 | +| hu | 125438 | 206546 | 586091 | 523501 | 523814 | +| hy | 113060 | 171415 | 418503 | 298111 | 298292 | +| hyw | 5310 | 9207 | 17616 | 8842 | 9168 | +| ia | 4021 | 4850 | 14972 | 11257 | 11263 | +| id | 158648 | 237793 | 734148 | 627764 | 629525 | +| ie | 2213 | 2523 | 6750 | 5036 | 5046 | +| ig | 7944 | 12354 | 6464 | 3466 | 3493 | +| ik | 100 | 118 | 120 | 64 | 71 | +| ilo | 4096 | 8297 | 14183 | 8609 | 8609 | +| inh | 399 | 494 | 1298 | 626 | 645 | +| io | 8868 | 11368 | 33682 | 28744 | 28748 | +| is | 13573 | 18566 | 62576 | 47263 | 47360 | +| it | 584902 | 968880 | 3050620 | 2902006 | 2903047 | +| iu | 61 | 62 | 48 | 29 | 29 | +| ja | 573457 | 1032568 | 3222875 | 3083301 | 3088604 | +| jam | 249 | 274 | 623 | 399 | 399 | +| jbo | 270 | 321 | 562 | 56 | 56 | +| jv | 13108 | 16457 | 60143 | 42112 | 42148 | +| ka | 53071 | 76961 | 252383 | 46974 | 46975 | +| kaa | 775 | 1071 | 1476 | 669 | 717 | +| kab | 1269 | 1685 | 4050 | 2397 | 2403 | +| kbd | 474 | 663 | 1482 | 537 | 537 | +| kbp | 535 | 656 | 835 | 810 | 811 | +| kcg | 190 | 223 | 311 | 196 | 197 | +| kg | 187 | 213 | 420 | 260 | 260 | +| ki | 273 | 333 | 248 | 169 | 206 | +| kk | 76635 | 99268 | 204324 | 126732 | 127677 | +| kl | 97 | 129 | 162 | 43 | 43 | +| km | 3844 | 9340 | 12192 | 4524 | 4583 | +| kn | 14217 | 29387 | 48402 | 20992 | 21022 | +| ko | 154713 | 239887 | 689906 | 633527 | 634725 | +| koi | 682 | 1010 | 1815 | 1144 | 1144 | +| krc | 423 | 698 | 2022 | 841 | 846 | +| ks | 888 | 1006 | 1692 | 645 | 670 | +| ksh | 918 | 1156 | 2951 | 1053 | 1055 | +| ku | 10060 | 12771 | 29766 | 23050 | 23232 | +| kv | 1105 | 1456 | 3365 | 2787 | 2787 | +| kw | 1820 | 2171 | 5570 | 3076 | 3082 | +| ky | 16655 | 21571 | 31213 | 21712 | 21757 | +| la | 22397 | 26732 | 161732 | 142447 | 142486 | +| lad | 961 | 1286 | 3984 | 2056 | 2056 | +| lb | 15385 | 19667 | 60568 | 46664 | 46730 | +| lbe | 207 | 232 | 488 | 290 | 290 | +| lez | 1184 | 1764 | 3829 | 2760 | 2760 | +| lfn | 1455 | 2435 | 3328 | 1602 | 1604 | +| lg | 1272 | 2650 | 1795 | 239 | 305 | +| li | 4501 | 6650 | 24213 | 15790 | 15826 | +| lij | 1781 | 2607 | 6658 | 3933 | 3933 | +| lld | 17293 | 17539 | 64059 | 49327 | 50864 | +| lmo | 12641 | 14976 | 40217 | 29874 | 29946 | +| ln | 585 | 692 | 1321 | 996 | 997 | +| lo | 1144 | 1680 | 3023 | 991 | 1013 | +| lt | 62652 | 85962 | 300456 | 269264 | 270227 | +| ltg | 289 | 341 | 686 | 285 | 285 | +| lv | 34742 | 48371 | 160433 | 136594 | 136873 | +| mad | 284 | 381 | 439 | 135 | 136 | +| mai | 2184 | 2499 | 5878 | 4209 | 4212 | +| map_bms | 1539 | 1847 | 7486 | 5705 | 5705 | +| mdf | 1086 | 1244 | 2512 | 1077 | 1077 | +| mg | 20361 | 23650 | 36313 | 29821 | 29974 | +| mhr | 2863 | 3594 | 6538 | 4114 | 4122 | +| mi | 1078 | 1154 | 3214 | 2743 | 2776 | +| min | 42987 | 46277 | 143692 | 55809 | 56077 | +| mk | 46235 | 76890 | 219310 | 180884 | 181042 | +| ml | 31116 | 46345 | 88976 | 53726 | 53818 | +| mn | 8485 | 13887 | 32271 | 15330 | 15455 | +| mni | 1843 | 2102 | 3418 | 2183 | 2325 | +| mnw | 1284 | 3750 | 897 | 202 | 224 | +| mr | 26803 | 36202 | 70510 | 43103 | 44352 | +| mrj | 2062 | 2297 | 5627 | 2888 | 2888 | +| ms | 75473 | 110077 | 270064 | 215280 | 215811 | +| mt | 2516 | 5510 | 11680 | 5760 | 5761 | +| mwl | 1828 | 4316 | 15365 | 3216 | 3287 | +| my | 24005 | 37165 | 49321 | 33223 | 33518 | +| myv | 1732 | 2327 | 4094 | 2923 | 2925 | +| mzn | 3784 | 4409 | 9938 | 5199 | 5205 | +| nah | 1128 | 1314 | 3316 | 1418 | 1556 | +| nap | 2047 | 2473 | 4579 | 2249 | 2249 | +| nds | 20646 | 26845 | 65355 | 34090 | 34094 | +| nds_nl | 2127 | 3063 | 10188 | 5585 | 5587 | +| ne | 6956 | 10087 | 16847 | 13502 | 13536 | +| new | 22645 | 27233 | 50860 | 32165 | 32217 | +| nia | 312 | 430 | 512 | 277 | 329 | +| nl | 490380 | 651743 | 1994062 | 1874588 | 1875259 | +| nn | 44180 | 60918 | 194747 | 153072 | 153140 | +| no | 172653 | 245377 | 779775 | 715618 | 716153 | +| nov | 339 | 410 | 861 | 452 | 452 | +| nqo | 583 | 1037 | 2598 | 704 | 813 | +| nrm | 1318 | 1600 | 4276 | 3734 | 3736 | +| nso | 960 | 1038 | 4242 | 4119 | 4119 | +| nv | 5649 | 6281 | 13652 | 11768 | 11768 | +| ny | 236 | 318 | 392 | 126 | 126 | +| oc | 23067 | 33775 | 115155 | 87980 | 88063 | +| olo | 1273 | 1598 | 2162 | 997 | 998 | +| om | 401 | 830 | 891 | 401 | 412 | +| or | 6261 | 8669 | 16120 | 6752 | 6757 | +| os | 3923 | 4535 | 9130 | 5470 | 5524 | +| pa | 17242 | 24844 | 37813 | 21759 | 21812 | +| pag | 1602 | 4519 | 404 | 300 | 300 | +| pam | 1509 | 1831 | 6019 | 3230 | 3272 | +| pap | 773 | 1376 | 2526 | 2042 | 2056 | +| pcd | 1089 | 1361 | 1803 | 1334 | 1338 | +| pcm | 353 | 542 | 409 | 128 | 139 | +| pdc | 370 | 565 | 839 | 424 | 429 | +| pfl | 1113 | 1500 | 2861 | 1070 | 1070 | +| pi | 578 | 682 | 881 | 26 | 26 | +| pih | 118 | 125 | 317 | 217 | 218 | +| pl | 444095 | 621669 | 2149058 | 2041686 | 2043400 | +| pms | 16530 | 19186 | 41547 | 34783 | 35474 | +| pnb | 21586 | 44654 | 103992 | 58461 | 59380 | +| pnt | 147 | 172 | 389 | 177 | 178 | +| ps | 7566 | 14922 | 8427 | 4108 | 4187 | +| pt | 349931 | 580790 | 1868210 | 1745832 | 1745858 | +| pwn | 103 | 166 | 85 | 31 | 31 | +| qu | 4540 | 5211 | 14781 | 11746 | 11750 | +| rm | 1076 | 3100 | 5539 | 2293 | 2298 | +| rmy | 214 | 235 | 446 | 176 | 184 | +| rn | 125 | 172 | 124 | 53 | 53 | +| ro | 106169 | 168972 | 473512 | 416263 | 416347 | +| roa_rup | 214 | 290 | 458 | 254 | 254 | +| roa_tara | 1278 | 1979 | 4455 | 1534 | 1534 | +| ru | 806592 | 1369860 | 3416036 | 3245837 | 3247963 | +| rue | 2022 | 2513 | 7023 | 5064 | 5066 | +| rw | 2577 | 3925 | 4139 | 2223 | 2349 | +| sa | 4344 | 8607 | 11313 | 4249 | 4391 | +| sah | 4729 | 8472 | 9040 | 6623 | 6660 | +| sat | 3485 | 4960 | 6473 | 3225 | 3278 | +| sc | 1900 | 2807 | 7641 | 5096 | 5098 | +| scn | 4263 | 5604 | 14333 | 11167 | 11171 | +| sco | 7382 | 9639 | 33771 | 16432 | 16453 | +| sd | 3970 | 5499 | 8879 | 3804 | 3925 | +| se | 982 | 1149 | 2841 | 1958 | 1958 | +| sg | 67 | 72 | 36 | 24 | 24 | +| sh | 103283 | 135121 | 484459 | 429555 | 429770 | +| shi | 477 | 679 | 1144 | 545 | 570 | +| shn | 3633 | 5630 | 5456 | 3627 | 3639 | +| si | 7672 | 14760 | 16443 | 6215 | 6346 | +| simple | 52503 | 68765 | 224811 | 187586 | 187598 | +| sk | 67520 | 93957 | 317232 | 272711 | 272779 | +| skr | 2090 | 6926 | 4136 | 1683 | 2359 | +| sl | 55621 | 89740 | 285769 | 228421 | 228530 | +| sm | 153 | 171 | 485 | 297 | 297 | +| smn | 1163 | 1420 | 4517 | 2681 | 2688 | +| sn | 1896 | 2139 | 4351 | 3384 | 3529 | +| so | 2358 | 4032 | 6064 | 5027 | 5083 | +| sq | 25223 | 41621 | 79295 | 59156 | 59350 | +| sr | 177997 | 258455 | 728755 | 584663 | 585394 | +| srn | 281 | 342 | 796 | 205 | 225 | +| ss | 188 | 259 | 265 | 125 | 125 | +| st | 157 | 198 | 248 | 164 | 166 | +| stq | 804 | 1162 | 3150 | 1816 | 1816 | +| su | 10348 | 13687 | 55055 | 42915 | 42944 | +| sv | 467467 | 558522 | 2473790 | 2382576 | 2382608 | +| sw | 18014 | 24348 | 90302 | 77817 | 78145 | +| szl | 11292 | 12173 | 52459 | 14419 | 14424 | +| szy | 2391 | 5418 | 2042 | 235 | 285 | +| ta | 59923 | 87114 | 183399 | 126977 | 127148 | +| tay | 1192 | 1757 | 1101 | 175 | 591 | +| tcy | 769 | 1077 | 1089 | 464 | 465 | +| te | 43790 | 79667 | 91327 | 69148 | 69484 | +| tet | 294 | 412 | 871 | 471 | 471 | +| tg | 27060 | 31599 | 86180 | 37522 | 37561 | +| th | 49169 | 78814 | 189768 | 154097 | 154453 | +| ti | 87 | 99 | 89 | 22 | 22 | +| tk | 1328 | 2612 | 2116 | 1056 | 1062 | +| tl | 11731 | 16623 | 49726 | 32858 | 32914 | +| tn | 296 | 424 | 477 | 278 | 278 | +| to | 254 | 277 | 393 | 230 | 233 | +| tpi | 180 | 207 | 394 | 216 | 217 | +| tr | 134938 | 200972 | 496960 | 440639 | 440790 | +| trv | 807 | 1814 | 400 | 53 | 98 | +| ts | 155 | 203 | 219 | 132 | 132 | +| tt | 113689 | 132676 | 228544 | 185563 | 185662 | +| tum | 2188 | 3516 | 6442 | 3105 | 4083 | +| tw | 1249 | 1885 | 1729 | 1217 | 1291 | +| ty | 162 | 167 | 215 | 143 | 143 | +| tyv | 1494 | 2486 | 2342 | 611 | 617 | +| udm | 1036 | 1240 | 2781 | 1957 | 1957 | +| ug | 2629 | 6556 | 2657 | 1479 | 1493 | +| uk | 203057 | 318240 | 758049 | 718278 | 718908 | +| ur | 54784 | 75152 | 206169 | 99493 | 100041 | +| uz | 65767 | 95465 | 149763 | 119192 | 120519 | +| ve | 128 | 148 | 256 | 229 | 229 | +| vec | 9463 | 11242 | 32188 | 22525 | 22531 | +| vep | 3225 | 4804 | 10375 | 4295 | 4295 | +| vi | 330763 | 455933 | 1211343 | 768936 | 769829 | +| vls | 2189 | 2904 | 7133 | 5776 | 5777 | +| vo | 7308 | 8647 | 13902 | 11270 | 11273 | +| wa | 4457 | 6269 | 12736 | 8751 | 8794 | +| war | 146537 | 149236 | 738087 | 666983 | 666983 | +| wo | 516 | 864 | 1083 | 404 | 414 | +| wuu | 5530 | 6448 | 13732 | 9168 | 9171 | +| xal | 407 | 449 | 549 | 308 | 308 | +| xh | 399 | 550 | 804 | 284 | 293 | +| xmf | 4516 | 5414 | 19437 | 2342 | 2447 | +| yi | 5260 | 7563 | 18821 | 12493 | 12510 | +| yo | 4431 | 5855 | 9761 | 5361 | 5410 | +| za | 335 | 414 | 777 | 457 | 458 | +| zea | 1470 | 1847 | 3682 | 2569 | 2574 | +| zh | 389361 | 611537 | 1817382 | 1592929 | 1597686 | +| zh_classical | 3601 | 4995 | 15834 | 8157 | 8170 | +| zh_min_nan | 87849 | 94529 | 291330 | 227978 | 228083 | +| zh_yue | 23579 | 30146 | 92720 | 75081 | 75096 | +| zu | 1646 | 2050 | 2518 | 2228 | 2234 | + +**NOTE:** The number of articles in the tables above refers to the number of articles that have at least one paragraph belonging to the article appear in the split. + +## Additional Information + +### Licensing Information + +The WikiAnc dataset is given under the [Creative Commons Attribution ShareAlike 4.0 International](https://creativecommons.org/licenses/by-sa/4.0/) license." +KETI-AIR/kor_duorc,"{""language"": [""ko""], ""license"": [""mit""], ""multilinguality"": [""monolingual""], ""size_categories"": [""10K(Male/Female/Unidentified) | +|:---:|:---:|:---:|:---:|:---:| +| ar-SA | validation | 2033 | 2.12 | 36 (22/14/0) | +| | test | 2974 | 3.23 | 37 (15/17/5) | +| | train_115 | 115 | 0.14 | 8 (4/4/0) | +| de-DE | validation | 2033 | 2.33 | 68 (35/32/1) | +| | test | 2974 | 3.41 | 82 (36/36/10) | +| | train | 11514 | 12.61 | 117 (50/63/4) | +| | train_115 | 115 | 0.15 | 7 (3/4/0) | +| es-ES | validation | 2033 | 2.53 | 109 (51/53/5) | +| | test | 2974 | 3.61 | 85 (37/33/15) | +| | train_115 | 115 | 0.13 | 7 (3/4/0) | +| fr-FR | validation | 2033 | 2.20 | 55 (26/26/3) | +| | test | 2974 | 2.65 | 75 (31/35/9) | +| | train | 11514 | 12.42 | 103 (50/52/1) | +| | train_115 | 115 | 0.12 | 103 (50/52/1) | +| hu-HU | validation | 2033 | 2.27 | 69 (33/33/3) | +| | test | 2974 | 3.30 | 55 (25/24/6) | +| | train_115 | 115 | 0.12 | 8 (3/4/1) | +| ko-KR | validation | 2033 | 2.12 | 21 (8/13/0) | +| | test | 2974 | 2.66 | 31 (10/18/3) | +| | train_115 | 115 | 0.14 | 8 (4/4/0) | +| nl-NL | validation | 2033 | 2.14 | 37 (17/19/1) | +| | test | 2974 | 3.30 | 100 (48/49/3) | +| | train_115 | 115 | 0.12 | 7 (3/4/0) | +| pl-PL | validation | 2033 | 2.24 | 105 (50/52/3) | +| | test | 2974 | 3.21 | 151 (73/71/7) | +| | train_115 | 115 | 0.10 | 7 (3/4/0) | +| pt-PT | validation | 2033 | 2.20 | 107 (51/53/3) | +| | test | 2974 | 3.25 | 102 (48/50/4) | +| | train_115 | 115 | 0.12 | 8 (4/4/0) | +| ru-RU | validation | 2033 | 2.25 | 40 (7/31/2) | +| | test | 2974 | 3.44 | 51 (25/23/3) | +| | train_115 | 115 | 0.12 | 7 (3/4/0) | +| tr-TR | validation | 2033 | 2.17 | 71 (36/34/1) | +| | test | 2974 | 3.00 | 42 (17/18/7) | +| | train_115 | 115 | 0.11 | 6 (3/3/0) | +| vi-VN | validation | 2033 | 2.10 | 28 (13/14/1) | +| | test | 2974 | 3.23 | 30 (11/14/5) | +|| train_115 | 115 | 0.11 | 7 (2/4/1) | + + +## How to use + +### How to use + +The `datasets` library allows you to load and pre-process your dataset in pure Python, at scale. The dataset can be downloaded and prepared in one call to your local drive by using the `load_dataset` function. + +For example, to download the French config, simply specify the corresponding language config name (i.e., ""fr-FR"" for French): + +```python +from datasets import load_dataset + +speech_massive_fr_train = load_dataset(""FBK-MT/Speech-MASSIVE"", ""fr-FR"", split=""train"") +``` + +In case you don't have enough space in the machine, you can stream dataset by adding a `streaming=True` argument to the `load_dataset` function call. Loading a dataset in streaming mode loads individual samples of the dataset at a time, rather than downloading the entire dataset to disk. +```python +from datasets import load_dataset + +speech_massive_de_train = load_dataset(""FBK-MT/Speech-MASSIVE"", ""de-DE"", split=""train"", streaming=True) +list(speech_massive_de_train.take(2)) +``` + +You can also load all the available languages and splits at once. +And then access each split. +```python +from datasets import load_dataset + +speech_massive = load_dataset(""FBK-MT/Speech-MASSIVE"", ""all"") +multilingual_validation = speech_massive['validation'] +``` + +Or you can load dataset's all the splits per language to separate languages more easily. +```python +from datasets import load_dataset, interleave_datasets, concatenate_datasets + +# creating full train set by interleaving between German and French +speech_massive_de = load_dataset(""FBK-MT/Speech-MASSIVE"", ""de-DE"") +speech_massive_fr = load_dataset(""FBK-MT/Speech-MASSIVE"", ""fr-FR"") +speech_massive_train_de_fr = interleave_datasets([speech_massive_de['train'], speech_massive_fr['train']]) + +# creating train_115 few-shot set by concatenating Korean and Russian +speech_massive_ko = load_dataset(""FBK-MT/Speech-MASSIVE"", ""ko-KR"") +speech_massive_ru = load_dataset(""FBK-MT/Speech-MASSIVE"", ""ru-RU"") +speech_massive_train_115_ko_ru = concatenate_datasets([speech_massive_ko['train_115'], speech_massive_ru['train_115']]) +``` + +## Dataset Structure + +### Data configs +- `all`: load all the 12 languages in one single dataset instance +- `lang`: load only `lang` in the dataset instance, by specifying one of below languages + - ```ar-SA, de-DE, es-ES, fr-FR, hu-HU, ko-KR, nl-NL, pl-PL, pt-PT, ru-RU, tr-TR, vi-VN``` + +### Data Splits +- `validation`: validation(dev) split available for all the 12 languages +- `train_115`: few-shot (115 samples) split available for all the 12 languages +- `train`: train split available for French (fr-FR) and German (de-DE) + +> [!WARNING] +> `test` split is uploaded as a separate dataset on HF to prevent possible data contamination +- ⚠️ `test`: available **_only_** in the separate HF dataset repository. ⚠️ +- [https://huggingface.co/datasets/FBK-MT/Speech-MASSIVE-test](https://huggingface.co/datasets/FBK-MT/Speech-MASSIVE-test) + +### Data Instances + +```json +{ + // Start of the data collected in Speech-MASSIVE + 'audio': { + 'path': 'train/2b12a21ca64a729ccdabbde76a8f8d56.wav', + 'array': array([-7.80913979e-...7259e-03]), + 'sampling_rate': 16000}, + 'path': '/path/to/wav/file.wav', + 'is_transcript_reported': False, + 'is_validated': True, + 'speaker_id': '60fcc09cb546eee814672f44', + 'speaker_sex': 'Female', + 'speaker_age': '25', + 'speaker_ethnicity_simple': 'White', + 'speaker_country_of_birth': 'France', + 'speaker_country_of_residence': 'Ireland', + 'speaker_nationality': 'France', + 'speaker_first_language': 'French', + // End of the data collected in Speech-MASSIVE + + // Start of the data extracted from MASSIVE + // (https://huggingface.co/datasets/AmazonScience/massive/blob/main/README.md#data-instances) + 'id': '7509', + 'locale': 'fr-FR', + 'partition': 'train', + 'scenario': 2, + 'scenario_str': 'calendar', + 'intent_idx': 32, + 'intent_str': 'calendar_query', + 'utt': 'après les cours de natation quoi d autre sur mon calendrier mardi', + 'annot_utt': 'après les cours de natation quoi d autre sur mon calendrier [date : mardi]', + 'worker_id': '22', + 'slot_method': {'slot': ['date'], 'method': ['translation']}, + 'judgments': { + 'worker_id': ['22', '19', '0'], + 'intent_score': [1, 2, 1], + 'slots_score': [1, 1, 1], + 'grammar_score': [4, 4, 4], + 'spelling_score': [2, 1, 2], + 'language_identification': ['target', 'target', 'target'] + }, + 'tokens': ['après', 'les', 'cours', 'de', 'natation', 'quoi', 'd', 'autre', 'sur', 'mon', 'calendrier', 'mardi'], + 'labels': ['Other', 'Other', 'Other', 'Other', 'Other', 'Other', 'Other', 'Other', 'Other', 'Other', 'Other', 'date'], + // End of the data extracted from MASSIVE +} +``` +### Data Fields + +`audio.path`: Original audio file name + +`audio.array`: Read audio file with the sampling rate of 16,000 + +`audio.sampling_rate`: Sampling rate + +`path`: Original audio file full path + +`is_transcript_reported`: Whether the transcript is reported as 'syntatically wrong' by crowd-source worker + +`is_validated`: Whether the recorded audio has been validated to check if the audio matches transcript exactly by crowd-source worker + +`speaker_id`: Unique hash id of the crowd source speaker + +`speaker_sex`: Speaker's sex information provided by the crowd-source platform ([Prolific](http://prolific.com)) +- Male +- Female +- Unidentified : Information not available from Prolific + +`speaker_age`: Speaker's age information provided by Prolific +- age value (`str`) +- Unidentified : Information not available from Prolific + +`speaker_ethnicity_simple`: Speaker's ethnicity information provided by Prolific +- ethnicity value (`str`) +- Unidentified : Information not available from Prolific + +`speaker_country_of_birth`: Speaker's country of birth information provided by Prolific +- country value (`str`) +- Unidentified : Information not available from Prolific + +`speaker_country_of_residence`: Speaker's country of residence information provided by Prolific +- country value (`str`) +- Unidentified : Information not available from Prolific + +`speaker_nationality`: Speaker's nationality information provided by Prolific +- nationality value (`str`) +- Unidentified : Information not available from Prolific + +`speaker_first_language`: Speaker's first language information provided by Prolific +- language value (`str`) +- Unidentified : Information not available from Prolific + + +### Limitations + +As Speech-MASSIVE is constructed based on the MASSIVE dataset, it inherently retains certain grammatical errors present in the original MASSIVE text. Correcting these errors was outside the scope of our project. However, by providing the `is_transcripted_reported` attribute in Speech-MASSIVE, we enable users of the dataset to be aware of these errors. + + +## License + +All datasets are licensed under the [CC-BY-NC-SA-4.0 license](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en). + +### Citation Information + +Speech-MASSIVE is accepted at INTERSPEECH 2024 (Kos, Greece). +You can access the [Speech-MASSIVE paper on arXiv](https://arxiv.org/abs/2408.03900). +Please cite the paper when referencing the Speech-MASSIVE corpus as: + +``` +@misc{lee2024speechmassivemultilingualspeechdataset, + title={Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond}, + author={Beomseok Lee and Ioan Calapodescu and Marco Gaido and Matteo Negri and Laurent Besacier}, + year={2024}, + eprint={2408.03900}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2408.03900}, +} +```" +facebook/2M-Belebele,"{""license"": ""cc-by-sa-4.0"", ""task_categories"": [""question-answering"", ""automatic-speech-recognition""], ""language"": [""bg"", ""pa"", ""en"", ""hu"", ""sv"", ""af"", ""ca"", ""ka"", ""sk"", ""jv"", ""bn"", ""tr"", ""sr"", ""ro"", ""tg"", ""fa"", ""wo"", ""fi"", ""hy"", ""vi"", ""kea"", ""as"", ""ja"", ""nl"", ""ne"", ""lg"", ""hi"", ""xh"", ""kk"", ""mn"", ""yo"", ""km"", ""ha"", ""ru"", ""sw"", ""ps"", ""ko"", ""cs"", ""lv"", ""ig"", ""ar"", ""es"", ""nb"", ""lt"", ""fil"", ""it"", ""he"", ""da"", ""ml"", ""my"", ""el"", ""et"", ""pl"", ""sn"", ""sd"", ""or"", ""th"", ""luo"", ""sl"", ""fr"", ""id"", ""ta"", ""gu"", ""mk"", ""am"", ""pt"", ""cmn"", ""de"", ""ceb"", ""is"", ""ur"", ""az"", ""te""], ""tags"": [""speech-recognition"", ""multilingual"", ""flores200"", ""translation"", ""audio"", ""speech""], ""pretty_name"": ""2M Belebele Speech"", ""size_categories"": [""1Kin multiple languages** to be the **Vript_Multilingual**. + +**New in Vript_Multilingual**: +1. Multilingual: zh (60%), en (17%), de (15%), ja (6%), ko (2%), ru (<1%), es (<1%), pt (<1%), jv (<1%), fr (<1%), id (<1%), vi (<1%) +2. More diverse and fine-grained categories: 113 categories (please check [vript_CN-V2_meta.json](https://huggingface.co/datasets/Mutonix/Vript_Multilingual/blob/main/vript_CN-V2_meta.jsonl)) +3. Wider range: from 2011-01 to 2024-06 +4. Higher resolution: 1080p +5. Longer duration: > 10 minutes in average +6. More clips: ~677k clips + + +## Getting Started +**By downloading these datasets, you agree to the terms of the [License](#License).** + +The captions of the videos in the Vript_Multilingual dataset are structured as follows: +``` +{ + ""meta"": { + ""video_id"": ""xxx"", + ""video_title"": ""..."", + ""num_clips"": ..., + ""integrity"": true, + }, + ""data"": { + ""xxx-Scene-001"": { + ""video_id"": ""xxx"", + ""clip_id"": ""xxx-Scene-001"", + ""video_title"": ""..."", + ""caption"":{ + ""shot_type"": ""..."", + ""camera_movement"": ""..."", + ""content"": ""..."", + ""scene_title"": ""..."", + }, + ""voiceover"": [""...""], + }, + ""xxx-Scene-002"": { + ... + } + } +} +``` +- `video_id`: The ID of the video from YouTube. +- `video_title`: The title of the video. +- `num_clips`: The number of clips in the video. If the `integrity` is `false`, some clips may not be captioned. +- `integrity`: Whether all clips of the video are captioned. +- `clip_id`: The ID of the clip in the video, which is the concatenation of the `video_id` and the scene number. +- `caption`: The caption of the scene, including the shot type, camera movement, content, and scene title. +- `voiceover`: The transcription of the voice-over in the scene. + +The data is organized as follows: +``` +Vript_Multilingual/ +| +├── vript_CN-V2_meta.json +│ +├── vript_CN-V2_captions/ +│ ├── vript_CN-V2_captions.zip +│ └── vript_CN-V2_captions.jsonl +│ +├── vript_CN-V2_videos/ +│ ├── CN-V2_video_1_of_224.zip +│ │ ├── xxx.mp4 +│ │ └── ... +│ ├── CN-V2_video_2_of_224.zip +│ └── ... +│ +└── vript_CN-V2_clips/ + ├── CN-V2_clips_1_of_224.zip + │ ├── xxx/ + │ │ ├── xxx_cut_meta.json + │ │ ├── xxx_asr.jsonl + │ │ ├── xxx-Scene-001.mp4 + │ │ └── ... + │ └── ... + ├── CN-V2_clips_2_of_224.zip + └── ... + + +``` +- `vript_CN-V2_meta.json`: The meta information of the videos in the Vript_Multilingual dataset, including the video id, title, url, description, category, etc. + +- `vript_CN-V2_captions/`: The video captions of the videos in the Vript_Multilingual dataset, which are structured as described above. + +- `vript_CN-V2_videos/` (711 GB): The untrimmed videos in the Vript_Multilingual dataset. We divide the whole data into multiple zip files, each containing 200 videos. + +- `vript_CN-V2_clips/` (890 GB): The trimmed video clips in the Vript_Multilingual dataset, which correspond to scenes in the `video_CN-V2_captions`. + +- `xxx_cut_meta.json`: The meta information about how the video is trimmed, including the start time, end time, and the duration of the scene. + +- `xxx_asr.jsonl`: The transcription of the voice-over in the scene. + + +## License +By downloading or using the data or model, you understand, acknowledge, and agree to all the terms in the following agreement. + +- ACADEMIC USE ONLY + +Any content from the Vript-related dataset and Vriptor model is available for academic research purposes only. You agree not to reproduce, duplicate, copy, trade, or exploit for any commercial purposes + +- NO DISTRIBUTION + +Respect the privacy of personal information of the original source. Without the permission of the copyright owner, you are not allowed to perform any form of broadcasting, modification or any other similar behavior to the data set content. + +- RESTRICTION AND LIMITATION OF LIABILITY + +In no event shall we be liable for any other damages whatsoever arising out of the use of, or inability to use this dataset and its associated software, even if we have been advised of the possibility of such damages. + +- DISCLAIMER + +You are solely responsible for legal liability arising from your improper use of the dataset content. We reserve the right to terminate your access to the dataset at any time. You should delete the Vript-related dataset or Vriptor model if required. + +This license is modified from the [HD-VG-100M](https://github.com/daooshee/HD-VG-130M) license. + + +## Citation +``` +@misc{yang2024vript, + title={Vript: A Video Is Worth Thousands of Words}, + author={Dongjie Yang and Suyuan Huang and Chengqiang Lu and Xiaodong Han and Haoxin Zhang and Yan Gao and Yao Hu and Hai Zhao}, + year={2024}, + eprint={2406.06040}, + archivePrefix={arXiv}, + primaryClass={cs.CV} +} +``` + +## Contact +**Dongjie Yang**: [djyang.tony@sjtu.edu.cn](djyang.tony@sjtu.edu.cn) + +Paper: arxiv.org/abs/2406.06040" +sentence-transformers/mldr,"{""multilinguality"": [""monolingual""], ""size_categories"": [""100K 1M | 9 | images > 1M | 6 +total > 500K | 10 | images > 500K | 12 +total > 100K | 36 | images > 100K | 35 +total > 50K | 15 | images > 50K | 17 +total > 14K | 38 | images > 13K | 38 + +## Dataset Structure + +### Data Instances + +``` +{ + 'language': 'en', + 'page_url': 'https://en.wikipedia.org/wiki/Oxydactylus', + 'image_url': 'https://upload.wikimedia.org/wikipedia/commons/5/5f/Oxydactylus_longipes_fm.jpg', + 'page_title': 'Oxydactylus', + 'section_title': None, + 'hierarchical_section_title': 'Oxydactylus', + 'caption_reference_description': None, + 'caption_attribution_description': 'English: Mounted skeleton of Oxydactylus longipes in the Field Museum of Natural History.', + 'caption_alt_text_description': None, + 'mime_type': 'image/jpeg', + 'original_height': 3564, + 'original_width': 2748, + 'is_main_image': True, + 'attribution_passes_lang_id': True, + 'page_changed_recently': True, + 'context_page_description': 'Oxydactylus is an extinct genus of camelid endemic to North America. It lived from the Late Oligocene to the Middle Miocene, existing for approximately 14 million years. The name is from the Ancient Greek οξύς and δάκτυλος.\nThey had very long legs and necks, and were probably adapted to eating high vegetation, much like modern giraffes. Unlike modern camelids, they had hooves, rather than tough sole-pads, and splayed toes.', + 'context_section_description': 'Oxydactylus is an extinct genus of camelid endemic to North America. It lived from the Late Oligocene to the Middle Miocene (28.4–13.7 mya), existing for approximately 14 million years. The name is from the Ancient Greek οξύς (oxys, ""sharp"")and δάκτυλος (daktylos, ""finger"").\n \nThey had very long legs and necks, and were probably adapted to eating high vegetation, much like modern giraffes. Unlike modern camelids, they had hooves, rather than tough sole-pads, and splayed toes.' +} +``` + +### Data Fields + +- `language`: Language code depicting wikipedia language of the page +- `page_url`: URL to wikipedia page +- `image_url`: URL to wikipedia image +- `page_title`: Wikipedia page's title +- `section_title`: Section's title +- `hierarchical_section_title`: Hierarchical section's title +- `caption_reference_description`: This is the caption that is visible on the wiki page directly below the image. +- `caption_attribution_description`: This is the text found on the Wikimedia page of the image. This text is common to all occurrences of that image across all Wikipedias and thus can be in a language different to the original page article. +- `caption_alt_text_description`: This is the “alt” text associated with the image. While not visible in general, it is commonly used for accessibility / screen readers +- `mime_type`: Mime type associated to the image. +- `original_height`: Image height +- `original_width`: Image width +- `is_main_image`: Flag determining if the image is the first image of the page. Usually displayed on the top-right part of the page when using web browsers. +- `attribution_passes_lang_id`: Compared `language` field with the attribution language (written in the prefix of the attribution description). +- `page_changed_recently`: [More Information Needed] +- `context_page_description`: Page description corresponds to the short description of the page. It provides a concise explanation of the scope of the page. +- `context_section_description`: Text within the image's section. + +

+
+Figure: WIT annotation example. +

+ +Details on the field content can be found directly in the [paper, figure 5 and table 12.](https://arxiv.org/abs/2103.01913) + +### Data Splits + +All data is held in `train` split, with a total of 37046386 rows. + +## Dataset Creation + +### Curation Rationale + +From the [repository](https://github.com/google-research-datasets/wit#motivation): + +> Multimodal visio-linguistic models rely on a rich dataset to help them learn to model the relationship between images and texts. Having large image-text datasets can significantly improve performance, as shown by recent works. Furthermore the lack of language coverage in existing datasets (which are mostly only in English) also impedes research in the multilingual multimodal space – we consider this a lost opportunity given the potential shown in leveraging images (as a language-agnostic medium) to help improve our multilingual textual understanding. +> +> To address these challenges and advance research on multilingual, multimodal learning we created the Wikipedia-based Image Text (WIT) Dataset. WIT is created by extracting multiple different texts associated with an image (e.g., as shown in the above image) from Wikipedia articles and Wikimedia image links. This was accompanied by rigorous filtering to only retain high quality image-text sets. +> +> The resulting dataset contains over 37.6 million image-text sets – making WIT the largest multimodal dataset (publicly available at the time of this writing) with unparalleled multilingual coverage – with 12K+ examples in each of 108 languages (53 languages have 100K+ image-text pairs). + +### Source Data + +#### Initial Data Collection and Normalization + +From the [paper, section 3.1](https://arxiv.org/abs/2103.01913): + +> We started with all Wikipedia content pages (i.e., ignoring other +pages that have discussions, comments and such). These number about ∼124M pages across 279 languages. + +#### Who are the source language producers? + +Text was extracted from Wikipedia. + +### Annotations + +#### Annotation process + +WIT was constructed using an automatic process. However it was human-validated. + +From the [paper, section 3.7](https://arxiv.org/abs/2103.01913): + +> To further verify the quality of the WIT dataset we performed a +study using (crowd-sourced) human annotators. As seen in Fig. 3, +we asked raters to answer 3 questions. Given an image and the page +title, raters first evaluate the quality of the attribution description +and reference description in the first two questions (order randomized). The third question understands the contextual quality of these +text descriptions given the page description and caption. Each response is on a 3-point scale: ""Yes"" if the text perfectly describes +the image, ""Maybe"" if it is sufficiently explanatory and ""No"" if it is +irrelevant or the image is inappropriate. + +#### Who are the annotators? + +[More Information Needed] + +### Personal and Sensitive Information + +[More Information Needed] + +## Considerations for Using the Data + +### Social Impact of Dataset + +[More Information Needed] + +### Discussion of Biases + +From the [paper, section 3.4](https://arxiv.org/abs/2103.01913): + +> Lastly we found that certain image-text pairs occurred very +frequently. These were often generic images that did not have +much to do with the main article page. Common examples +included flags, logos, maps, insignia and such. To prevent +biasing the data, we heavily under-sampled all such images + +### Other Known Limitations + +[More Information Needed] + +## Additional Information + +### Dataset Curators + +[More Information Needed] + +### Licensing Information + +[More Information Needed] + +### Citation Information + +```bibtex +@article{srinivasan2021wit, + title={WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning}, + author={Srinivasan, Krishna and Raman, Karthik and Chen, Jiecao and Bendersky, Michael and Najork, Marc}, + journal={arXiv preprint arXiv:2103.01913}, + year={2021} +} +``` + +### Contributions + +Thanks to [@thomasw21](https://github.com/thomasw21), [@nateraw](https://github.com/nateraw) and [hassiahk](https://github.com/hassiahk) for adding this dataset." +msarmi9/korean-english-multitarget-ted-talks-task,"{""annotations_creators"": [""expert-generated""], ""language_creators"": [""other""], ""language"": [""en"", ""ko""], ""language_bcp47"": [""en-US"", ""ko-KR""], ""license"": [""cc-by-nc-nd-4.0""], ""multilinguality"": [""translation"", ""multilingual""], ""pretty_name"": ""English-Korean Multitarget Ted Talks Task (MTTT)"", ""task_categories"": [""conditional-text-generation""], ""task_ids"": [""machine-translation""]}","# Dataset Card for english-korean-multitarget-ted-talks-task + +## Table of Contents +- [Table of Contents](#table-of-contents) +- [Dataset Description](#dataset-description) + - [Dataset Summary](#dataset-summary) + - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) + - [Languages](#languages) +- [Dataset Structure](#dataset-structure) + - [Data Instances](#data-instances) + - [Data Fields](#data-fields) + - [Data Splits](#data-splits) +- [Dataset Creation](#dataset-creation) + - [Curation Rationale](#curation-rationale) + - [Source Data](#source-data) + - [Annotations](#annotations) + - [Personal and Sensitive Information](#personal-and-sensitive-information) +- [Considerations for Using the Data](#considerations-for-using-the-data) + - [Social Impact of Dataset](#social-impact-of-dataset) + - [Discussion of Biases](#discussion-of-biases) + - [Other Known Limitations](#other-known-limitations) +- [Additional Information](#additional-information) + - [Dataset Curators](#dataset-curators) + - [Licensing Information](#licensing-information) + - [Citation Information](#citation-information) + - [Contributions](#contributions) + +## Dataset Description + +- **Homepage:** https://www.cs.jhu.edu/~kevinduh/a/multitarget-tedtalks/ + +### Dataset Summary + +- Parallel English-Korean Text Corpus +- Text was originally transcribed to English from various Ted Talks, then translated to Korean by TED translators +- Approximately 166k train, 2k validation, and 2k test sentence pairs. + +### Supported Tasks and Leaderboards + +- Machine Translation + +### Languages + +- English +- Korean + +## Additional Information + +### Dataset Curators + +Kevin Duh, ""The Multitarget TED Talks Task"", http://www.cs.jhu.edu/~kevinduh/a/multitarget-tedtalks/, 2018 + +### Licensing Information + +TED makes its collection available under the Creative Commons BY-NC-ND license. Please acknowledge TED when using this data. We acknowledge the authorship of TED Talks (BY condition). We are not redistributing the transcripts for commercial purposes (NC condition) nor making derivative works of the original contents (ND condition). + +### Citation Information + +@misc{duh18multitarget, + author = {Kevin Duh}, + title = {The Multitarget TED Talks Task}, + howpublished = {\url{http://www.cs.jhu.edu/~kevinduh/a/multitarget-tedtalks/}}, + year = {2018}, +}" +DAMO-NLP-SG/MultiJail,"{""license"": ""mit"", ""task_categories"": [""conversational""], ""language"": [""en"", ""zh"", ""it"", ""vi"", ""ar"", ""ko"", ""th"", ""bn"", ""sw"", ""jv""], ""size_categories"": [""n<1K""]}","# Multilingual Jailbreak Challenges in Large Language Models + +This repo contains the data for our paper [""Multilingual Jailbreak Challenges in Large Language Models""](https://arxiv.org/abs/2310.06474). +[[Github repo]](https://github.com/DAMO-NLP-SG/multilingual-safety-for-LLMs/) + +## Annotation Statistics +We collected a total of 315 English unsafe prompts and annotated them into nine non-English languages. The languages were categorized based on resource availability, as shown below: + +**High-resource languages:** Chinese (zh), Italian (it), Vietnamese (vi) + +**Medium-resource languages:** Arabic (ar), Korean (ko), Thai (th) + +**Low-resource languages:** Bengali (bn), Swahili (sw), Javanese (jv) + +## Ethics Statement +Our research investigates the safety challenges of LLMs in multilingual settings. We are aware of the potential misuse of our findings and emphasize that our research is solely for academic purposes and ethical use. Misuse or harm resulting from the information in this paper is strongly discouraged. To address the identified risks and vulnerabilities, we commit to open-sourcing the data used in our study. This openness aims to facilitate vulnerability identification, encourage discussions, and foster collaborative efforts to enhance LLM safety in multilingual contexts. Furthermore, we have developed the SELF-DEFENSE framework to address multilingual jailbreak challenges in LLMs. This framework automatically generates multilingual safety training data to mitigate risks associated with unintentional and intentional jailbreak scenarios. Overall, our work not only highlights multilingual jailbreak challenges in LLMs but also paves the way for future research, collaboration, and innovation to enhance their safety. + +## Citation +``` +@misc{deng2023multilingual, +title={Multilingual Jailbreak Challenges in Large Language Models}, +author={Yue Deng and Wenxuan Zhang and Sinno Jialin Pan and Lidong Bing}, +year={2023}, +eprint={2310.06474}, +archivePrefix={arXiv}, +primaryClass={cs.CL} +} +```" +sentence-transformers/parallel-sentences-opensubtitles,"{""language"": [""en"", ""multilingual"", ""ar"", ""bg"", ""ca"", ""cs"", ""da"", ""de"", ""el"", ""es"", ""et"", ""fa"", ""fi"", ""fr"", ""gl"", ""he"", ""hi"", ""hr"", ""hu"", ""hy"", ""id"", ""it"", ""ja"", ""ka"", ""ko"", ""lt"", ""lv"", ""mk"", ""ms"", ""nl"", ""pl"", ""pt"", ""ro"", ""ru"", ""sk"", ""sl"", ""sq"", ""sr"", ""sv"", ""th"", ""tr"", ""uk"", ""ur"", ""vi"", ""zh""], ""size_categories"": [""100MBelow is original dataset card + +## Table of Contents +- [Dataset Summary](#dataset-summary) +- [Dataset Attribution](#dataset-attribution) +- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) +- [Languages](#languages) +- [Dataset Structure](#dataset-structure) + - [Data Instances](#data-instances) + - [Data Fields](#data-fields) + - [Data Splits](#data-splits) +- [Dataset Creation](#dataset-creation) + - [Curation Rationale](#curation-rationale) + - [Source Data](#source-data) +- [Dataset Use](#dataset-use) + - [Use Cases](#use-cases) + - [Usage Caveats](#usage-caveats) + - [Getting Started](#getting-started) + + +

🐋 The OpenOrca Dataset! 🐋

+ +![OpenOrca Logo](https://huggingface.co/datasets/Open-Orca/OpenOrca/resolve/main/OpenOrcaLogo.png ""OpenOrca Logo"") + + + +We are thrilled to announce the release of the OpenOrca dataset! +This rich collection of augmented FLAN data aligns, as best as possible, with the distributions outlined in the [Orca paper](https://arxiv.org/abs/2306.02707). +It has been instrumental in generating high-performing model checkpoints and serves as a valuable resource for all NLP researchers and developers! + +# Official Models + +## OpenOrca-Platypus2-13B + +Our [latest release](https://huggingface.co/Open-Orca/OpenOrca-Platypus2-13B), the first 13B model to score higher than LLaMA1-65B on the HuggingFace Leaderboard! +Released in partnership with Platypus. + +## LlongOrca 7B & 13B + +* Our [first 7B release](https://huggingface.co/Open-Orca/LlongOrca-7B-16k), trained on top of LLongMA2 to achieve 16,000 tokens context. #1 long context 7B model at release time, with >99% of the overall #1 model's performance. +* [LlongOrca-13B-16k](https://huggingface.co/Open-Orca/LlongOrca-13B-16k), trained on top of LLongMA2. #1 long context 13B model at release time, with >97% of the overall #1 model's performance. + +## OpenOrcaxOpenChat-Preview2-13B + +Our [second model](https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-13B), highlighting that we've surpassed the performance reported in the Orca paper. +Was #1 at release time, now surpassed by our own OpenOrca-Platypus2-13B. +Released in partnership with OpenChat. + +## OpenOrca-Preview1-13B + +[OpenOrca-Preview1-13B](https://huggingface.co/Open-Orca/OpenOrca-Preview1-13B) +This model was trained in less than a day, for <$200, with <10% of our data. +At release, it beat the current state of the art models on BigBench-Hard and AGIEval. Achieves ~60% of the improvements reported in the Orca paper. + + + +# Dataset Summary + +The OpenOrca dataset is a collection of augmented [FLAN Collection data](https://arxiv.org/abs/2301.13688). +Currently ~1M GPT-4 completions, and ~3.2M GPT-3.5 completions. +It is tabularized in alignment with the distributions presented in the ORCA paper and currently represents a partial completion of the full intended dataset, with ongoing generation to expand its scope. +The data is primarily used for training and evaluation in the field of natural language processing. + + + +# Dataset Attribution + +We would like to give special recognition to the following contributors for their significant efforts and dedication: + + + Teknium + WingLian/Caseus + Eric Hartford + NanoBit + Pankaj + Winddude + Rohan + + http://AlignmentLab.ai: + Autometa + Entropi + AtlasUnified + NeverendingToast + NanoBit + WingLian/Caseus + +Also of course, as always, TheBloke, for being the backbone of the whole community. + +Many thanks to NanoBit and Caseus, makers of [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl), for lending us their expertise on the platform that developed and trained manticore, minotaur, and many others! + +We are welcoming sponsors or collaborators to help us build these models to the scale they deserve. Please reach out via our socials: +http://Alignmentlab.ai https://discord.gg/n9hXaBPWxx + +Want to visualize our full dataset? Check out our [Nomic Atlas Map](https://atlas.nomic.ai/map/c1b88b47-2d9b-47e0-9002-b80766792582/2560fd25-52fe-42f1-a58f-ff5eccc890d2). + [](https://atlas.nomic.ai/map/c1b88b47-2d9b-47e0-9002-b80766792582/2560fd25-52fe-42f1-a58f-ff5eccc890d2) + + + + +# Supported Tasks and Leaderboards + +This dataset supports a range of tasks including language modeling, text generation, and text augmentation. +It has been instrumental in the generation of multiple high-performing model checkpoints which have exhibited exceptional performance in our unit testing. +Further information on leaderboards will be updated as they become available. + + + +# Languages + +The language of the data is primarily English. + + + +# Dataset Structure + + + +## Data Instances + +A data instance in this dataset represents entries from the FLAN collection which have been augmented by submitting the listed question to either GPT-4 or GPT-3.5. +The response is then entered into the response field. + + + +## Data Fields + +The fields are: +1) 'id', a unique numbered identifier which includes one of 'niv', 't0', 'cot', or 'flan' to represent which source FLAN Collection submix the 'question' is sourced from. +2) 'system_prompt', representing the System Prompt presented to the GPT-3.5 or GPT-4 API for the datapoint +3) 'question', representing a question entry as provided by the FLAN Collection +4) 'response', a response to that question received from a query to either GPT-3.5 or GPT-4. + + + +## Data Splits + +The data is unsplit. + + + +# Dataset Creation + + + +## Curation Rationale + +The dataset was created to provide a source of augmented text data for researchers and developers. +The datapoints are intended primarily to provide an enhancement of the core FLAN Collection data which relies upon the detailed step by step reasoning capabilities of GPT-3.5 and GPT-4. +This ""reasoning trace"" augmentation has demonstrated exceptional results, allowing a LLaMA-13B model trained with this data to rival or beat GPT-3.5 on broad sets of hard reasoning tasks which all models below 100B parameters had previously performed dramatically worse on. + + + +## Source Data + +The data is generated using techniques in alignment with the distributions outlined in the Orca paper, except as noted below: + +1) There is not enough CoT data in the FLAN Collection to generate 150K zero-shot entries, as the paper purports to use. + We suspect this portion was either undocumented or misrepresented. We have used the ~75K points available. +2) We used the pre-generated FLAN Collection datasets hosted on HuggingFace under conceptofmind, e.g. [conceptofmind/flan2021](https://huggingface.co/datasets/conceptofmind/flan2021_submix_original). + These are referenced by the [official FLAN Collection repo](https://github.com/google-research/FLAN/tree/main/flan/v2) as the preferred data source. + However, these are a subset of the full FLAN Collection data, and have less than the required entries for the flan2021 and t0 submixes, by ~1.25M and 200k respectively. + +Combined, this gave us ~1.5M fewer datapoints than in the original Orca paper. Completing the set is an ongoing work. + + + +# Dataset Use + + + +## Use Cases + +The dataset can be used for tasks related to language understanding, natural language processing, machine learning model training, and model performance evaluation. + + + +## Usage Caveats + +Given that this is a work-in-progress dataset, it is recommended to regularly check for updates and improvements. +Further, the data should be used in accordance with the guidelines and recommendations outlined in the Orca paper. + + + +## Getting Started + +This dataset is organized such that it can be naively loaded via Hugging Face datasets library. +We recommend using streaming due to the large size of the files. +Regular updates and data generation progress can be monitored through the OpenOrca repository on Hugging Face. + + +# Citation + +```bibtex +@misc{OpenOrca, + title = {OpenOrca: An Open Dataset of GPT Augmented FLAN Reasoning Traces}, + author = {Wing Lian and Bleys Goodson and Eugene Pentland and Austin Cook and Chanvichet Vong and ""Teknium""}, + year = {2023}, + publisher = {HuggingFace}, + journal = {HuggingFace repository}, + howpublished = {\url{https://https://huggingface.co/Open-Orca/OpenOrca}, +} +``` +```bibtex +@misc{mukherjee2023orca, + title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4}, + author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah}, + year={2023}, + eprint={2306.02707}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +``` +```bibtex +@misc{longpre2023flan, + title={The Flan Collection: Designing Data and Methods for Effective Instruction Tuning}, + author={Shayne Longpre and Le Hou and Tu Vu and Albert Webson and Hyung Won Chung and Yi Tay and Denny Zhou and Quoc V. Le and Barret Zoph and Jason Wei and Adam Roberts}, + year={2023}, + eprint={2301.13688}, + archivePrefix={arXiv}, + primaryClass={cs.AI} +} +``` +```bibtex +@misc{touvron2023llama, + title={Llama 2: Open Foundation and Fine-Tuned Chat Models}, + author={Hugo Touvron and Louis Martin and Kevin Stone and Peter Albert and Amjad Almahairi and Yasmine Babaei and Nikolay Bashlykov and Soumya Batra and Prajjwal Bhargava and Shruti Bhosale and Dan Bikel and Lukas Blecher and Cristian Canton Ferrer and Moya Chen and Guillem Cucurull and David Esiobu and Jude Fernandes and Jeremy Fu and Wenyin Fu and Brian Fuller and Cynthia Gao and Vedanuj Goswami and Naman Goyal and Anthony Hartshorn and Saghar Hosseini and Rui Hou and Hakan Inan and Marcin Kardas and Viktor Kerkez and Madian Khabsa and Isabel Kloumann and Artem Korenev and Punit Singh Koura and Marie-Anne Lachaux and Thibaut Lavril and Jenya Lee and Diana Liskovich and Yinghai Lu and Yuning Mao and Xavier Martinet and Todor Mihaylov and Pushkar Mishra and Igor Molybog and Yixin Nie and Andrew Poulton and Jeremy Reizenstein and Rashi Rungta and Kalyan Saladi and Alan Schelten and Ruan Silva and Eric Michael Smith and Ranjan Subramanian and Xiaoqing Ellen Tan and Binh Tang and Ross Taylor and Adina Williams and Jian Xiang Kuan and Puxin Xu and Zheng Yan and Iliyan Zarov and Yuchen Zhang and Angela Fan and Melanie Kambadur and Sharan Narang and Aurelien Rodriguez and Robert Stojnic and Sergey Edunov and Thomas Scialom}, + year={2023}, + eprint= arXiv 2307.09288 +} +@software{touvron2023llama, + title={LLaMA: Open and Efficient Foundation Language Models}, + author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and Rodriguez, Aurelien and Joulin, Armand and Grave, Edouard and Lample, Guillaume}, + journal={arXiv preprint arXiv:2302.13971}, + year={2023} +} +```" +sentence-transformers/miracl,"{""language"": [""en"", ""ar"", ""bn"", ""es"", ""fa"", ""fi"", ""fr"", ""hi"", ""id"", ""ja"", ""ko"", ""ru"", ""sw"", ""te"", ""th"", ""zh""], ""size_categories"": [""1M>> from datasets import load_dataset + +>>> dataset = load_dataset(""Bingsu/laion2b_multi_korean_subset_with_image"", streaming=True, split=""train"") + +>>> dataset.features +{'image': Image(decode=True, id=None), + 'text': Value(dtype='string', id=None), + 'width': Value(dtype='int32', id=None), + 'height': Value(dtype='int32', id=None)} + +>>> next(iter(dataset)) +{'image': , + 'text': '소닉기어 에어폰5 휴대용 스테레오 블루투스 헤드폰', + 'width': 256, + 'height': 256} +``` + +### 2. webdataset + +이 데이터셋은 [webdataset](https://github.com/webdataset/webdataset)으로 사용할 수 있도록 구성되어있습니다. 데이터를 다운로드하지 않고 스트리밍으로 처리한다면 1번 방법보다 훨씬 빠릅니다. + +!! 아래 방법은 Windows에서는 에러가 발생합니다. + +```python +>>> import webdataset as wds + +>>> url = ""https://huggingface.co/datasets/Bingsu/laion2b_multi_korean_subset_with_image/resolve/main/data/{00000..02122}.tar"" +>>> dataset = wds.WebDataset(url).shuffle(1000).decode(""pil"").to_tuple(""webp"", ""json"") +``` + +```python +>>> next(iter(dataset)) +... +``` + +이 글을 작성하는 현재(22-10-18), webp이미지의 자동 디코딩을 지원하지 않고 있기 때문에([PR #215](https://github.com/webdataset/webdataset/pull/215)), 직접 디코딩해야 합니다. + +```python +import io +import webdataset as wds +from PIL import Image + +def preprocess(data): + webp, jsn = data + img = Image.open(io.BytesIO(webp)) + out = { + ""image"": img, + ""text"": jsn[""caption""], + ""width"": jsn[""width""], + ""height"": jsn[""height""] + } + return out + +url = ""https://huggingface.co/datasets/Bingsu/laion2b_multi_korean_subset_with_image/resolve/main/data/{00000..02122}.tar"" +dataset = wds.WebDataset(url).shuffle(1000).decode(""pil"").to_tuple(""webp"", ""json"").map(preprocess) +``` + +```python +>>> next(iter(dataset)) +{'image': , + 'text': '[따블리에]유아동 미술가운, 미술 전신복', + 'width': 427, + 'height': 256} +``` + +## Note + +![tar_image](https://huggingface.co/datasets/Bingsu/laion2b_multi_korean_subset_with_image/resolve/main/tar_example.png) +각각의 tar 파일은 위 처럼 구성되어 있습니다. + +다운로드에 실패한 이미지는 건너뛰어져있기 때문에 파일 이름은 완전히 연속적이지는 않습니다. + +각각의 json 파일은 다음처럼 되어있습니다. + +```json +{ + ""caption"": ""\ub514\uc790\uc778 \uc53d\ud0b9\uacfc \ub514\uc9c0\ud138 \ud2b8\ub79c\uc2a4\ud3ec\uba54\uc774\uc158"", + ""url"": ""https://image.samsungsds.com/kr/insights/dt1.jpg?queryString=20210915031642"", + ""key"": ""014770069"", + ""status"": ""success"", + ""error_message"": null, + ""width"": 649, + ""height"": 256, + ""original_width"": 760, + ""original_height"": 300, + ""exif"": ""{}"" +} +``` + +txt파일은 json파일의 ""caption""을 담고 있습니다." +phonemetransformers/CHILDES,"{""configs"": [{""config_name"": ""English"", ""default"": true, ""data_files"": ""Eng-NA/processed.csv""}, {""config_name"": ""EnglishUK"", ""data_files"": ""Eng-UK/processed.csv""}, {""config_name"": ""French"", ""data_files"": ""French/processed.csv""}, {""config_name"": ""German"", ""data_files"": ""German/processed.csv""}, {""config_name"": ""Spanish"", ""data_files"": ""Spanish/processed.csv""}, {""config_name"": ""Dutch"", ""data_files"": ""Dutch/processed.csv""}, {""config_name"": ""Mandarin"", ""data_files"": ""Mandarin/processed.csv""}, {""config_name"": ""Japanese"", ""data_files"": ""Japanese/processed.csv""}, {""config_name"": ""Cantonese"", ""data_files"": ""Cantonese/processed.csv""}, {""config_name"": ""Estonian"", ""data_files"": ""Estonian/processed.csv""}, {""config_name"": ""Croatian"", ""data_files"": ""Croatian/processed.csv""}, {""config_name"": ""Danish"", ""data_files"": ""Danish/processed.csv""}, {""config_name"": ""Basque"", ""data_files"": ""Basque/processed.csv""}, {""config_name"": ""Hungarian"", ""data_files"": ""Hungarian/processed.csv""}, {""config_name"": ""Turkish"", ""data_files"": ""Turkish/processed.csv""}, {""config_name"": ""Farsi"", ""data_files"": ""Farsi/processed.csv""}, {""config_name"": ""Icelandic"", ""data_files"": ""Icelandic/processed.csv""}, {""config_name"": ""Indonesian"", ""data_files"": ""Indonesian/processed.csv""}, {""config_name"": ""Irish"", ""data_files"": ""Irish/processed.csv""}, {""config_name"": ""Welsh"", ""data_files"": ""Welsh/processed.csv""}, {""config_name"": ""Korean"", ""data_files"": ""Korean/processed.csv""}, {""config_name"": ""Swedish"", ""data_files"": ""Swedish/processed.csv""}, {""config_name"": ""Norwegian"", ""data_files"": ""Norwegian/processed.csv""}, {""config_name"": ""Quechua"", ""data_files"": ""Quechua/processed.csv""}, {""config_name"": ""Catalan"", ""data_files"": ""Catalan/processed.csv""}, {""config_name"": ""Italian"", ""data_files"": ""Italian/processed.csv""}, {""config_name"": ""PortuguesePt"", ""data_files"": ""PortuguesePt/processed.csv""}, {""config_name"": ""PortugueseBr"", ""data_files"": ""PortugueseBr/processed.csv""}, {""config_name"": ""Romanian"", ""data_files"": ""Romanian/processed.csv""}, {""config_name"": ""Serbian"", ""data_files"": ""Serbian/processed.csv""}, {""config_name"": ""Polish"", ""data_files"": ""Polish/processed.csv""}], ""language"": [""en"", ""de"", ""fr"", ""es"", ""nl"", ""cmn"", ""ja"", ""yue"", ""et"", ""hr"", ""da"", ""eu"", ""hu"", ""tr"", ""fa"", ""is"", ""id"", ""ga"", ""cy"", ""ko"", ""sv"", ""nb"", ""qu"", ""ca"", ""it"", ""pt"", ""ro"", ""sv"", ""pl""], ""tags"": [""language modeling"", ""cognitive modeling""], ""pretty_name"": ""Phonemized Child Directed Speech"", ""size_categories"": [""100K + + +### Original Source? +Around 11 months ago, I downloaded and preprocessed 2.7M rows of text data, but completely forgot the original source of these datasets... +All I remember is that I downloaded datasets from everywhere I could: HuggingFace, research papers, GitHub, Kaggle, SurgeAI, and Google search. I even fetched 20K+ tweets using the Twitter API. +Recently, I came across 6 datasets, so I remembered to credit them below. + +Known datasets: +- tomekkorbak/pile-toxicity-balanced2 (HuggingFace) +- datasets/thai_toxicity_tweet (HuggingFace) +- datasets/ethos (HuggingFace) +- inspection-ai/japanese-toxic-dataset (GitHub) +- mathigatti/sexting-dataset (GitHub) +- omar-sharif03/BAD-Bangla-Aggressive-Text-Dataset (GitHub) + +I manually collected and wrote 100 rows of data. + +
+ +### Loading the Dataset + +To prevent errors like [row count mismatch](https://huggingface.co/datasets/FredZhang7/toxi-text-3M/discussions/5), please add `verification_mode=""no_checks""` when loading the dataset. + +```py +from datasets import load_dataset + +ds = load_dataset(""FredZhang7/toxi-text-3M"", verification_mode=""no_checks"") +``` + + +
+ +### Limitations +Limitations include: +- All labels were rounded to the nearest integer. If a text was classified as 46%-54% toxic, the text itself might not be noticeably toxic or neutral. +- There were disagreements among moderators on some labels, due to ambiguity and lack of context. +- When there're only URL(s), emojis, or anything that's unrecognizable as natural language in the ""text"" column, the corresponding ""lang"" is ""unknown"". + +Have fun modelling!" +sentence-transformers/parallel-sentences-jw300,"{""language"": [""en"", ""multilingual"", ""ar"", ""bg"", ""cs"", ""da"", ""de"", ""el"", ""es"", ""et"", ""fa"", ""fi"", ""fr"", ""gu"", ""he"", ""hi"", ""hr"", ""hu"", ""hy"", ""id"", ""it"", ""ja"", ""ka"", ""ko"", ""lt"", ""lv"", ""mk"", ""mn"", ""mr"", ""my"", ""nl"", ""pl"", ""pt"", ""ro"", ""ru"", ""sk"", ""sl"", ""sq"", ""sv"", ""th"", ""tr"", ""uk"", ""ur"", ""vi""], ""size_categories"": [""10M 답변에 오픈 어시스턴트라고 하는 경우가 나오기 때문 +또한 스탠포드 대학 번역 데이터에서 번역 과정 오류로 input에 입력없음 과 같이 추가된 부분 삭제 +그리고 \ 등으로 gpt 상에서 번역 오류가 난 것들을 삭제 +*** +자연스러움을 위해 stanford alpaca data, oig_chip2를 ChatGPT3.5 turbo 16k를 이용하여 새롭게 전처리 과정을 거쳤습니다. +https://github.com/JoJo0217/rlhf_korean_dataset/tree/main +여기에서 자세한 설명을 볼 수 있으며 +데이터의 구성은 다음과 같습니다. +*** +데이터 구성 +|데이터 종류|개수|url| +|:---|---:|---:| +|koalpaca v1.1|21155|https://github.com/Beomi/KoAlpaca| +|stanford alpaca|51374|https://huggingface.co/datasets/tatsu-lab/alpaca| +|dolly|15009|https://huggingface.co/datasets/nlpai-lab/databricks-dolly-15k-ko| +|openassistant|9651|https://huggingface.co/datasets/nlpai-lab/openassistant-guanaco-ko| +|oig_chip2|10000|https://huggingface.co/datasets/0-hero/OIG-small-chip2| +|총합|107189||" +Muennighoff/xP3x-sample,"{""annotations_creators"": [""expert-generated"", ""crowdsourced""], ""language"": [""af"", ""ar"", ""az"", ""be"", ""bg"", ""bn"", ""br"", ""bs"", ""ca"", ""ch"", ""cs"", ""cv"", ""cy"", ""da"", ""de"", ""el"", ""en"", ""eo"", ""es"", ""et"", ""eu"", ""fa"", ""fi"", ""fo"", ""fr"", ""fy"", ""ga"", ""gd"", ""gl"", ""gn"", ""he"", ""hi"", ""hr"", ""hu"", ""hy"", ""ia"", ""id"", ""ie"", ""io"", ""is"", ""it"", ""ja"", ""jv"", ""ka"", ""kk"", ""km"", ""ko"", ""ku"", ""kw"", ""la"", ""lb"", ""lt"", ""lv"", ""mi"", ""mk"", ""ml"", ""mn"", ""mr"", ""ms"", ""mt"", ""my"", ""nb"", ""nl"", ""nn"", ""no"", ""oc"", ""pl"", ""pt"", ""qu"", ""rn"", ""ro"", ""ru"", ""sh"", ""sl"", ""sq"", ""sr"", ""sv"", ""sw"", ""ta"", ""te"", ""th"", ""tk"", ""tl"", ""tr"", ""tt"", ""ug"", ""uk"", ""ur"", ""uz"", ""vi"", ""vo"", ""yi"", ""zh"", ""ace"", ""acm"", ""acq"", ""aeb"", ""af"", ""ajp"", ""ak"", ""als"", ""am"", ""apc"", ""ar"", ""ars"", ""ary"", ""arz"", ""as"", ""ast"", ""awa"", ""ayr"", ""azb"", ""azj"", ""ba"", ""bm"", ""ban"", ""be"", ""bem"", ""bn"", ""bho"", ""bjn"", ""bo"", ""bs"", ""bug"", ""bg"", ""ca"", ""ceb"", ""cs"", ""cjk"", ""ckb"", ""crh"", ""cy"", ""da"", ""de"", ""dik"", ""dyu"", ""dz"", ""el"", ""en"", ""eo"", ""et"", ""eu"", ""ee"", ""fo"", ""fj"", ""fi"", ""fon"", ""fr"", ""fur"", ""fuv"", ""gaz"", ""gd"", ""ga"", ""gl"", ""gn"", ""gu"", ""ht"", ""ha"", ""he"", ""hi"", ""hne"", ""hr"", ""hu"", ""hy"", ""ig"", ""ilo"", ""id"", ""is"", ""it"", ""jv"", ""ja"", ""kab"", ""kac"", ""kam"", ""kn"", ""ks"", ""ka"", ""kk"", ""kbp"", ""kea"", ""khk"", ""km"", ""ki"", ""rw"", ""ky"", ""kmb"", ""kmr"", ""knc"", ""kg"", ""ko"", ""lo"", ""lij"", ""li"", ""ln"", ""lt"", ""lmo"", ""ltg"", ""lb"", ""lua"", ""lg"", ""luo"", ""lus"", ""lvs"", ""mag"", ""mai"", ""ml"", ""mar"", ""min"", ""mk"", ""mt"", ""mni"", ""mos"", ""mi"", ""my"", ""nl"", ""nn"", ""nb"", ""npi"", ""nso"", ""nus"", ""ny"", ""oc"", ""ory"", ""pag"", ""pa"", ""pap"", ""pbt"", ""pes"", ""plt"", ""pl"", ""pt"", ""prs"", ""quy"", ""ro"", ""rn"", ""ru"", ""sg"", ""sa"", ""sat"", ""scn"", ""shn"", ""si"", ""sk"", ""sl"", ""sm"", ""sn"", ""sd"", ""so"", ""st"", ""es"", ""sc"", ""sr"", ""ss"", ""su"", ""sv"", ""swh"", ""szl"", ""ta"", ""taq"", ""tt"", ""te"", ""tg"", ""tl"", ""th"", ""ti"", ""tpi"", ""tn"", ""ts"", ""tk"", ""tum"", ""tr"", ""tw"", ""tzm"", ""ug"", ""uk"", ""umb"", ""ur"", ""uzn"", ""vec"", ""vi"", ""war"", ""wo"", ""xh"", ""ydd"", ""yo"", ""yue"", ""zh"", ""zsm"", ""zu""], ""programming_language"": [""Java"", ""Python"", ""Jupyter-Notebook""], ""license"": [""apache-2.0""], ""multilinguality"": [""multilingual""], ""pretty_name"": ""xP3x"", ""size_categories"": [""100M + additional details + +The columns corresponding to annotations collected from our cultural bias study (i.e. 'required_knowledge', 'time_sensitive', 'reference', 'culture', 'region', 'country') contain a list of values representing annotations from different annotators. +However, to avoid conversion issues to HF dataset, these columns are provided as string in the final dataset. +You can convert these columns back to list of values for easier manipulation as follows: +```python +import ast + +# convert string values to list +gmmlu_lite_test['required_knowledge'] = gmmlu_lite_test['required_knowledge'].apply(lamda x: ast.literal_eval(x)) +``` + +
+ + +## Data Fields + +The data fields are the same among all splits. Brief description of each field is provided below. + +
+ data field description + +- `sample_id`: A unique identifier for the question. +- `subject`: The main topic the question falls under. +- `subject_category`: The high-level category the subject falls under i.e. STEM/Humanities/Social Sciences/Medical/Business/Other. +- `question`: translated question from MMLU +- `option_a`: one of the possible option choices +- `option_b`: one of the possible option choices +- `option_c`: one of the possible option choices +- `option_d`: one of the possible option choices +- `answer': the correct answer (A/B/C/D) +- `required_knowledge`: annotator votes for knowledge needed to answer the question correctly. Possible values include: ""cultural"", ""regional"", ""dialect"" or ""none"" +- `time_sensitive`: annotator votes indicating if the question's answer is time-dependent. Possible values include: Yes/No +- `reference`: annotations for which part of the question contains cultural/regional/dialect references. The different items in the list are annotations from different annotators. +- `culture`: annotations for which culture does the question belong to. The different items in the list correspond to annotations from different annotators. +- `region`: Geographic region the question is relevant to. Each item in the list correspond to annotations from different annotators. +- `country`: Specific country the question pertains to. Each item in the list correspond to annotations from different annotators. +- `cultural_sensitivity_label`: Label to indicate if question is culturally sensitive (CS) or culturally agnostic (CA) based on annotator votes. +- `is_annotated`: True/False flag to indicate if sample contains any annotations from our cultural bias study. + +
+
+ +## Data Splits +The following are the splits of the data: +| Split | No. of instances | Language Coverage | +|-------|------------------|-------------------| +| test | 6,000 | 15 | +| dev | 4,275 | 15 | + + +## Data Instances + +An example from `test` set looks as follows: +```json +{'sample_id': 'astronomy/test/58', + 'subject': 'astronomy', + 'subject_category': 'STEM', + 'question': 'When traveling north from the United States into Canada you’ll see the North Star (Polaris) getting _________.', + 'option_a': 'Brighter', + 'option_b': 'Dimmer', + 'option_c': 'Higher in the sky', + 'option_d': 'Lower in the sky', + 'answer': 'C', + 'required_knowledge': ""['regional', 'regional', 'regional', 'regional']"", + 'time_sensitive': ""['No', 'No', 'No', 'No']"", + 'reference': ""[{'end': 55, 'label': 'Geographic', 'score': None, 'start': 5}, {'end': 43, 'label': 'Geographic', 'score': None, 'start': 30}, {'end': 55, 'label': 'Geographic', 'score': None, 'start': 5}, {'end': 43, 'label': 'Geographic', 'score': None, 'start': 30}]"", + 'culture': '[]', + 'region': ""['North America', 'North America', 'North America', 'North America']"", + 'country': ""['United States of America (USA)', 'United States of America (USA)', 'United States of America (USA)', 'United States of America (USA)']"", + 'cultural_sensitivity_label': 'CS', + 'is_annotated': True +} +``` + +## Statistics +### Annotation Types +The following is the breakdown of CS🗽, CA⚖️ and MA📝 samples in the final dataset. + +| Type of Annotation | Instances per language | No. of languages | Total instances +|--------------------|------------------------|------------------|----------------| +| Culturally Sensitive 🗽 | 200 | 15 | 3,000 | +| Culturally Agnostic ⚖️ | 200 |15 | 3,000 | +| MMLU Annotated 📝| 400 |15 | 6,000 | + +### Languages +The dataset covers 15 languages. The following is details about the languages included in the dataset. + +
+ Languages Info + +| ISO Code | Language | Resources | +|----------|----------|-----------| +| `ar` | Arabic (Standard)| High | +| `bn` | Bengali | Mid | +| `de` | German | High | +| `en` | English | High | +| `fr` | French | High | +| `hi` | Hindi | High | +| `id` | Indonesian | Mid | +| `it` | Italian | High | +| `ja` | Japanese | High | +| `ko` | Korean | Mid | +| `pt` | Portuguese | High | +| `es` | Spanish | High | +| `sw` | Swahili | Low | +| `yo` | Yorùbá | Low | +| `zh` | Chinese (Simplified) | High | +
+
+ +# Known Limitations +A brief overview of limitations of this dataset is provided below. +
+ show limitations + +- **Language and dialect coverage:** Global-MMLU focusses on 42 languages. However, this is still only a tiny fraction of the world’s linguistic diversity. Future work is needed to continue to improve evaluations beyond these 42 languages and take into account how technology serves different dialects. +- **Uneven distribution of contributions:** The dataset contains translation post-edits from community volunteers, with a 'long tail' of volunteers making only one or two contributions. Similarly, there is a huge gap between languages with the highest number of contributions and ones with the lowest number of contributions. +- **Toxic or offensive speech:** Our annotation process did not focus on flagging for toxic,harmful, or offensive speech, so it is possible that Global-MMLU contains some data that could be considered harmful. We believe this is of relatively low risk because of the nature of the original MMLU and the focus on examination material. +- **Region Category Assignment:** For the annotation of geographically sensitive questions, we classified regions into six geographic regions (Africa, Asia, Europe, North America, Oceania,and South America). However, based upon discussions we would going forward recommend switching to the taxonomy proposed by the World Bank which is more granular and includes separate designations for Central America and Sub-Saharan Africa. +- **Identifying cultural sensitivity does not guarantee cultural inclusion:** While Global-MMLU highlights important limitations in current datasets by identifying gaps in non-Western cultural representation. Future work must prioritize the integration of diverse culturally grounded knowledge to achieve true inclusivity and fairness in multilingual AI evaluation. + +
+
+ +# Additional Information + +## Provenance +- **Methods Used:** Professional annotations as well as crowd-sourced through volunteer annotations. +- **Methodology Details:** We collected cultural bias annotations as well as post-edits of translations for different mmlu questions. + - [Cultural Sensitivity Annotation Platform](https://huggingface.co/spaces/CohereForAI/MMLU-evaluation) + - [Translation Quality Annotation Platform](https://huggingface.co/spaces/CohereForAI/review-mmlu-translations) + - Dates of Collection: May 2024 - Aug 2024 + + +## Dataset Version and Maintenance +- **Maintenance Status:** Actively Maintained +- **Version Details:** + - *Current version:* 1.0 + - *Last Update:* 12/2024 + - *First Release:* 12/2024 + + +## Authorship +- **Publishing Organization:** [Cohere For AI](https://cohere.com/research) +- **Industry Type:** Not-for-profit - Tech + +## Licensing Information +This dataset can be used for any purpose, under the terms of the [Apache 2.0](https://opensource.org/license/apache-2-0) License. + +## Continuous Improvement: +If you want to contribute to improving the quality of translations in Global-MMLU-Lite then please contribute using our [annotation UI](https://huggingface.co/spaces/CohereForAI/review-global-mmlu-lite). +You can also help review and edit machine translations in additional languages using our annotation interface to help improve language coverage of Global-MMLU-Lite. + +## Additional Details +For any additional details, please check our paper, [Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation](https://arxiv.org/abs/2412.03304). + + +## Citation Information +```bibtex +@misc{singh2024globalmmluunderstandingaddressing, + title={Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation}, + author={Shivalika Singh and Angelika Romanou and Clémentine Fourrier and David I. Adelani and Jian Gang Ngui and Daniel Vila-Suero and Peerat Limkonchotiwat and Kelly Marchisio and Wei Qi Leong and Yosephine Susanto and Raymond Ng and Shayne Longpre and Wei-Yin Ko and Madeline Smith and Antoine Bosselut and Alice Oh and Andre F. T. Martins and Leshem Choshen and Daphne Ippolito and Enzo Ferrante and Marzieh Fadaee and Beyza Ermis and Sara Hooker}, + year={2024}, + eprint={2412.03304}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2412.03304}, +} +```" +gsarti/iwslt2017_context,"{""annotations_creators"": [""crowdsourced""], ""language"": [""ar"", ""de"", ""en"", ""fr"", ""it"", ""ja"", ""ko"", ""nl"", ""ro"", ""zh""], ""language_creators"": [""expert-generated""], ""license"": [""cc-by-nc-nd-4.0""], ""multilinguality"": [""translation""], ""pretty_name"": ""IWSLT 2017"", ""size_categories"": [""1M>> from datasets import load_dataset +>>> ko_lima = load_dataset('taeshahn/ko-lima', 'plain') # or load_dataset('taeshahn/ko-lima') +>>> ko_lima_vicuna = load_dataset('taeshahn/ko-lima', 'vicuna') +``` + +```python +>>> ko_lima['train'][1025] +{ + 'conversations': [ + '저는 케냐 출신입니다. 망명을 신청하고 싶은데 비자없이 네덜란드로 망명을 신청하기 위해 여행할 수 있나요? 케냐항공에서 여권을 소지한 경우 스키폴 공항으로 가는 비자없이 비행기에 탑승할 수 있나요?', + '항공사가 탑승을 허용할 가능성은 극히 낮습니다. 네덜란드에 입국하려는 케냐 시민은 비자, 체류 기간에 필요한 충분한 자금 증명, 다음 목적지 입국에 필요한 서류를 소지해야 합니다. 또한 항공사는 케냐에서 출발하는 승객에 대해 특별 조사를 실시해야 합니다:\n\n> 다음 공항에서 네덜란드로 운항하는 항공사:\n\n아부다비(AUH), 아크라(ACC), 바레인(BAH), 베이징 캐피탈(PEK), 보리스필(KBP), 카이로(CAI), 담만(DMM), 다르에스살람(DAR), 두바이(DXB), 엔테베(EBB), 광저우(CAN), 홍콩(HKG), 하마드(DOH), 이스탄불 아타튀르크(IST), 이스탄불 사비하곡첸(SAW), 요하네스버그(JNB), 키갈리(KGL), 킬리만자로(JRO), 쿠알라룸푸르(KUL), 쿠웨이트(KWI), 라고스(LOS), 모스크바 셰레메티예보(SVO), 무스카트(MCT), 나이로비(NB ), 뉴델리(DEL), 상파울루(GRU), 싱가포르(SIN) 및 테헤란(IKA)은 네덜란드 도착 시 적절한 여행 서류가 없어 입국할 수 없는 경우 해당 항공편의 모든 승객의 여행 서류 사본을 제출하셔야 합니다. 사본에는 여권/여행 서류의 데이터 페이지, 비자가 있는 페이지, 출국/통관 스탬프가 있는 페이지(해당되는 경우)가 포함되어야 합니다. 이러한 입국 규정을 준수하지 않을 경우 항공사에 승객 1인당 최대 11,250유로의 벌금이 부과될 수 있습니다.\n\n마지막 문장에서 볼 수 있듯이 항공사는 탑승 전에 여행 서류를 확인해야 하는 강력한 인센티브를 갖게 됩니다.', + '인용된 자료의 출처는 무엇인가요?', + '출처는 항공을 통해 해외로 여행하는 승객의 여권 및 비자 요건과 같은 서류 요건이 포함된 데이터베이스인 Timatic(여행 정보 매뉴얼 자동)에서 가져온 것입니다. 위의 답변은 목적지가 네덜란드이고 귀국/귀국 여행 증빙이 있으며 5일간 체류할 계획이며 케냐 여권의 유효 기간이 약 3년 남은 케냐 시민이 케냐에서 직접 여행하는 시나리오를 기반으로 한 것입니다.' + ], + 'source': 'multi_turn' +} +``` + +```python +>>> ko_lima_vicuna['train'][1025] +{ + 'id': '1026-multi_turn', + 'conversations': [ + { + 'from': '사람', + 'value': '저는 케냐 출신입니다. 망명을 신청하고 싶은데 비자없이 네덜란드로 망명을 신청하기 위해 여행할 수 있나요? 케냐항공에서 여권을 소지한 경우 스키폴 공항으로 가는 비자없이 비행기에 탑승할 수 있나요?' + }, + { + 'from': '어시스턴트', + 'value': '항공사가 탑승을 허용할 가능성은 극히 낮습니다. 네덜란드에 입국하려는 케냐 시민은 비자, 체류 기간에 필요한 충분한 자금 증명, 다음 목적지 입국에 필요한 서류를 소지해야 합니다. 또한 항공사는 케냐에서 출발하는 승객에 대해 특별 조사를 실시해야 합니다:\n\n> 다음 공항에서 네덜란드로 운항하는 항공사:\n\n아부다비(AUH), 아크라(ACC), 바레인(BAH), 베이징 캐피탈(PEK), 보리스필(KBP), 카이로(CAI), 담만(DMM), 다르에스살람(DAR), 두바이(DXB), 엔테베(EBB), 광저우(CAN), 홍콩(HKG), 하마드(DOH), 이스탄불 아타튀르크(IST), 이스탄불 사비하곡첸(SAW), 요하네스버그(JNB), 키갈리(KGL), 킬리만자로(JRO), 쿠알라룸푸르(KUL), 쿠웨이트(KWI), 라고스(LOS), 모스크바 셰레메티예보(SVO), 무스카트(MCT), 나이로비(NB ), 뉴델리(DEL), 상파울루(GRU), 싱가포르(SIN) 및 테헤란(IKA)은 네덜란드 도착 시 적절한 여행 서류가 없어 입국할 수 없는 경우 해당 항공편의 모든 승객의 여행 서류 사본을 제출하셔야 합니다. 사본에는 여권/여행 서류의 데이터 페이지, 비자가 있는 페이지, 출국/통관 스탬프가 있는 페이지(해당되는 경우)가 포함되어야 합니다. 이러한 입국 규정을 준수하지 않을 경우 항공사에 승객 1인당 최대 11,250유로의 벌금이 부과될 수 있습니다.\n\n마지막 문장에서 볼 수 있듯이 항공사는 탑승 전에 여행 서류를 확인해야 하는 강력한 인센티브를 갖게 됩니다.' + }, + { + 'from': '사람', + 'value': '인용된 자료의 출처는 무엇인가요?' + }, + { + 'from': '어시스턴트', + 'value': '출처는 항공을 통해 해외로 여행하는 승객의 여권 및 비자 요건과 같은 서류 요건이 포함된 데이터베이스인 Timatic(여행 정보 매뉴얼 자동)에서 가져온 것입니다. 위의 답변은 목적지가 네덜란드이고 귀국/귀국 여행 증빙이 있으며 5일간 체류할 계획이며 케냐 여권의 유효 기간이 약 3년 남은 케냐 시민이 케냐에서 직접 여행하는 시나리오를 기반으로 한 것입니다.' + } + ] +} +``` + +### Citation Information +``` +@InProceedings{kolimadataset, + title = {KoLIMA: Korean LIMA Dataset for Efficient Instruction-tuning}, + author = {Hahn, Taeseung}, + year = {2023} +} +```" +kuotient/gsm8k-ko,"{""dataset_info"": {""features"": [{""name"": ""question"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""question_en"", ""dtype"": ""string""}, {""name"": ""answer_en"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 8792462, ""num_examples"": 7473}, {""name"": ""test"", ""num_bytes"": 1585126, ""num_examples"": 1319}], ""download_size"": 6575639, ""dataset_size"": 10377588}, ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""train"", ""path"": ""data/train-*""}, {""split"": ""test"", ""path"": ""data/test-*""}]}], ""language"": [""ko""], ""pretty_name"": ""g""}","번역 모델 `kuotient/Seagull-13B-translate` 사용. + +## How to evaluate +``` +git clone https://github.com/kuotient/lm-evaluation-harness.git +cd lm-evaluation-harness +pip install -e . +``` + +``` +lm_eval --model hf \ + --model_args pretrained=yanolja/EEVE-Korean-Instruct-2.8B-v1.0 \ + --tasks gsm8k-ko \ + --device cuda:0 \ + --batch_size auto:4 +``` +혹은 원본 lm-evaluation-harness에서 + +데이터셋 내의 `gsm8k-ko.yaml` 파일을 `lm-evaluation-harness/tasks/gsm8k-ko` 내에 생성해 사용." +leey4n/KR3,"{""annotations_creators"": [], ""language_creators"": [], ""language"": [""ko""], ""license"": [""cc-by-nc-sa-4.0""], ""multilinguality"": [""monolingual""], ""pretty_name"": ""KR3"", ""size_categories"": [""100K + ""num_docs"": + ""title"": + ""intro"": + ""section_name"": + ""previous_text"": + ""question"": + ""gold_section_text"": + ""en_gold_section_text"": + ""citations"": +} +``` + +## Licensing and Takedown + +MegaWika 1.0 consists in part of documents scraped from across the web (based on citations linked in Wikipedia articles.) + +We do not own any of the scraped text nor do we claim copyright: text drawn from Wikipedia citations are meant for research use in algorithmic design and model training. + +We release this dataset and all its contents under CC-BY-SA-4.0. + +### Notice and Takedown Policy: +*NB*: Should you consider that our data contains material that is owned by you and should therefore not be reproduced here, please: + +- Clearly identify yourself, with detailed contact data such as an address, telephone number or email address at which you can be contacted. +- Clearly identify the copyrighted work claimed to be infringed. +- Clearly identify the material that is claimed to be infringing and information reasonably sufficient to allow us to locate the material. + +And contact the authors. + +*Take down*: We will comply to legitimate requests by removing the affected sources from the next release of the dataset. + +## Usage + +``` +# all of the dataset (not recommended) +dataset = load_dataset(""hltcoe/megawika-report-generation"") + +# just the `all`` section data (all splits) +dataset = load_dataset(""hltcoe/megawika-report-generation"", data_dir=""all"") + +# just the `all` English test set (can replace with ""validation"" or ""train"", or other langs) +dataset = load_dataset(""hltcoe/megawika-report-generation"", data_dir=""all/en"", split=""test"") +``` + +### Dataset Curators + +Released and maintained by the Johns Hopkins University Human Language Technology Center of Excellence (JHU/HLTCOE). +You can contact one the MegaWika authors, including [Samuel Barham](mailto:samuel.barham@jhuapl.edu), [Orion Weller](mailto:oweller2@jhu.edu), +and [Ben van Durme](mailto:vandurme@jhu.edu) with questions. + +### Licensing Information + +Released under the [Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)](https://creativecommons.org/licenses/by-sa/4.0/) license. + +### Citation Information + +``` +@misc{barham2023megawika, + title={MegaWika: Millions of reports and their sources across 50 diverse languages}, + author={Samuel Barham and and Weller and Michelle Yuan and Kenton Murray and Mahsa Yarmohammadi and Zhengping Jiang and Siddharth Vashishtha and Alexander Martin and Anqi Liu and Aaron Steven White and Jordan Boyd-Graber and Benjamin Van Durme}, + year={2023}, + eprint={2307.07049}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +```" +joonhok-exo-ai/korean_law_open_data_precedents,"{""language"": [""ko""], ""tags"": [""legal""], ""size_categories"": [""10K, + + # text containing w words (one per language) separated by underscores + 'text': 'σπιτάκι πουλιών_ドーム_प्रयोगशाला कोट_мавпа-павук_gown', + + # target word class name in English (key in translations.json) + 'cls': 'dome', + + # class ID from translations.json (0 to 999) + 'cls_id': 538, + + # target word (class name in the language of the audio) + 'target_text': 'ドーム' +} +``` + +The dataset includes a `translations.json` file that maps ImageNet class names across all supported languages. Each entry contains: +- The English class name as the key +- Translations for all supported languages (`ar`, `el`, `en`, `hi`, `ja`, `ko`, `te`, `th`, `uk`, `zh-CN`) +- The ImageNet synset ID +- A unique class ID (0-999) + +Example structure: +```json +{ + ""tench"": { + ""synset_id"": ""n01440764"", + ""cls_id"": 0, + ""ar"": ""سمك البنش"", + ""el"": ""είδος κυπρίνου"", + ""en"": ""tench"", + ""hi"": ""टेंच"", + ""ja"": ""テンチ"", + ""ko"": ""텐치"", + ""te"": ""టెంచ్"", + ""th"": ""ปลาเทนช์"", + ""uk"": ""линь"", + ""zh-CN"": ""丁鱥"" + } +} +``` + +## Dataset Variants +We release three variants of the dataset: +- Symile-M3-2 with 2 languages: English (`en`) and Greek (`el`). +- Symile-M3-5 with 5 languages: English (`en`), Greek (`el`), Hindi (`hi`), Japanese (`ja`), and Ukrainian (`uk`). +- Symile-M3-10 with 10 languages: Arabic (`ar`), Greek (`el`), English (`en`), Hindi (`hi`), Japanese (`ja`), Korean (`ko`), Telugu (`te`), Thai (`th`), Ukrainian (`uk`), and Chinese (`zh-CN`). + +Each variant is available in four sizes: +- Large (`l`): 10M training samples, 500K validation samples, 500K test samples +- Medium (`m`): 5M training samples, 250K validation samples, 250K test samples +- Small (`s`): 1M training samples, 50K validation samples, 50K test samples +- Extra Small (`xs`): 500K training samples, 25K validation samples, 25K test samples + +## Usage + +Before using the dataset, ensure you have the required audio and image processing libraries installed: +```bash +pip install librosa soundfile pillow +``` + +To load a specific version of Symile-M3, use a configuration name following the pattern `symile-m3-{num_langs}-{size}` where: +- `num_langs` is `2`, `5`, or `10` +- `size` is `xs`, `s`, `m`, or `l` + +For example, to load the `xs` version of Symile-M3-5: + +```python +from datasets import load_dataset + +dataset = load_dataset(""arsaporta/symile-m3"", ""symile-m3-5-xs"") + +print(dataset['train'][0]) # access first train sample +print(len(dataset['train'])) # get number of train samples +``` + +To process the dataset without loading it entirely into memory, use streaming mode to load samples one at a time: + +```python +from datasets import load_dataset + +dataset = load_dataset(""arsaporta/symile-m3"", ""symile-m3-5-xs"", streaming=True) + +print(next(iter(dataset['train']))) +``` + +To download the dataset for offline use: + +```python +import os +from datasets import load_dataset +from huggingface_hub import snapshot_download + +local_dir = ""./symile-m3-5-xs"" # where to save + +# download parquet files +snapshot_download( + repo_id=""arsaporta/symile-m3"", + repo_type=""dataset"", + local_dir=local_dir, + allow_patterns=[""symile-m3-5-xs/*""] # which configuration to download +) + +# load the downloaded parquet files +dataset = load_dataset( + ""parquet"", + data_files={ + ""train"": os.path.join(data_dir, ""train-*.parquet""), + ""validation"": os.path.join(data_dir, ""val-*.parquet""), + ""test"": os.path.join(data_dir, ""test-*.parquet"") + } +) +``` + +## Working with Raw Data + +To work directly with the source images (jpeg) and audio (mp3): + +1. Download the source data: + - **ImageNet:** Get the training data from [Kaggle's ImageNet Challenge](https://www.kaggle.com/c/imagenet-object-localization-challenge/data?select=ILSVRC) + - **Common Voice:** Download your needed languages from [Common Voice](https://commonvoice.mozilla.org/en/datasets): + * All languages use Common Voice v16.0, except English which uses v14.0 + * Required languages vary by configuration: + - Symile-M3-2: English (`en`), Greek (`el`) + - Symile-M3-5: English, Greek, Hindi (`hi`), Japanese (`ja`), Ukrainian (`uk`) + - Symile-M3-10: All of the above plus Arabic (`ar`), Korean (`ko`), Telugu (`te`), Thai (`th`), Chinese (`zh-CN`) + +2. Access the dataset CSV files: + - Find them in the `.csv_files` directory, organized by configuration (e.g., `symile-m3-2-xs`, `symile-m3-10-l`) + - Each configuration contains `train.csv`, `val.csv`, and `test.csv` + - CSV paths match the default extraction paths of ImageNet (`ILSVRC/Data/CLS-LOC/train/...`) and Common Voice (`cv/{lang}/clips/...`) + +## Citation + +``` +@inproceedings{saporta2024symile, + title = {Contrasting with Symile: Simple Model-Agnostic Representation Learning for Unlimited Modalities} + author = {Saporta, Adriel and Puli, Aahlad and Goldstein, Mark and Ranganath, Rajesh} + booktitle = {Advances in Neural Information Processing Systems}, + year = {2024} +} +```" +bltlab/lr-sum,"{""license"": ""cc-by-4.0"", ""task_categories"": [""summarization"", ""text-generation""], ""annotations_creators"": [""found""], ""language_creators"": [""found""], ""language"": [""am"", ""az"", ""bn"", ""bo"", ""bs"", ""ku"", ""zh"", ""el"", ""en"", ""fa"", ""fr"", ""ht"", ""ha"", ""hy"", ""id"", ""ka"", ""km"", ""rw"", ""ko"", ""lo"", ""mk"", ""my"", ""nd"", ""pt"", ""ps"", ""ru"", ""sn"", ""so"", ""es"", ""sq"", ""sr"", ""sw"", ""th"", ""ti"", ""tr"", ""uk"", ""ur"", ""uz"", ""vi""], ""pretty_name"": ""LR-Sum"", ""size_categories"": [""100K +

HALvest

+

Open Scientific Papers Harvested from HAL (Unfiltered)

+
+ +--- + + +## Dataset Description + +- **Repository:** [GitHub](https://github.com/Madjakul/HALvesting/tree/main) + + +## Dataset Summary + +### overview: + +This is the unfiltered version of [HALvest](https://huggingface.co/datasets/Madjakul/HALvest), comprising of fulltext from open papers found on [Hyper Articles en Ligne (HAL)](https://hal.science/) with extra fields for potential filtering. Our dump is mostly english/french but gather papers written in 56 languages across 13 domains. + +You can download the dataset using Hugging Face datasets: +```py +from datasets import load_dataset + +ds = load_dataset(""almanach/HALvest"", ""en"") +``` + + +### Details + +Building the dataset is a three steps process: data fetching from HAL, data merging and data enriching. + +1. We first request [HAL's API](https://api.archives-ouvertes.fr/docs) in order to gather open research papers and parse it -- effectively sorting papers by language. Then, we download the PDFs of the fetched data. +2. Using [GROBID](https://github.com/kermitt2/grobid), we convert each PDF to an `xml-tei` format in order to have structured data. We convert each `xml-tei` file to a `txt` format before concatenating it with the paper's. +3. Finally, we compute some statistics about each document. + + +### Languages + +Please, note that the number of tokens is highly inflated in the raw version of the dataset because of badly encoded PDFs, translating to gibberish documents/texts. + +ISO-639|Language|# Documents|# mT5 Tokens +-------|--------|-----------|-------- +en|English|464,679|8,158,933,235 +fr|French|199,216|9,018,529,985 +es|Spanish|2,975|69,221,667 +it|Italian|1,172|48,747,986 +pt|Portuguese|934|32,918,832 +de|German|652|12,225,960 +ru|Russian|245|5,763,532 +zh|Chinese|160|2,861,585 +eu|Basque|113|2,297,485 +ar|Arabic|92|2,167,431 +ja|Japanese|92|547,861 +el|Greek|54|1,738,878 +pl|Polish|43|987,878 +ro|Romanian|39|1,298,901 +uk|Ukrainian|34|837,793 +vi|Viêt Namese|29|436,660 +ca|Catalan|28|975,078 +da|Danish|27|961,955 +oc|Occitan|26|285,334 +br|Breton|24|998,088 +sr|Serbian|24|336,878 +ko|Korean|17|226,268 +fa|Persian|17|213,903 +tr|Turkish|17|149,718 +hu|Hungarian|14|577,568 +eo|Esperanto|14|105,286 +hy|Armenian|10|127,988 +cs|Czech|9|712,263 +bg|Bulgarian|9|208,763 +sq|Albanian|9|98,009 +id|Indonesian|9|53,075 +he|Hebrew|8|61,283 +hr|Croatian|8|40,621 +et|Estonian|7|20,405 +sv|Swedish|6|270,642 +no|Norwegian|6|62,767 +az|Azerbaijani|5|52,762 +fi|Finnish|4|60,507 +tet|Tetum|4|18,485 +lt|Lithuanian|3|16,572 +mr|Marathi|3|16,386 +hi|Hindi|3|3,490 +ie|Interlingue|2|140,383 +ta|Tamil|2|77,087 +sw|Swahili|2|73,921 +tl|Tagalog|2|35,962 +gl|Galician|2|29,688 +mk|Macedonian|2|14,654 +th|Thai|1|70,909 +tk|Turkmen|1|66,104 +bs|Bosnian|1|63,018 +kk|Kazakh|1|41,839 +sl|Slovenian|1|22,844 +sk|Slovak|1|12,997 +co|Corsican|1|9,083 +gn|Guarani|1|1,566 +bo|Tibetan|1|579 + + +### Domains + +Please, note that the number of tokens is highly inflated in the raw version of the dataset because of badly encoded PDFs, translating to gibberish documents/texts. + +Domain|Code|# Documents|# mT5 Tokens +------|----|-----------|------------ +Humanities and Social Sciences|shs|156,566|5,614,423,171 +Computer Science|info|148,316|2,573,673,455 +Life Sciences|sdv|115,744|3,145,323,780 +Engineering Sciences|spi|102,751|2,254,653,825 +Physics|phys|65,991|1,503,190,749 +Mathematics|math|62,921|1,638,500,361 +Chemical Science|chim|40,012|899,507,319 +Environmental Science|sde|31,575|579,076,669 +Sciences of the Universe|sdu|23,557|682,356,264 +Cognitive science|scco|11,772|227,487,096 +Statistics|stat|10,579|184,678,350 +Quantitative Finance|qfin|3,451|68,518,636 +Nonlinear Sciences|nlin|1,972|30,694,088 + +You can browse through every domains and sub-domains here: https://hal.science/browse/domain. + + +## Considerations for Using the Data + +The corpus is extracted from the [HAL's open archive](https://hal.science/) which distributes scientific publications following open access principles. The corpus is made up of both creative commons licensed and copyrighted documents (distribution authorized on HAL by the publisher). This must be considered prior to using this dataset for any purpose, other than training deep learning models, data mining etc. We do not own any of the text from which these data has been extracted. + + +## Citation + +```bib +@misc{kulumba2024harvestingtextualstructureddata, + title={Harvesting Textual and Structured Data from the HAL Publication Repository}, + author={Francis Kulumba and Wissam Antoun and Guillaume Vimont and Laurent Romary}, + year={2024}, + eprint={2407.20595}, + archivePrefix={arXiv}, + primaryClass={cs.DL}, + url={https://arxiv.org/abs/2407.20595}, +} +``` + + +## Dataset Copyright + +The licence terms for HALvest strictly follows the one from HAL. Please refer to the below license when using this dataset. +- [HAL license](https://doc.archives-ouvertes.fr/en/legal-aspects/)" +davidkim205/ko_hellaswag,"{""language"": [""ko""]}","# Korean HellaSwag +hellaswag 영어 데이터셋을 한국어로 번역 + +https://huggingface.co/datasets/Rowan/hellaswag + +## Structure +```jsonl +{ + ""ind"": 24, + ""activity_label"": ""지붕 슁글 제거"", + ""ctx_a"": ""한 남자가 지붕 위에 앉아 있다."", + ""ctx_b"": ""그"", + ""ctx"": ""한 남자가 지붕 위에 앉아 있다. 그"", + ""endings"": [ + ""스키 한 켤레를 감싸기 위해 랩을 사용하고 있습니다."", + ""레벨 타일을 뜯어내고 있습니다."", + ""루빅스 큐브를 들고 있습니다."", + ""지붕에 지붕을 올리기 시작합니다."" + ], + ""source_id"": ""activitynet~v_-JhWjGDPHMY"", + ""split"": ""val"", + ""split_type"": ""indomain"", + ""label"": ""3"" +} +{...} +```" +squarelike/OpenOrca-gugugo-ko,"{""language"": [""ko""], ""license"": ""mit"", ""task_categories"": [""conversational"", ""text-classification"", ""token-classification"", ""table-question-answering"", ""question-answering"", ""zero-shot-classification"", ""summarization"", ""feature-extraction"", ""text-generation"", ""text2text-generation""], ""pretty_name"": ""OpenOrca"", ""size_categories"": [""10M

🐋 The OpenOrca Dataset! 🐋

+ +![OpenOrca Logo](https://huggingface.co/datasets/Open-Orca/OpenOrca/resolve/main/OpenOrcaLogo.png ""OpenOrca Logo"") + + + +We are thrilled to announce the release of the OpenOrca dataset! +This rich collection of augmented FLAN data aligns, as best as possible, with the distributions outlined in the [Orca paper](https://arxiv.org/abs/2306.02707). +It has been instrumental in generating high-performing model checkpoints and serves as a valuable resource for all NLP researchers and developers! + +# Official Models + +## Mistral-7B-OpenOrca + +Our [latest model](https://huggingface.co/spaces/Open-Orca/Mistral-7B-OpenOrca), the first 7B to score better overall than all previous models below 30B. +98% of Llama2-70b-chat's performance, in a completely open 7B! + +## OpenOrca-Platypus2-13B + +Our [third model](https://huggingface.co/Open-Orca/OpenOrca-Platypus2-13B), the first 13B model to score higher than LLaMA1-65B on the HuggingFace Leaderboard! +Released in partnership with Platypus. + +## LlongOrca 7B & 13B + +* Our [first 7B release](https://huggingface.co/Open-Orca/LlongOrca-7B-16k), trained on top of LLongMA2 to achieve 16,000 tokens context. #1 long context 7B model at release time, with >99% of the overall #1 model's performance. +* [LlongOrca-13B-16k](https://huggingface.co/Open-Orca/LlongOrca-13B-16k), trained on top of LLongMA2. #1 long context 13B model at release time, with >97% of the overall #1 model's performance. + +## OpenOrcaxOpenChat-Preview2-13B + +Our [second model](https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-13B), highlighting that we've surpassed the performance reported in the Orca paper. +Was #1 at release time, now surpassed by our own OpenOrca-Platypus2-13B. +Released in partnership with OpenChat. + +## OpenOrca-Preview1-13B + +[OpenOrca-Preview1-13B](https://huggingface.co/Open-Orca/OpenOrca-Preview1-13B) +This model was trained in less than a day, for <$200, with <10% of our data. +At release, it beat the current state of the art models on BigBench-Hard and AGIEval. Achieves ~60% of the improvements reported in the Orca paper. + + + +# Dataset Summary + +The OpenOrca dataset is a collection of augmented [FLAN Collection data](https://arxiv.org/abs/2301.13688). +Currently ~1M GPT-4 completions, and ~3.2M GPT-3.5 completions. +It is tabularized in alignment with the distributions presented in the ORCA paper and currently represents a partial completion of the full intended dataset, with ongoing generation to expand its scope. +The data is primarily used for training and evaluation in the field of natural language processing. + + + +# Dataset Attribution + +We would like to give special recognition to the following contributors for their significant efforts and dedication: + + Teknium + WingLian/Caseus + Eric Hartford + NanoBit + Pankaj + Winddude + Rohan + http://AlignmentLab.ai: + Autometa + Entropi + AtlasUnified + NeverendingToast + NanoBit + WingLian/Caseus +Also of course, as always, TheBloke, for being the backbone of the whole community. + +Many thanks to NanoBit and Caseus, makers of [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl), for lending us their expertise on the platform that developed and trained manticore, minotaur, and many others! + +We are welcoming sponsors or collaborators to help us build these models to the scale they deserve. Please reach out via our socials: +http://Alignmentlab.ai https://discord.gg/n9hXaBPWxx + +Want to visualize our full dataset? Check out our [Nomic Atlas Map](https://atlas.nomic.ai/map/c1b88b47-2d9b-47e0-9002-b80766792582/2560fd25-52fe-42f1-a58f-ff5eccc890d2). + [](https://atlas.nomic.ai/map/c1b88b47-2d9b-47e0-9002-b80766792582/2560fd25-52fe-42f1-a58f-ff5eccc890d2) + + + + +# Supported Tasks and Leaderboards + +This dataset supports a range of tasks including language modeling, text generation, and text augmentation. +It has been instrumental in the generation of multiple high-performing model checkpoints which have exhibited exceptional performance in our unit testing. +Further information on leaderboards will be updated as they become available. + + + +# Languages + +The language of the data is primarily English. + + + +# Dataset Structure + + + +## Data Instances + +A data instance in this dataset represents entries from the FLAN collection which have been augmented by submitting the listed question to either GPT-4 or GPT-3.5. +The response is then entered into the response field. + + + +## Data Fields + +The fields are: +1) 'id', a unique numbered identifier which includes one of 'niv', 't0', 'cot', or 'flan' to represent which source FLAN Collection submix the 'question' is sourced from. +2) 'system_prompt', representing the System Prompt presented to the GPT-3.5 or GPT-4 API for the datapoint +3) 'question', representing a question entry as provided by the FLAN Collection +4) 'response', a response to that question received from a query to either GPT-3.5 or GPT-4. + +## Data Splits +The data is unsplit. + +# Dataset Creation + +## Curation Rationale +The dataset was created to provide a source of augmented text data for researchers and developers. +The datapoints are intended primarily to provide an enhancement of the core FLAN Collection data which relies upon the detailed step by step reasoning capabilities of GPT-3.5 and GPT-4. +This ""reasoning trace"" augmentation has demonstrated exceptional results, allowing a LLaMA-13B model trained with this data to rival or beat GPT-3.5 on broad sets of hard reasoning tasks which all models below 100B parameters had previously performed dramatically worse on. + +## Source Data +The data is generated using techniques in alignment with the distributions outlined in the Orca paper, except as noted below: +1) There is not enough CoT data in the FLAN Collection to generate 150K zero-shot entries, as the paper purports to use. + We suspect this portion was either undocumented or misrepresented. We have used the ~75K points available. +2) We used the pre-generated FLAN Collection datasets hosted on HuggingFace under conceptofmind, e.g. [conceptofmind/flan2021](https://huggingface.co/datasets/conceptofmind/flan2021_submix_original). + These are referenced by the [official FLAN Collection repo](https://github.com/google-research/FLAN/tree/main/flan/v2) as the preferred data source. + However, these are a subset of the full FLAN Collection data, and have less than the required entries for the flan2021 and t0 submixes, by ~1.25M and 200k respectively. +Combined, this gave us ~1.5M fewer datapoints than in the original Orca paper. Completing the set is an ongoing work. + +# Dataset Use + +## Use Cases +The dataset can be used for tasks related to language understanding, natural language processing, machine learning model training, and model performance evaluation. + +## Usage Caveats +Given that this is a work-in-progress dataset, it is recommended to regularly check for updates and improvements. +Further, the data should be used in accordance with the guidelines and recommendations outlined in the Orca paper. + +## Getting Started +This dataset is organized such that it can be naively loaded via Hugging Face datasets library. +We recommend using streaming due to the large size of the files. +Regular updates and data generation progress can be monitored through the OpenOrca repository on Hugging Face. +# Citation +```bibtex +@misc{OpenOrca, + title = {OpenOrca: An Open Dataset of GPT Augmented FLAN Reasoning Traces}, + author = {Wing Lian and Bleys Goodson and Eugene Pentland and Austin Cook and Chanvichet Vong and ""Teknium""}, + year = {2023}, + publisher = {HuggingFace}, + journal = {HuggingFace repository}, + howpublished = {\url{https://https://huggingface.co/Open-Orca/OpenOrca}}, +} +``` +```bibtex +@misc{mukherjee2023orca, + title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4}, + author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah}, + year={2023}, + eprint={2306.02707}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +``` +```bibtex +@misc{longpre2023flan, + title={The Flan Collection: Designing Data and Methods for Effective Instruction Tuning}, + author={Shayne Longpre and Le Hou and Tu Vu and Albert Webson and Hyung Won Chung and Yi Tay and Denny Zhou and Quoc V. Le and Barret Zoph and Jason Wei and Adam Roberts}, + year={2023}, + eprint={2301.13688}, + archivePrefix={arXiv}, + primaryClass={cs.AI} +} +``` +```bibtex +@misc{touvron2023llama, + title={Llama 2: Open Foundation and Fine-Tuned Chat Models}, + author={Hugo Touvron and Louis Martin and Kevin Stone and Peter Albert and Amjad Almahairi and Yasmine Babaei and Nikolay Bashlykov and Soumya Batra and Prajjwal Bhargava and Shruti Bhosale and Dan Bikel and Lukas Blecher and Cristian Canton Ferrer and Moya Chen and Guillem Cucurull and David Esiobu and Jude Fernandes and Jeremy Fu and Wenyin Fu and Brian Fuller and Cynthia Gao and Vedanuj Goswami and Naman Goyal and Anthony Hartshorn and Saghar Hosseini and Rui Hou and Hakan Inan and Marcin Kardas and Viktor Kerkez and Madian Khabsa and Isabel Kloumann and Artem Korenev and Punit Singh Koura and Marie-Anne Lachaux and Thibaut Lavril and Jenya Lee and Diana Liskovich and Yinghai Lu and Yuning Mao and Xavier Martinet and Todor Mihaylov and Pushkar Mishra and Igor Molybog and Yixin Nie and Andrew Poulton and Jeremy Reizenstein and Rashi Rungta and Kalyan Saladi and Alan Schelten and Ruan Silva and Eric Michael Smith and Ranjan Subramanian and Xiaoqing Ellen Tan and Binh Tang and Ross Taylor and Adina Williams and Jian Xiang Kuan and Puxin Xu and Zheng Yan and Iliyan Zarov and Yuchen Zhang and Angela Fan and Melanie Kambadur and Sharan Narang and Aurelien Rodriguez and Robert Stojnic and Sergey Edunov and Thomas Scialom}, + year={2023}, + eprint= arXiv 2307.09288 +} +@software{touvron2023llama, + title={LLaMA: Open and Efficient Foundation Language Models}, + author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and Rodriguez, Aurelien and Joulin, Armand and Grave, Edouard and Lample, Guillaume}, + journal={arXiv preprint arXiv:2302.13971}, + year={2023} +} +```" +devngho/culturax-mini-nonshuffled,"{""dataset_info"": [{""config_name"": ""af"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 47914226, ""num_examples"": 8265}], ""download_size"": 29299096, ""dataset_size"": 47914226}, {""config_name"": ""als"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 48403, ""num_examples"": 69}], ""download_size"": 37780, ""dataset_size"": 48403}, {""config_name"": ""am"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 21830519, ""num_examples"": 2433}], ""download_size"": 10734167, ""dataset_size"": 21830519}, {""config_name"": ""an"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 16821, ""num_examples"": 27}], ""download_size"": 8251, ""dataset_size"": 16821}, {""config_name"": ""ar"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 4151742409, ""num_examples"": 740280}], ""download_size"": 2037845118, ""dataset_size"": 4151742409}, {""config_name"": ""arz"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 553243, ""num_examples"": 716}], ""download_size"": 242572, ""dataset_size"": 553243}, {""config_name"": ""as"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 5152044, ""num_examples"": 526}], ""download_size"": 1989351, ""dataset_size"": 5152044}, {""config_name"": ""ast"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 35333, ""num_examples"": 90}], ""download_size"": 12091, ""dataset_size"": 35333}, {""config_name"": ""av"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 5927, ""num_examples"": 4}], ""download_size"": 13686, ""dataset_size"": 5927}, {""config_name"": ""az"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 178968096, ""num_examples"": 50845}], ""download_size"": 102873990, ""dataset_size"": 178968096}, {""config_name"": ""azb"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 289670, ""num_examples"": 298}], ""download_size"": 102227, ""dataset_size"": 289670}, {""config_name"": ""ba"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 3869656, ""num_examples"": 720}], ""download_size"": 1866021, ""dataset_size"": 3869656}, {""config_name"": ""be"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 118923540, ""num_examples"": 16435}], ""download_size"": 60378152, ""dataset_size"": 118923540}, {""config_name"": ""bg"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1568660631, ""num_examples"": 241318}], ""download_size"": 762579995, ""dataset_size"": 1568660631}, {""config_name"": ""bh"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1328, ""num_examples"": 3}], ""download_size"": 4781, ""dataset_size"": 1328}, {""config_name"": ""bn"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 822984361, ""num_examples"": 124366}], ""download_size"": 308588716, ""dataset_size"": 822984361}, {""config_name"": ""bo"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 9132545, ""num_examples"": 542}], ""download_size"": 2605240, ""dataset_size"": 9132545}, {""config_name"": ""bpy"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 245749, ""num_examples"": 51}], ""download_size"": 78424, ""dataset_size"": 245749}, {""config_name"": ""br"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 641444, ""num_examples"": 438}], ""download_size"": 366282, ""dataset_size"": 641444}, {""config_name"": ""bs"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 4982, ""num_examples"": 12}], ""download_size"": 10971, ""dataset_size"": 4982}, {""config_name"": ""bxr"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 340, ""num_examples"": 1}], ""download_size"": 4080, ""dataset_size"": 340}, {""config_name"": ""ca"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 537336240, ""num_examples"": 155318}], ""download_size"": 334120761, ""dataset_size"": 537336240}, {""config_name"": ""ce"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 158946, ""num_examples"": 173}], ""download_size"": 64453, ""dataset_size"": 158946}, {""config_name"": ""ceb"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 7978160, ""num_examples"": 2639}], ""download_size"": 4018429, ""dataset_size"": 7978160}, {""config_name"": ""ckb"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 14520157, ""num_examples"": 1720}], ""download_size"": 6663902, ""dataset_size"": 14520157}, {""config_name"": ""cs"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 2250377897, ""num_examples"": 653506}], ""download_size"": 1493825235, ""dataset_size"": 2250377897}, {""config_name"": ""cv"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1267176, ""num_examples"": 226}], ""download_size"": 624139, ""dataset_size"": 1267176}, {""config_name"": ""cy"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 21180962, ""num_examples"": 5500}], ""download_size"": 13063947, ""dataset_size"": 21180962}, {""config_name"": ""da"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 966271184, ""num_examples"": 254298}], ""download_size"": 582888859, ""dataset_size"": 966271184}, {""config_name"": ""de"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 15649594701, ""num_examples"": 4200175}], ""download_size"": 9734776977, ""dataset_size"": 15649594701}, {""config_name"": ""dsb"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 303, ""num_examples"": 1}], ""download_size"": 3858, ""dataset_size"": 303}, {""config_name"": ""dv"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 3735234, ""num_examples"": 667}], ""download_size"": 1492894, ""dataset_size"": 3735234}, {""config_name"": ""el"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 2712448803, ""num_examples"": 514302}], ""download_size"": 1345073560, ""dataset_size"": 2712448803}, {""config_name"": ""eml"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 401, ""num_examples"": 1}], ""download_size"": 4541, ""dataset_size"": 401}, {""config_name"": ""en"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 118589793215, ""num_examples"": 32410657}], ""download_size"": 73211369011, ""dataset_size"": 118589793215}, {""config_name"": ""eo"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 35738000, ""num_examples"": 4601}], ""download_size"": 21992261, ""dataset_size"": 35738000}, {""config_name"": ""es"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 16463142543, ""num_examples"": 4509376}], ""download_size"": 10151881762, ""dataset_size"": 16463142543}, {""config_name"": ""et"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 380391945, ""num_examples"": 80048}], ""download_size"": 243102579, ""dataset_size"": 380391945}, {""config_name"": ""eu"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 58524898, ""num_examples"": 15988}], ""download_size"": 35529943, ""dataset_size"": 58524898}, {""config_name"": ""fa"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 3143144959, ""num_examples"": 595311}], ""download_size"": 1463543689, ""dataset_size"": 3143144959}, {""config_name"": ""fi"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1214683096, ""num_examples"": 304677}], ""download_size"": 769607927, ""dataset_size"": 1214683096}, {""config_name"": ""fr"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 13071329986, ""num_examples"": 3637543}], ""download_size"": 7968623946, ""dataset_size"": 13071329986}, {""config_name"": ""fy"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 6154765, ""num_examples"": 2233}], ""download_size"": 3810893, ""dataset_size"": 6154765}, {""config_name"": ""ga"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 15239433, ""num_examples"": 3043}], ""download_size"": 8910658, ""dataset_size"": 15239433}, {""config_name"": ""gd"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 272932, ""num_examples"": 84}], ""download_size"": 165365, ""dataset_size"": 272932}, {""config_name"": ""gl"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 67394305, ""num_examples"": 17860}], ""download_size"": 41760462, ""dataset_size"": 67394305}, {""config_name"": ""gn"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 293, ""num_examples"": 1}], ""download_size"": 3758, ""dataset_size"": 293}, {""config_name"": ""gom"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 79389, ""num_examples"": 7}], ""download_size"": 31671, ""dataset_size"": 79389}, {""config_name"": ""gu"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 86897373, ""num_examples"": 11629}], ""download_size"": 33664792, ""dataset_size"": 86897373}, {""config_name"": ""he"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 425728060, ""num_examples"": 46540}], ""download_size"": 215527218, ""dataset_size"": 425728060}, {""config_name"": ""hi"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1476484284, ""num_examples"": 196654}], ""download_size"": 565966884, ""dataset_size"": 1476484284}, {""config_name"": ""hr"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1657545, ""num_examples"": 4607}], ""download_size"": 1061804, ""dataset_size"": 1657545}, {""config_name"": ""hsb"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 27010, ""num_examples"": 42}], ""download_size"": 18470, ""dataset_size"": 27010}, {""config_name"": ""hu"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1819937397, ""num_examples"": 441322}], ""download_size"": 1160423578, ""dataset_size"": 1819937397}, {""config_name"": ""hy"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 159683892, ""num_examples"": 29645}], ""download_size"": 74782480, ""dataset_size"": 159683892}, {""config_name"": ""ia"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 6598, ""num_examples"": 6}], ""download_size"": 5808, ""dataset_size"": 6598}, {""config_name"": ""id"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 629329515, ""num_examples"": 232514}], ""download_size"": 352896945, ""dataset_size"": 629329515}, {""config_name"": ""ilo"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 5183, ""num_examples"": 23}], ""download_size"": 5038, ""dataset_size"": 5183}, {""config_name"": ""io"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 2637, ""num_examples"": 11}], ""download_size"": 4792, ""dataset_size"": 2637}, {""config_name"": ""is"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 104256268, ""num_examples"": 23736}], ""download_size"": 63804435, ""dataset_size"": 104256268}, {""config_name"": ""it"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 7149380555, ""num_examples"": 2113099}], ""download_size"": 4514678157, ""dataset_size"": 7149380555}, {""config_name"": ""ja"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 5175409022, ""num_examples"": 1111885}], ""download_size"": 2918380663, ""dataset_size"": 5175409022}, {""config_name"": ""jbo"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 22447, ""num_examples"": 13}], ""download_size"": 26662, ""dataset_size"": 22447}, {""config_name"": ""jv"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 248112, ""num_examples"": 21}], ""download_size"": 143652, ""dataset_size"": 248112}, {""config_name"": ""ka"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 260720432, ""num_examples"": 31203}], ""download_size"": 94582642, ""dataset_size"": 260720432}, {""config_name"": ""kk"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 205739783, ""num_examples"": 27340}], ""download_size"": 96662550, ""dataset_size"": 205739783}, {""config_name"": ""km"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 69303374, ""num_examples"": 10132}], ""download_size"": 25063681, ""dataset_size"": 69303374}, {""config_name"": ""kn"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 109114779, ""num_examples"": 13521}], ""download_size"": 41841503, ""dataset_size"": 109114779}, {""config_name"": ""ko"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1080491739, ""num_examples"": 205573}], ""download_size"": 640352203, ""dataset_size"": 1080491739}, {""config_name"": ""krc"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 5213, ""num_examples"": 17}], ""download_size"": 4418, ""dataset_size"": 5213}, {""config_name"": ""ku"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 12150347, ""num_examples"": 2953}], ""download_size"": 7283637, ""dataset_size"": 12150347}, {""config_name"": ""kv"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 4479, ""num_examples"": 14}], ""download_size"": 5159, ""dataset_size"": 4479}, {""config_name"": ""kw"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 201, ""num_examples"": 1}], ""download_size"": 3138, ""dataset_size"": 201}, {""config_name"": ""ky"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 37686163, ""num_examples"": 5709}], ""download_size"": 18097022, ""dataset_size"": 37686163}, {""config_name"": ""la"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 4471637, ""num_examples"": 490}], ""download_size"": 2569958, ""dataset_size"": 4471637}, {""config_name"": ""lb"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 6975194, ""num_examples"": 1659}], ""download_size"": 4287815, ""dataset_size"": 6975194}, {""config_name"": ""lez"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 11712, ""num_examples"": 18}], ""download_size"": 7371, ""dataset_size"": 11712}, {""config_name"": ""li"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 478, ""num_examples"": 2}], ""download_size"": 3584, ""dataset_size"": 478}, {""config_name"": ""lmo"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 15093, ""num_examples"": 35}], ""download_size"": 10219, ""dataset_size"": 15093}, {""config_name"": ""lo"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 16677427, ""num_examples"": 2178}], ""download_size"": 6323357, ""dataset_size"": 16677427}, {""config_name"": ""lt"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 594627488, ""num_examples"": 133398}], ""download_size"": 375349095, ""dataset_size"": 594627488}, {""config_name"": ""lv"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 333697262, ""num_examples"": 71366}], ""download_size"": 206347782, ""dataset_size"": 333697262}, {""config_name"": ""mai"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 459, ""num_examples"": 1}], ""download_size"": 4860, ""dataset_size"": 459}, {""config_name"": ""mg"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 5497530, ""num_examples"": 1159}], ""download_size"": 3005490, ""dataset_size"": 5497530}, {""config_name"": ""mhr"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 438800, ""num_examples"": 79}], ""download_size"": 212268, ""dataset_size"": 438800}, {""config_name"": ""min"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 40467, ""num_examples"": 14}], ""download_size"": 22942, ""dataset_size"": 40467}, {""config_name"": ""mk"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 149674631, ""num_examples"": 27628}], ""download_size"": 70500031, ""dataset_size"": 149674631}, {""config_name"": ""ml"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 213710028, ""num_examples"": 26931}], ""download_size"": 78315697, ""dataset_size"": 213710028}, {""config_name"": ""mn"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 118599039, ""num_examples"": 19288}], ""download_size"": 56664207, ""dataset_size"": 118599039}, {""config_name"": ""mr"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 183531742, ""num_examples"": 22666}], ""download_size"": 69818044, ""dataset_size"": 183531742}, {""config_name"": ""mrj"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 15670, ""num_examples"": 11}], ""download_size"": 12574, ""dataset_size"": 15670}, {""config_name"": ""ms"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 3568236, ""num_examples"": 2382}], ""download_size"": 1955952, ""dataset_size"": 3568236}, {""config_name"": ""mt"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 8906317, ""num_examples"": 1513}], ""download_size"": 4931205, ""dataset_size"": 8906317}, {""config_name"": ""my"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 79209425, ""num_examples"": 8656}], ""download_size"": 27359509, ""dataset_size"": 79209425}, {""config_name"": ""mzn"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 8611, ""num_examples"": 19}], ""download_size"": 7329, ""dataset_size"": 8611}, {""config_name"": ""nah"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 208, ""num_examples"": 1}], ""download_size"": 3179, ""dataset_size"": 208}, {""config_name"": ""nds"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 536401, ""num_examples"": 151}], ""download_size"": 328368, ""dataset_size"": 536401}, {""config_name"": ""ne"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 218530089, ""num_examples"": 31240}], ""download_size"": 81244964, ""dataset_size"": 218530089}, {""config_name"": ""new"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 146180, ""num_examples"": 43}], ""download_size"": 68225, ""dataset_size"": 146180}, {""config_name"": ""nl"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 3423958390, ""num_examples"": 1173927}], ""download_size"": 2104260605, ""dataset_size"": 3423958390}, {""config_name"": ""nn"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 573924, ""num_examples"": 1261}], ""download_size"": 376802, ""dataset_size"": 573924}, {""config_name"": ""no"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 886293156, ""num_examples"": 189073}], ""download_size"": 544754812, ""dataset_size"": 886293156}, {""config_name"": ""oc"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 56775, ""num_examples"": 106}], ""download_size"": 37657, ""dataset_size"": 56775}, {""config_name"": ""or"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 10376851, ""num_examples"": 1535}], ""download_size"": 4026133, ""dataset_size"": 10376851}, {""config_name"": ""os"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 969628, ""num_examples"": 86}], ""download_size"": 366851, ""dataset_size"": 969628}, {""config_name"": ""pa"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 53247320, ""num_examples"": 6470}], ""download_size"": 20258193, ""dataset_size"": 53247320}, {""config_name"": ""pl"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 4797322841, ""num_examples"": 1421672}], ""download_size"": 3144888097, ""dataset_size"": 4797322841}, {""config_name"": ""pms"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 193689, ""num_examples"": 76}], ""download_size"": 99115, ""dataset_size"": 193689}, {""config_name"": ""pnb"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 2324564, ""num_examples"": 156}], ""download_size"": 1081639, ""dataset_size"": 2324564}, {""config_name"": ""ps"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 21838581, ""num_examples"": 3769}], ""download_size"": 10449929, ""dataset_size"": 21838581}, {""config_name"": ""pt"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 6030569925, ""num_examples"": 1902897}], ""download_size"": 3753416975, ""dataset_size"": 6030569925}, {""config_name"": ""qu"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 3248, ""num_examples"": 12}], ""download_size"": 4834, ""dataset_size"": 3248}, {""config_name"": ""ro"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1647222938, ""num_examples"": 403254}], ""download_size"": 1029473728, ""dataset_size"": 1647222938}, {""config_name"": ""ru"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 51932917568, ""num_examples"": 7993109}], ""download_size"": 25902408245, ""dataset_size"": 51932917568}, {""config_name"": ""sa"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 353271, ""num_examples"": 163}], ""download_size"": 109390, ""dataset_size"": 353271}, {""config_name"": ""sah"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1626716, ""num_examples"": 221}], ""download_size"": 751737, ""dataset_size"": 1626716}, {""config_name"": ""sd"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 8935394, ""num_examples"": 1092}], ""download_size"": 4342313, ""dataset_size"": 8935394}, {""config_name"": ""sh"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 119845, ""num_examples"": 456}], ""download_size"": 28082, ""dataset_size"": 119845}, {""config_name"": ""si"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 79363360, ""num_examples"": 7537}], ""download_size"": 31632414, ""dataset_size"": 79363360}, {""config_name"": ""sk"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 656920389, ""num_examples"": 185825}], ""download_size"": 435390243, ""dataset_size"": 656920389}, {""config_name"": ""sl"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 345866750, ""num_examples"": 73354}], ""download_size"": 222614687, ""dataset_size"": 345866750}, {""config_name"": ""sq"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 150747645, ""num_examples"": 52056}], ""download_size"": 90031594, ""dataset_size"": 150747645}, {""config_name"": ""sr"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 330933007, ""num_examples"": 40532}], ""download_size"": 164474120, ""dataset_size"": 330933007}, {""config_name"": ""su"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 71933, ""num_examples"": 16}], ""download_size"": 50712, ""dataset_size"": 71933}, {""config_name"": ""sv"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1658749441, ""num_examples"": 497092}], ""download_size"": 1026016237, ""dataset_size"": 1658749441}, {""config_name"": ""sw"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 2120663, ""num_examples"": 665}], ""download_size"": 1172807, ""dataset_size"": 2120663}, {""config_name"": ""ta"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 433993378, ""num_examples"": 47285}], ""download_size"": 153834177, ""dataset_size"": 433993378}, {""config_name"": ""te"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 142492032, ""num_examples"": 18229}], ""download_size"": 55247684, ""dataset_size"": 142492032}, {""config_name"": ""tg"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 36581062, ""num_examples"": 4838}], ""download_size"": 17091868, ""dataset_size"": 36581062}, {""config_name"": ""th"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1565290526, ""num_examples"": 209606}], ""download_size"": 608699456, ""dataset_size"": 1565290526}, {""config_name"": ""tk"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 143460, ""num_examples"": 144}], ""download_size"": 82943, ""dataset_size"": 143460}, {""config_name"": ""tl"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 22766411, ""num_examples"": 3485}], ""download_size"": 12970450, ""dataset_size"": 22766411}, {""config_name"": ""tr"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 2979296527, ""num_examples"": 942075}], ""download_size"": 1803862992, ""dataset_size"": 2979296527}, {""config_name"": ""tt"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 15703273, ""num_examples"": 2181}], ""download_size"": 7741613, ""dataset_size"": 15703273}, {""config_name"": ""ug"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 5337670, ""num_examples"": 470}], ""download_size"": 2355545, ""dataset_size"": 5337670}, {""config_name"": ""uk"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 2613621381, ""num_examples"": 447405}], ""download_size"": 1303094462, ""dataset_size"": 2613621381}, {""config_name"": ""ur"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 178978059, ""num_examples"": 27573}], ""download_size"": 85756317, ""dataset_size"": 178978059}, {""config_name"": ""uz"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 3642685, ""num_examples"": 872}], ""download_size"": 2153925, ""dataset_size"": 3642685}, {""config_name"": ""vec"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 266, ""num_examples"": 1}], ""download_size"": 3581, ""dataset_size"": 266}, {""config_name"": ""vi"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 2709971576, ""num_examples"": 576063}], ""download_size"": 1439675245, ""dataset_size"": 2709971576}, {""config_name"": ""vo"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 39947, ""num_examples"": 66}], ""download_size"": 15487, ""dataset_size"": 39947}, {""config_name"": ""wa"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 3609, ""num_examples"": 14}], ""download_size"": 4680, ""dataset_size"": 3609}, {""config_name"": ""war"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 56875, ""num_examples"": 237}], ""download_size"": 27169, ""dataset_size"": 56875}, {""config_name"": ""wuu"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 897, ""num_examples"": 2}], ""download_size"": 4869, ""dataset_size"": 897}, {""config_name"": ""xal"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 532, ""num_examples"": 1}], ""download_size"": 5361, ""dataset_size"": 532}, {""config_name"": ""xmf"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 71001, ""num_examples"": 97}], ""download_size"": 21953, ""dataset_size"": 71001}, {""config_name"": ""yi"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 13129826, ""num_examples"": 1412}], ""download_size"": 5978777, ""dataset_size"": 13129826}, {""config_name"": ""yo"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 844, ""num_examples"": 2}], ""download_size"": 4927, ""dataset_size"": 844}, {""config_name"": ""zh"", ""features"": [{""name"": ""text"", ""dtype"": ""string""}, {""name"": ""timestamp"", ""dtype"": ""string""}, {""name"": ""url"", ""dtype"": ""string""}, {""name"": ""source"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 9206626122, ""num_examples"": 2186246}], ""download_size"": 6424105929, ""dataset_size"": 9206626122}], ""configs"": [{""config_name"": ""af"", ""data_files"": [{""split"": ""train"", ""path"": ""af/train-*""}]}, {""config_name"": ""als"", ""data_files"": [{""split"": ""train"", ""path"": ""als/train-*""}]}, {""config_name"": ""am"", ""data_files"": [{""split"": ""train"", ""path"": ""am/train-*""}]}, {""config_name"": ""an"", ""data_files"": [{""split"": ""train"", ""path"": ""an/train-*""}]}, {""config_name"": ""ar"", ""data_files"": [{""split"": ""train"", ""path"": ""ar/train-*""}]}, {""config_name"": ""arz"", ""data_files"": [{""split"": ""train"", ""path"": ""arz/train-*""}]}, {""config_name"": ""as"", ""data_files"": [{""split"": ""train"", ""path"": ""as/train-*""}]}, {""config_name"": ""ast"", ""data_files"": [{""split"": ""train"", ""path"": ""ast/train-*""}]}, {""config_name"": ""av"", ""data_files"": [{""split"": ""train"", ""path"": ""av/train-*""}]}, {""config_name"": ""az"", ""data_files"": [{""split"": ""train"", ""path"": ""az/train-*""}]}, {""config_name"": ""azb"", ""data_files"": [{""split"": ""train"", ""path"": ""azb/train-*""}]}, {""config_name"": ""ba"", ""data_files"": [{""split"": ""train"", ""path"": ""ba/train-*""}]}, {""config_name"": ""be"", ""data_files"": [{""split"": ""train"", ""path"": ""be/train-*""}]}, {""config_name"": ""bg"", ""data_files"": [{""split"": ""train"", ""path"": ""bg/train-*""}]}, {""config_name"": ""bh"", ""data_files"": [{""split"": ""train"", ""path"": ""bh/train-*""}]}, {""config_name"": ""bn"", ""data_files"": [{""split"": ""train"", ""path"": ""bn/train-*""}]}, {""config_name"": ""bo"", ""data_files"": [{""split"": ""train"", ""path"": ""bo/train-*""}]}, {""config_name"": ""bpy"", ""data_files"": [{""split"": ""train"", ""path"": ""bpy/train-*""}]}, {""config_name"": ""br"", ""data_files"": [{""split"": ""train"", ""path"": ""br/train-*""}]}, {""config_name"": ""bs"", ""data_files"": [{""split"": ""train"", ""path"": ""bs/train-*""}]}, {""config_name"": ""bxr"", ""data_files"": [{""split"": ""train"", ""path"": ""bxr/train-*""}]}, {""config_name"": ""ca"", ""data_files"": [{""split"": ""train"", ""path"": ""ca/train-*""}]}, {""config_name"": ""ce"", ""data_files"": [{""split"": ""train"", ""path"": ""ce/train-*""}]}, {""config_name"": ""ceb"", ""data_files"": [{""split"": ""train"", ""path"": ""ceb/train-*""}]}, {""config_name"": ""ckb"", ""data_files"": [{""split"": ""train"", ""path"": ""ckb/train-*""}]}, {""config_name"": ""cs"", ""data_files"": [{""split"": ""train"", ""path"": ""cs/train-*""}]}, {""config_name"": ""cv"", ""data_files"": [{""split"": ""train"", ""path"": ""cv/train-*""}]}, {""config_name"": ""cy"", ""data_files"": [{""split"": ""train"", ""path"": ""cy/train-*""}]}, {""config_name"": ""da"", ""data_files"": [{""split"": ""train"", ""path"": ""da/train-*""}]}, {""config_name"": ""de"", ""data_files"": [{""split"": ""train"", ""path"": ""de/train-*""}]}, {""config_name"": ""dsb"", ""data_files"": [{""split"": ""train"", ""path"": ""dsb/train-*""}]}, {""config_name"": ""dv"", ""data_files"": [{""split"": ""train"", ""path"": ""dv/train-*""}]}, {""config_name"": ""el"", ""data_files"": [{""split"": ""train"", ""path"": ""el/train-*""}]}, {""config_name"": ""eml"", ""data_files"": [{""split"": ""train"", ""path"": ""eml/train-*""}]}, {""config_name"": ""en"", ""data_files"": [{""split"": ""train"", ""path"": ""en/train-*""}]}, {""config_name"": ""eo"", ""data_files"": [{""split"": ""train"", ""path"": ""eo/train-*""}]}, {""config_name"": ""es"", ""data_files"": [{""split"": ""train"", ""path"": ""es/train-*""}]}, {""config_name"": ""et"", ""data_files"": [{""split"": ""train"", ""path"": ""et/train-*""}]}, {""config_name"": ""eu"", ""data_files"": [{""split"": ""train"", ""path"": ""eu/train-*""}]}, {""config_name"": ""fa"", ""data_files"": [{""split"": ""train"", ""path"": ""fa/train-*""}]}, {""config_name"": ""fi"", ""data_files"": [{""split"": ""train"", ""path"": ""fi/train-*""}]}, {""config_name"": ""fr"", ""data_files"": [{""split"": ""train"", ""path"": ""fr/train-*""}]}, {""config_name"": ""fy"", ""data_files"": [{""split"": ""train"", ""path"": ""fy/train-*""}]}, {""config_name"": ""ga"", ""data_files"": [{""split"": ""train"", ""path"": ""ga/train-*""}]}, {""config_name"": ""gd"", ""data_files"": [{""split"": ""train"", ""path"": ""gd/train-*""}]}, {""config_name"": ""gl"", ""data_files"": [{""split"": ""train"", ""path"": ""gl/train-*""}]}, {""config_name"": ""gn"", ""data_files"": [{""split"": ""train"", ""path"": ""gn/train-*""}]}, {""config_name"": ""gom"", ""data_files"": [{""split"": ""train"", ""path"": ""gom/train-*""}]}, {""config_name"": ""gu"", ""data_files"": [{""split"": ""train"", ""path"": ""gu/train-*""}]}, {""config_name"": ""he"", ""data_files"": [{""split"": ""train"", ""path"": ""he/train-*""}]}, {""config_name"": ""hi"", ""data_files"": [{""split"": ""train"", ""path"": ""hi/train-*""}]}, {""config_name"": ""hr"", ""data_files"": [{""split"": ""train"", ""path"": ""hr/train-*""}]}, {""config_name"": ""hsb"", ""data_files"": [{""split"": ""train"", ""path"": ""hsb/train-*""}]}, {""config_name"": ""hu"", ""data_files"": [{""split"": ""train"", ""path"": ""hu/train-*""}]}, {""config_name"": ""hy"", ""data_files"": [{""split"": ""train"", ""path"": ""hy/train-*""}]}, {""config_name"": ""ia"", ""data_files"": [{""split"": ""train"", ""path"": ""ia/train-*""}]}, {""config_name"": ""id"", ""data_files"": [{""split"": ""train"", ""path"": ""id/train-*""}]}, {""config_name"": ""ilo"", ""data_files"": [{""split"": ""train"", ""path"": ""ilo/train-*""}]}, {""config_name"": ""io"", ""data_files"": [{""split"": ""train"", ""path"": ""io/train-*""}]}, {""config_name"": ""is"", ""data_files"": [{""split"": ""train"", ""path"": ""is/train-*""}]}, {""config_name"": ""it"", ""data_files"": [{""split"": ""train"", ""path"": ""it/train-*""}]}, {""config_name"": ""ja"", ""data_files"": [{""split"": ""train"", ""path"": ""ja/train-*""}]}, {""config_name"": ""jbo"", ""data_files"": [{""split"": ""train"", ""path"": ""jbo/train-*""}]}, {""config_name"": ""jv"", ""data_files"": [{""split"": ""train"", ""path"": ""jv/train-*""}]}, {""config_name"": ""ka"", ""data_files"": [{""split"": ""train"", ""path"": ""ka/train-*""}]}, {""config_name"": ""kk"", ""data_files"": [{""split"": ""train"", ""path"": ""kk/train-*""}]}, {""config_name"": ""km"", ""data_files"": [{""split"": ""train"", ""path"": ""km/train-*""}]}, {""config_name"": ""kn"", ""data_files"": [{""split"": ""train"", ""path"": ""kn/train-*""}]}, {""config_name"": ""ko"", ""data_files"": [{""split"": ""train"", ""path"": ""ko/train-*""}]}, {""config_name"": ""krc"", ""data_files"": [{""split"": ""train"", ""path"": ""krc/train-*""}]}, {""config_name"": ""ku"", ""data_files"": [{""split"": ""train"", ""path"": ""ku/train-*""}]}, {""config_name"": ""kv"", ""data_files"": [{""split"": ""train"", ""path"": ""kv/train-*""}]}, {""config_name"": ""kw"", ""data_files"": [{""split"": ""train"", ""path"": ""kw/train-*""}]}, {""config_name"": ""ky"", ""data_files"": [{""split"": ""train"", ""path"": ""ky/train-*""}]}, {""config_name"": ""la"", ""data_files"": [{""split"": ""train"", ""path"": ""la/train-*""}]}, {""config_name"": ""lb"", ""data_files"": [{""split"": ""train"", ""path"": ""lb/train-*""}]}, {""config_name"": ""lez"", ""data_files"": [{""split"": ""train"", ""path"": ""lez/train-*""}]}, {""config_name"": ""li"", ""data_files"": [{""split"": ""train"", ""path"": ""li/train-*""}]}, {""config_name"": ""lmo"", ""data_files"": [{""split"": ""train"", ""path"": ""lmo/train-*""}]}, {""config_name"": ""lo"", ""data_files"": [{""split"": ""train"", ""path"": ""lo/train-*""}]}, {""config_name"": ""lt"", ""data_files"": [{""split"": ""train"", ""path"": ""lt/train-*""}]}, {""config_name"": ""lv"", ""data_files"": [{""split"": ""train"", ""path"": ""lv/train-*""}]}, {""config_name"": ""mai"", ""data_files"": [{""split"": ""train"", ""path"": ""mai/train-*""}]}, {""config_name"": ""mg"", ""data_files"": [{""split"": ""train"", ""path"": ""mg/train-*""}]}, {""config_name"": ""mhr"", ""data_files"": [{""split"": ""train"", ""path"": ""mhr/train-*""}]}, {""config_name"": ""min"", ""data_files"": [{""split"": ""train"", ""path"": ""min/train-*""}]}, {""config_name"": ""mk"", ""data_files"": [{""split"": ""train"", ""path"": ""mk/train-*""}]}, {""config_name"": ""ml"", ""data_files"": [{""split"": ""train"", ""path"": ""ml/train-*""}]}, {""config_name"": ""mn"", ""data_files"": [{""split"": ""train"", ""path"": ""mn/train-*""}]}, {""config_name"": ""mr"", ""data_files"": [{""split"": ""train"", ""path"": ""mr/train-*""}]}, {""config_name"": ""mrj"", ""data_files"": [{""split"": ""train"", ""path"": ""mrj/train-*""}]}, {""config_name"": ""ms"", ""data_files"": [{""split"": ""train"", ""path"": ""ms/train-*""}]}, {""config_name"": ""mt"", ""data_files"": [{""split"": ""train"", ""path"": ""mt/train-*""}]}, {""config_name"": ""my"", ""data_files"": [{""split"": ""train"", ""path"": ""my/train-*""}]}, {""config_name"": ""mzn"", ""data_files"": [{""split"": ""train"", ""path"": ""mzn/train-*""}]}, {""config_name"": ""nah"", ""data_files"": [{""split"": ""train"", ""path"": ""nah/train-*""}]}, {""config_name"": ""nds"", ""data_files"": [{""split"": ""train"", ""path"": ""nds/train-*""}]}, {""config_name"": ""ne"", ""data_files"": [{""split"": ""train"", ""path"": ""ne/train-*""}]}, {""config_name"": ""new"", ""data_files"": [{""split"": ""train"", ""path"": ""new/train-*""}]}, {""config_name"": ""nl"", ""data_files"": [{""split"": ""train"", ""path"": ""nl/train-*""}]}, {""config_name"": ""nn"", ""data_files"": [{""split"": ""train"", ""path"": ""nn/train-*""}]}, {""config_name"": ""no"", ""data_files"": [{""split"": ""train"", ""path"": ""no/train-*""}]}, {""config_name"": ""oc"", ""data_files"": [{""split"": ""train"", ""path"": ""oc/train-*""}]}, {""config_name"": ""or"", ""data_files"": [{""split"": ""train"", ""path"": ""or/train-*""}]}, {""config_name"": ""os"", ""data_files"": [{""split"": ""train"", ""path"": ""os/train-*""}]}, {""config_name"": ""pa"", ""data_files"": [{""split"": ""train"", ""path"": ""pa/train-*""}]}, {""config_name"": ""pl"", ""data_files"": [{""split"": ""train"", ""path"": ""pl/train-*""}]}, {""config_name"": ""pms"", ""data_files"": [{""split"": ""train"", ""path"": ""pms/train-*""}]}, {""config_name"": ""pnb"", ""data_files"": [{""split"": ""train"", ""path"": ""pnb/train-*""}]}, {""config_name"": ""ps"", ""data_files"": [{""split"": ""train"", ""path"": ""ps/train-*""}]}, {""config_name"": ""pt"", ""data_files"": [{""split"": ""train"", ""path"": ""pt/train-*""}]}, {""config_name"": ""qu"", ""data_files"": [{""split"": ""train"", ""path"": ""qu/train-*""}]}, {""config_name"": ""ro"", ""data_files"": [{""split"": ""train"", ""path"": ""ro/train-*""}]}, {""config_name"": ""ru"", ""data_files"": [{""split"": ""train"", ""path"": ""ru/train-*""}]}, {""config_name"": ""sa"", ""data_files"": [{""split"": ""train"", ""path"": ""sa/train-*""}]}, {""config_name"": ""sah"", ""data_files"": [{""split"": ""train"", ""path"": ""sah/train-*""}]}, {""config_name"": ""sd"", ""data_files"": [{""split"": ""train"", ""path"": ""sd/train-*""}]}, {""config_name"": ""sh"", ""data_files"": [{""split"": ""train"", ""path"": ""sh/train-*""}]}, {""config_name"": ""si"", ""data_files"": [{""split"": ""train"", ""path"": ""si/train-*""}]}, {""config_name"": ""sk"", ""data_files"": [{""split"": ""train"", ""path"": ""sk/train-*""}]}, {""config_name"": ""sl"", ""data_files"": [{""split"": ""train"", ""path"": ""sl/train-*""}]}, {""config_name"": ""sq"", ""data_files"": [{""split"": ""train"", ""path"": ""sq/train-*""}]}, {""config_name"": ""sr"", ""data_files"": [{""split"": ""train"", ""path"": ""sr/train-*""}]}, {""config_name"": ""su"", ""data_files"": [{""split"": ""train"", ""path"": ""su/train-*""}]}, {""config_name"": ""sv"", ""data_files"": [{""split"": ""train"", ""path"": ""sv/train-*""}]}, {""config_name"": ""sw"", ""data_files"": [{""split"": ""train"", ""path"": ""sw/train-*""}]}, {""config_name"": ""ta"", ""data_files"": [{""split"": ""train"", ""path"": ""ta/train-*""}]}, {""config_name"": ""te"", ""data_files"": [{""split"": ""train"", ""path"": ""te/train-*""}]}, {""config_name"": ""tg"", ""data_files"": [{""split"": ""train"", ""path"": ""tg/train-*""}]}, {""config_name"": ""th"", ""data_files"": [{""split"": ""train"", ""path"": ""th/train-*""}]}, {""config_name"": ""tk"", ""data_files"": [{""split"": ""train"", ""path"": ""tk/train-*""}]}, {""config_name"": ""tl"", ""data_files"": [{""split"": ""train"", ""path"": ""tl/train-*""}]}, {""config_name"": ""tr"", ""data_files"": [{""split"": ""train"", ""path"": ""tr/train-*""}]}, {""config_name"": ""tt"", ""data_files"": [{""split"": ""train"", ""path"": ""tt/train-*""}]}, {""config_name"": ""ug"", ""data_files"": [{""split"": ""train"", ""path"": ""ug/train-*""}]}, {""config_name"": ""uk"", ""data_files"": [{""split"": ""train"", ""path"": ""uk/train-*""}]}, {""config_name"": ""ur"", ""data_files"": [{""split"": ""train"", ""path"": ""ur/train-*""}]}, {""config_name"": ""uz"", ""data_files"": [{""split"": ""train"", ""path"": ""uz/train-*""}]}, {""config_name"": ""vec"", ""data_files"": [{""split"": ""train"", ""path"": ""vec/train-*""}]}, {""config_name"": ""vi"", ""data_files"": [{""split"": ""train"", ""path"": ""vi/train-*""}]}, {""config_name"": ""vo"", ""data_files"": [{""split"": ""train"", ""path"": ""vo/train-*""}]}, {""config_name"": ""wa"", ""data_files"": [{""split"": ""train"", ""path"": ""wa/train-*""}]}, {""config_name"": ""war"", ""data_files"": [{""split"": ""train"", ""path"": ""war/train-*""}]}, {""config_name"": ""wuu"", ""data_files"": [{""split"": ""train"", ""path"": ""wuu/train-*""}]}, {""config_name"": ""xal"", ""data_files"": [{""split"": ""train"", ""path"": ""xal/train-*""}]}, {""config_name"": ""xmf"", ""data_files"": [{""split"": ""train"", ""path"": ""xmf/train-*""}]}, {""config_name"": ""yi"", ""data_files"": [{""split"": ""train"", ""path"": ""yi/train-*""}]}, {""config_name"": ""yo"", ""data_files"": [{""split"": ""train"", ""path"": ""yo/train-*""}]}, {""config_name"": ""zh"", ""data_files"": [{""split"": ""train"", ""path"": ""zh/train-*""}]}], ""source_datasets"": [""uonlp/CulturaX""], ""task_categories"": [""text-generation"", ""fill-mask""], ""task_ids"": [""language-modeling"", ""masked-language-modeling""], ""multilinguality"": [""multilingual""], ""language"": [""af"", ""als"", ""am"", ""an"", ""ar"", ""arz"", ""as"", ""ast"", ""av"", ""az"", ""azb"", ""ba"", ""be"", ""bg"", ""bh"", ""bn"", ""bo"", ""bpy"", ""br"", ""bs"", ""bxr"", ""ca"", ""ce"", ""ceb"", ""ckb"", ""cs"", ""cv"", ""cy"", ""da"", ""de"", ""dsb"", ""dv"", ""el"", ""eml"", ""en"", ""eo"", ""es"", ""et"", ""eu"", ""fa"", ""fi"", ""fr"", ""fy"", ""ga"", ""gd"", ""gl"", ""gn"", ""gom"", ""gu"", ""he"", ""hi"", ""hr"", ""hsb"", ""hu"", ""hy"", ""ia"", ""id"", ""ilo"", ""io"", ""is"", ""it"", ""ja"", ""jbo"", ""jv"", ""ka"", ""kk"", ""km"", ""kn"", ""ko"", ""krc"", ""ku"", ""kv"", ""kw"", ""ky"", ""la"", ""lb"", ""lez"", ""li"", ""lmo"", ""lo"", ""lt"", ""lv"", ""mai"", ""mg"", ""mhr"", ""min"", ""mk"", ""ml"", ""mn"", ""mr"", ""mrj"", ""ms"", ""mt"", ""my"", ""mzn"", ""nah"", ""nds"", ""ne"", ""new"", ""nl"", ""nn"", false, ""oc"", ""or"", ""os"", ""pa"", ""pl"", ""pms"", ""pnb"", ""ps"", ""pt"", ""qu"", ""ro"", ""ru"", ""sa"", ""sah"", ""sd"", ""sh"", ""si"", ""sk"", ""sl"", ""sq"", ""sr"", ""su"", ""sv"", ""sw"", ""ta"", ""te"", ""tg"", ""th"", ""tk"", ""tl"", ""tr"", ""tt"", ""ug"", ""uk"", ""ur"", ""uz"", ""vec"", ""vi"", ""vo"", ""wa"", ""war"", ""wuu"", ""xal"", ""xmf"", ""yi"", ""yo"", ""zh""]}","This repo contains 1% of each language of uonlp/CulturaX. + +```python +load_dataset('devngho/culturax-mini-nonshuffled', '[lang]', split='train') # read specified language +load_dataset('devngho/culturax-mini-nonshuffled', data_files=""*/*"", split='train') # read all language +```" +jp1924/KsponSpeech,{},"--- +dataset_info: + features: + - name: audio + dtype: + audio: + sampling_rate: 16000 + - name: sentence + dtype: string + - name: id + dtype: string + splits: + - name: dev + num_bytes: 453996265.875 + num_examples: 2545 + - name: eval_clean + num_bytes: 304987608 + num_examples: 3000 + - name: eval_other + num_bytes: 438544274 + num_examples: 3000 + - name: train + num_bytes: 111286133042 + num_examples: 620000 + download_size: 105060754027 + dataset_size: 112483661189.875 +configs: +- config_name: default + data_files: + - split: dev + path: data/dev-* + - split: eval_clean + path: data/eval_clean-* + - split: eval_other + path: data/eval_other-* + - split: train + path: data/train-* +task_categories: +- automatic-speech-recognition +language: +- ko +tags: +- STT +- Audio +size_categories: +- 100B + + + KO + JA + IT + RU + DE + FR + TH + AR + VI + Total + + + Train Images + 580 + 1039 + 622 + 635 + 984 + 792 + 319 + 568 + 1139 + 6678 + + + Test Images + 250 + 250 + 250 + 250 + 250 + 250 + 116 + 250 + 250 + 2116 + + + Train QA + 1280 + 3332 + 2168 + 1835 + 4238 + 2743 + 625 + 1597 + 4011 + 21829 + + + Test QA + 558 + 828 + 884 + 756 + 1048 + 886 + 231 + 703 + 884 + 6778 + + + +## - LeaderBoard + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
ModelsARDEFRITJAKORUTHVIAverage
GPT-4O20.2 34.2 41.2 32.7 20.0 33.9 11.5 22.5 34.2 27.8
Claude3 Opus15.1 33.4 40.6 34.4 19.4 27.2 13.0 19.5 29.1 25.7
Gemini Ultra14.7 32.3 40.0 31.8 12.3 17.2 11.8 20.3 28.6 23.2
GPT-4V11.5 31.5 40.4 32.3 11.5 16.7 10.3 15.0 28.9 22.0
QwenVL Max7.7 31.4 37.6 30.2 18.6 25.4 10.4 4.8 23.5 21.1
Claude3 Sonnet10.5 28.9 35.6 31.8 13.9 22.2 11.0 15.2 20.8 21.1
QwenVL Plus4.8 28.8 33.7 27.1 12.8 19.9 9.4 5.6 18.1 17.8
MiniCPM-Llama3-V-2_56.1 29.6 35.7 26.0 12.1 13.1 5.7 12.6 15.3 17.3
InternVL-V1.53.4 27.1 31.4 27.1 9.9 9.0 4.9 8.7 12.4 14.9
GLM4V0.3 30.0 34.1 30.1 3.4 5.7 3.0 3.5 12.3 13.6
TextSquare3.7 27.0 30.8 26.7 3.2 7.2 6.7 5.2 12.4 13.6
Mini-Gemini-HD-34B2.2 25.0 29.2 25.5 6.1 8.6 4.1 4.3 11.8 13.0
InternLM-Xcomposer2-4KHD2.0 20.6 23.2 21.6 5.6 7.7 4.1 6.1 10.1 11.2
Llava-Next-34B3.3 24.0 28.0 22.3 3.6 6.1 2.6 0.4 9.8 11.1
TextMonkey2.0 18.1 19.9 22.1 4.6 7.2 3.2 0.9 11.1 9.9
MiniCPM-V-21.3 12.7 14.9 17.0 3.7 5.6 2.2 2.2 6.8 7.4
mPLUG-DocOwl 1.51.0 13.9 14.9 18.2 2.9 5.0 2.0 0.9 6.4 7.2
YI-VL-34B1.7 13.5 15.7 12.1 4.8 5.2 0.8 3.5 4.1 6.8
DeepSeek-VL0.6 14.2 15.3 15.2 2.9 3.8 1.6 0.9 5.2 6.6
+ + +## - Direct usage +The data is designed to evaluate and enhance the multilingual textual vqa capabilities of multimodal models in the hope of facilitating the understanding of multilingual images, enabling AI to reach more people in the world. + +### -- Huggingface dataloader +``` +from datasets import load_dataset +dataset = load_dataset(""ByteDance/MTVQA"") +``` + +## - Out-of-Scope usage +Academic use only, not supported for commercial usage. + +## - Ethics Assessment +Both GPT4V and manual assessment are employed to filter out unethical question and answer pairs. + +## - Bias, Risks, and Limitations +Your access to and use of this dataset are at your own risk. We do not guarantee the accuracy of this dataset. The dataset is provided “as is” and we make no warranty or representation to you with respect to it and we expressly disclaim, and hereby expressly waive, all warranties, express, implied, statutory or otherwise. This includes, without limitation, warranties of quality, performance, merchantability or fitness for a particular purpose, non-infringement, absence of latent or other defects, accuracy, or the presence or absence of errors, whether or not known or discoverable. In no event will we be liable to you on any legal theory (including, without limitation, negligence) or otherwise for any direct, special, indirect, incidental, consequential, punitive, exemplary, or other losses, costs, expenses, or damages arising out of this public license or use of the licensed material. The disclaimer of warranties and limitation of liability provided above shall be interpreted in a manner that, to the extent possible, most closely approximates an absolute disclaimer and waiver of all liability. + + +## - Citation +``` +@misc{tang2024mtvqa, + title={MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering}, + author={Jingqun Tang and Qi Liu and Yongjie Ye and Jinghui Lu and Shu Wei and Chunhui Lin and Wanqing Li and Mohamad Fitri Faiz Bin Mahmood and Hao Feng and Zhen Zhao and Yanjie Wang and Yuliang Liu and Hao Liu and Xiang Bai and Can Huang}, + year={2024}, + eprint={2405.11985}, + archivePrefix={arXiv}, + primaryClass={cs.CV} +} +```" +Bingsu/ko_alpaca_data,"{""dataset_info"": {""features"": [{""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""input"", ""dtype"": ""string""}, {""name"": ""output"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 13791136, ""num_examples"": 49620}], ""download_size"": 8491044, ""dataset_size"": 13791136}, ""license"": ""cc-by-nc-4.0"", ""language"": [""ko""], ""pretty_name"": ""ko-alpaca-data"", ""size_categories"": [""10K +huggingface: [beomi/KoAlpaca](https://huggingface.co/beomi/KoAlpaca) + +1. Translate dataset + +Translated 'instruction' and 'input' in the dataset via the DeepL API, except for 'output', which we did not translate because it is the output of OpenAI's `text-davinci-003` model. + +2. Generate output data + +Then, using the instruction and input, generate output data via the OpenAI ChatGPT API (gpt-3.5-turbo). + +Below is the prompt we used to generate the answer. + +```python +PROMPT = """"""\ +다양한 작업에 대한 답변을 생성해주세요. 이러한 작업 지침은 ChatGPT 모델에 주어지며, ChatGPT 모델이 지침을 완료하는지 평가합니다. + +요구 사항은 다음과 같습니다: +1. 다양성을 극대화하기 위해 각 지시에 대해 동사를 반복하지 않도록 하세요. +2. 지시에 사용되는 언어도 다양해야 합니다. 예를 들어, 질문과 명령형 지시를 결합해야 합니다. +3. 지시 사항의 유형이 다양해야 합니다. 목록에는 개방형 생성, 분류, 편집 등과 같은 다양한 유형의 작업이 포함되어야 합니다. +2. GPT 언어 모델은 지시를 완료할 수 있어야 합니다. 예를 들어 어시스턴트에게 시각적 또는 오디오 출력을 생성하도록 요청하지 마세요. 또 다른 예로, 어시스턴트가 어떤 작업도 수행할 수 없으므로 오후 5시에 깨우거나 미리 알림을 설정하도록 요청하지 마세요. +3. 답변은 한국어로 작성해야 합니다. +4. 답변을 1~2문장으로 작성하세요. 명령문이나 질문도 허용됩니다. +5. 지시 사항에 대한 적절한 입력을 생성해야 합니다. 입력 필드에는 지시에 대한 구체적인 예가 포함되어야 합니다. 실제 데이터를 포함해야 하며 단순한 자리 표시자를 포함해서는 안 됩니다. 입력은 지시 사항을 어렵게 만들 수 있는 상당한 내용을 제공해야 하지만 100단어를 넘지 않는 것이 이상적입니다. +6. 일부 지시사항은 추가 입력이 있고, 일부 지시에는 입력 필드가 비어있습니다. 예를 들어 ""세계에서 가장 높은 봉우리는 무엇인가?""라는 일반적인 정보를 묻는 지시의 경우 구체적인 맥락을 제공할 필요가 없어, 입력 필드가 비어있을 수 있습니다. +7. 출력은 명령어와 입력에 대한 적절한 응답이어야 합니다. + +아래에 10개의 명령어와 입력(옵션)에 따라 적절한 응답을 생성하세요. +응답은 아래와 같은 형식으로 10가지를 0번 부터 9번 까지, 번호에 따라 해당 번호의 명령어와 입력에 알맞게 작성하세요. + +각 응답 사이는 ### 으로 내용을 분리해주세요. + +응답0: 첫 번째 응답내용### +응답1: 두 번째 응답내용### +... +응답9: 마지막 응답내용"""""" +``` + +### Lisence + +CC-BY-NC-4.0 + +### Data Splits + +| | train | +| --------- | -------- | +| # of data | 49620 | + +\# Note that the number is not the same as the original data(52002) + + +```python +>>> from datasets import load_dataset + +>>> ds = load_dataset(""Bingsu/ko_alpaca_data"", split=""train"") +>>> ds +Dataset({ + features: ['instruction', 'input', 'output'], + num_rows: 49620 +}) +``` + +```python +>>> ds[0] +{'instruction': '건강을 유지하기 위한 세 가지 팁을 알려주세요.', + 'input': '', + 'output': '세 가지 팁은 아침식사를 꼭 챙기며, 충분한 수면을 취하고, 적극적으로 운동을 하는 것입니다.'} +```" +haoranxu/X-ALMA-Parallel-Data,"{""dataset_info"": [{""config_name"": ""af-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""af"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 803353, ""num_examples"": 2994}], ""download_size"": 520887, ""dataset_size"": 803353}, {""config_name"": ""ar-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""ar"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1017470, ""num_examples"": 2994}], ""download_size"": 587244, ""dataset_size"": 1017470}, {""config_name"": ""az-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""az"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 868767, ""num_examples"": 2994}], ""download_size"": 548812, ""dataset_size"": 868767}, {""config_name"": ""bg-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""bg"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1123254, ""num_examples"": 2994}], ""download_size"": 624175, ""dataset_size"": 1123254}, {""config_name"": ""ca-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""ca"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 827496, ""num_examples"": 2994}], ""download_size"": 538392, ""dataset_size"": 827496}, {""config_name"": ""cs-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""cs"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1550880, ""num_examples"": 6479}], ""download_size"": 1044916, ""dataset_size"": 1550880}, {""config_name"": ""da-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""da"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 786316, ""num_examples"": 2994}], ""download_size"": 514286, ""dataset_size"": 786316}, {""config_name"": ""de-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""de"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1694313, ""num_examples"": 7015}], ""download_size"": 1097168, ""dataset_size"": 1694313}, {""config_name"": ""el-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""el"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1211278, ""num_examples"": 2994}], ""download_size"": 672762, ""dataset_size"": 1211278}, {""config_name"": ""es-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""es"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 844431, ""num_examples"": 2994}], ""download_size"": 545686, ""dataset_size"": 844431}, {""config_name"": ""et-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""et"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1269025, ""num_examples"": 4994}], ""download_size"": 844040, ""dataset_size"": 1269025}, {""config_name"": ""fa-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""fa"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1043334, ""num_examples"": 2994}], ""download_size"": 587273, ""dataset_size"": 1043334}, {""config_name"": ""fi-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""fi"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1767639, ""num_examples"": 6987}], ""download_size"": 1151622, ""dataset_size"": 1767639}, {""config_name"": ""fr-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""fr"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1161017, ""num_examples"": 4494}], ""download_size"": 755975, ""dataset_size"": 1161017}, {""config_name"": ""gl-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""gl"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 817189, ""num_examples"": 2994}], ""download_size"": 534093, ""dataset_size"": 817189}, {""config_name"": ""gu-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""gu"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 2105747, ""num_examples"": 5008}], ""download_size"": 1022173, ""dataset_size"": 2105747}, {""config_name"": ""he-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""he"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 931335, ""num_examples"": 2994}], ""download_size"": 548830, ""dataset_size"": 931335}, {""config_name"": ""hi-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""hi"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1389945, ""num_examples"": 2994}], ""download_size"": 658112, ""dataset_size"": 1389945}, {""config_name"": ""hu-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""hu"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 848293, ""num_examples"": 2994}], ""download_size"": 560248, ""dataset_size"": 848293}, {""config_name"": ""id-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 821134, ""num_examples"": 2994}], ""download_size"": 514539, ""dataset_size"": 821134}, {""config_name"": ""is-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""is"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1384495, ""num_examples"": 4994}], ""download_size"": 884198, ""dataset_size"": 1384495}, {""config_name"": ""it-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""it"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 838865, ""num_examples"": 2994}], ""download_size"": 543944, ""dataset_size"": 838865}, {""config_name"": ""ja-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""ja"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1715595, ""num_examples"": 7039}], ""download_size"": 1075528, ""dataset_size"": 1715595}, {""config_name"": ""ka-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""ka"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1483680, ""num_examples"": 2994}], ""download_size"": 674194, ""dataset_size"": 1483680}, {""config_name"": ""kk-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""kk"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1790056, ""num_examples"": 4992}], ""download_size"": 978776, ""dataset_size"": 1790056}, {""config_name"": ""ko-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""ko"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 864688, ""num_examples"": 2994}], ""download_size"": 551253, ""dataset_size"": 864688}, {""config_name"": ""ky-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""ky"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1093521, ""num_examples"": 2994}], ""download_size"": 611728, ""dataset_size"": 1093521}, {""config_name"": ""lt-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""lt"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1360363, ""num_examples"": 4992}], ""download_size"": 892348, ""dataset_size"": 1360363}, {""config_name"": ""lv-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""lv"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1364674, ""num_examples"": 4995}], ""download_size"": 892646, ""dataset_size"": 1364674}, {""config_name"": ""mg-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""mg"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 885246, ""num_examples"": 2994}], ""download_size"": 534161, ""dataset_size"": 885246}, {""config_name"": ""mk-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""mk"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1122169, ""num_examples"": 2994}], ""download_size"": 613172, ""dataset_size"": 1122169}, {""config_name"": ""mr-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""mr"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1430599, ""num_examples"": 2994}], ""download_size"": 679329, ""dataset_size"": 1430599}, {""config_name"": ""ms-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""ms"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 816233, ""num_examples"": 2994}], ""download_size"": 509468, ""dataset_size"": 816233}, {""config_name"": ""ne-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""ne"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1375637, ""num_examples"": 2994}], ""download_size"": 660276, ""dataset_size"": 1375637}, {""config_name"": ""nl-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""nl"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 829405, ""num_examples"": 2994}], ""download_size"": 535906, ""dataset_size"": 829405}, {""config_name"": ""no-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""no"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 784676, ""num_examples"": 2994}], ""download_size"": 515255, ""dataset_size"": 784676}, {""config_name"": ""pl-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""pl"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1378794, ""num_examples"": 4995}], ""download_size"": 910980, ""dataset_size"": 1378794}, {""config_name"": ""pt-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""pt"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 821085, ""num_examples"": 2994}], ""download_size"": 535046, ""dataset_size"": 821085}, {""config_name"": ""ro-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""ro"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1395115, ""num_examples"": 4993}], ""download_size"": 893942, ""dataset_size"": 1395115}, {""config_name"": ""ru-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""ru"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 2328746, ""num_examples"": 7047}], ""download_size"": 1322470, ""dataset_size"": 2328746}, {""config_name"": ""sr-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""sr"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1063210, ""num_examples"": 2994}], ""download_size"": 610495, ""dataset_size"": 1063210}, {""config_name"": ""sv-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""sv"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 791631, ""num_examples"": 2994}], ""download_size"": 517584, ""dataset_size"": 791631}, {""config_name"": ""th-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""th"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1398077, ""num_examples"": 2994}], ""download_size"": 676121, ""dataset_size"": 1398077}, {""config_name"": ""tr-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""tr"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1596930, ""num_examples"": 5994}], ""download_size"": 1029093, ""dataset_size"": 1596930}, {""config_name"": ""uk-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""uk"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 2152390, ""num_examples"": 7049}], ""download_size"": 1233350, ""dataset_size"": 2152390}, {""config_name"": ""ur-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""ur"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1060022, ""num_examples"": 2994}], ""download_size"": 596439, ""dataset_size"": 1060022}, {""config_name"": ""uz-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""uz"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 842293, ""num_examples"": 2994}], ""download_size"": 537748, ""dataset_size"": 842293}, {""config_name"": ""vi-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""vi"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 927691, ""num_examples"": 2994}], ""download_size"": 552852, ""dataset_size"": 927691}, {""config_name"": ""zh-en"", ""features"": [{""name"": ""translation"", ""struct"": [{""name"": ""zh"", ""dtype"": ""string""}, {""name"": ""en"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1661642, ""num_examples"": 6906}], ""download_size"": 1107090, ""dataset_size"": 1661642}], ""configs"": [{""config_name"": ""af-en"", ""data_files"": [{""split"": ""train"", ""path"": ""af-en/train-*""}]}, {""config_name"": ""ar-en"", ""data_files"": [{""split"": ""train"", ""path"": ""ar-en/train-*""}]}, {""config_name"": ""az-en"", ""data_files"": [{""split"": ""train"", ""path"": ""az-en/train-*""}]}, {""config_name"": ""bg-en"", ""data_files"": [{""split"": ""train"", ""path"": ""bg-en/train-*""}]}, {""config_name"": ""ca-en"", ""data_files"": [{""split"": ""train"", ""path"": ""ca-en/train-*""}]}, {""config_name"": ""cs-en"", ""data_files"": [{""split"": ""train"", ""path"": ""cs-en/train-*""}]}, {""config_name"": ""da-en"", ""data_files"": [{""split"": ""train"", ""path"": ""da-en/train-*""}]}, {""config_name"": ""de-en"", ""data_files"": [{""split"": ""train"", ""path"": ""de-en/train-*""}]}, {""config_name"": ""el-en"", ""data_files"": [{""split"": ""train"", ""path"": ""el-en/train-*""}]}, {""config_name"": ""es-en"", ""data_files"": [{""split"": ""train"", ""path"": ""es-en/train-*""}]}, {""config_name"": ""et-en"", ""data_files"": [{""split"": ""train"", ""path"": ""et-en/train-*""}]}, {""config_name"": ""fa-en"", ""data_files"": [{""split"": ""train"", ""path"": ""fa-en/train-*""}]}, {""config_name"": ""fi-en"", ""data_files"": [{""split"": ""train"", ""path"": ""fi-en/train-*""}]}, {""config_name"": ""fr-en"", ""data_files"": [{""split"": ""train"", ""path"": ""fr-en/train-*""}]}, {""config_name"": ""gl-en"", ""data_files"": [{""split"": ""train"", ""path"": ""gl-en/train-*""}]}, {""config_name"": ""gu-en"", ""data_files"": [{""split"": ""train"", ""path"": ""gu-en/train-*""}]}, {""config_name"": ""he-en"", ""data_files"": [{""split"": ""train"", ""path"": ""he-en/train-*""}]}, {""config_name"": ""hi-en"", ""data_files"": [{""split"": ""train"", ""path"": ""hi-en/train-*""}]}, {""config_name"": ""hu-en"", ""data_files"": [{""split"": ""train"", ""path"": ""hu-en/train-*""}]}, {""config_name"": ""id-en"", ""data_files"": [{""split"": ""train"", ""path"": ""id-en/train-*""}]}, {""config_name"": ""is-en"", ""data_files"": [{""split"": ""train"", ""path"": ""is-en/train-*""}]}, {""config_name"": ""it-en"", ""data_files"": [{""split"": ""train"", ""path"": ""it-en/train-*""}]}, {""config_name"": ""ja-en"", ""data_files"": [{""split"": ""train"", ""path"": ""ja-en/train-*""}]}, {""config_name"": ""ka-en"", ""data_files"": [{""split"": ""train"", ""path"": ""ka-en/train-*""}]}, {""config_name"": ""kk-en"", ""data_files"": [{""split"": ""train"", ""path"": ""kk-en/train-*""}]}, {""config_name"": ""ko-en"", ""data_files"": [{""split"": ""train"", ""path"": ""ko-en/train-*""}]}, {""config_name"": ""ky-en"", ""data_files"": [{""split"": ""train"", ""path"": ""ky-en/train-*""}]}, {""config_name"": ""lt-en"", ""data_files"": [{""split"": ""train"", ""path"": ""lt-en/train-*""}]}, {""config_name"": ""lv-en"", ""data_files"": [{""split"": ""train"", ""path"": ""lv-en/train-*""}]}, {""config_name"": ""mg-en"", ""data_files"": [{""split"": ""train"", ""path"": ""mg-en/train-*""}]}, {""config_name"": ""mk-en"", ""data_files"": [{""split"": ""train"", ""path"": ""mk-en/train-*""}]}, {""config_name"": ""mr-en"", ""data_files"": [{""split"": ""train"", ""path"": ""mr-en/train-*""}]}, {""config_name"": ""ms-en"", ""data_files"": [{""split"": ""train"", ""path"": ""ms-en/train-*""}]}, {""config_name"": ""ne-en"", ""data_files"": [{""split"": ""train"", ""path"": ""ne-en/train-*""}]}, {""config_name"": ""nl-en"", ""data_files"": [{""split"": ""train"", ""path"": ""nl-en/train-*""}]}, {""config_name"": ""no-en"", ""data_files"": [{""split"": ""train"", ""path"": ""no-en/train-*""}]}, {""config_name"": ""pl-en"", ""data_files"": [{""split"": ""train"", ""path"": ""pl-en/train-*""}]}, {""config_name"": ""pt-en"", ""data_files"": [{""split"": ""train"", ""path"": ""pt-en/train-*""}]}, {""config_name"": ""ro-en"", ""data_files"": [{""split"": ""train"", ""path"": ""ro-en/train-*""}]}, {""config_name"": ""ru-en"", ""data_files"": [{""split"": ""train"", ""path"": ""ru-en/train-*""}]}, {""config_name"": ""sr-en"", ""data_files"": [{""split"": ""train"", ""path"": ""sr-en/train-*""}]}, {""config_name"": ""sv-en"", ""data_files"": [{""split"": ""train"", ""path"": ""sv-en/train-*""}]}, {""config_name"": ""th-en"", ""data_files"": [{""split"": ""train"", ""path"": ""th-en/train-*""}]}, {""config_name"": ""tr-en"", ""data_files"": [{""split"": ""train"", ""path"": ""tr-en/train-*""}]}, {""config_name"": ""uk-en"", ""data_files"": [{""split"": ""train"", ""path"": ""uk-en/train-*""}]}, {""config_name"": ""ur-en"", ""data_files"": [{""split"": ""train"", ""path"": ""ur-en/train-*""}]}, {""config_name"": ""uz-en"", ""data_files"": [{""split"": ""train"", ""path"": ""uz-en/train-*""}]}, {""config_name"": ""vi-en"", ""data_files"": [{""split"": ""train"", ""path"": ""vi-en/train-*""}]}, {""config_name"": ""zh-en"", ""data_files"": [{""split"": ""train"", ""path"": ""zh-en/train-*""}]}], ""language"": [""en"", ""da"", ""nl"", ""de"", ""is"", ""no"", ""sc"", ""af"", ""ca"", ""ro"", ""gl"", ""it"", ""pt"", ""es"", ""bg"", ""mk"", ""sr"", ""uk"", ""ru"", ""id"", ""ms"", ""th"", ""vi"", ""mg"", ""fr"", ""hu"", ""el"", ""cs"", ""pl"", ""lt"", ""lv"", ""ka"", ""zh"", ""ja"", ""ko"", ""fi"", ""et"", ""gu"", ""hi"", ""mr"", ""ne"", ""ur"", ""az"", ""kk"", ""ky"", ""tr"", ""uz"", ""ar"", ""he"", ""fa""]}","--- + +This is the translation parallel dataset used by [X-ALMA](https://arxiv.org/pdf/2410.03115). + +``` +@misc{xu2024xalmaplugplay, + title={X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale}, + author={Haoran Xu and Kenton Murray and Philipp Koehn and Hieu Hoang and Akiko Eriguchi and Huda Khayrallah}, + year={2024}, + eprint={2410.03115}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2410.03115}, +} +```" +changpt/ko-lima-vicuna,"{""license"": ""cc-by-2.0"", ""task_categories"": [""text-generation""], ""language"": [""ko""], ""size_categories"": [""n<1K""], ""pretty_name"": ""KoLima(vicuna)"", ""tags"": [""KoLima""]}","# Ko Lima Vicuna Dataset + +GPT4 API를 사용하여 [lima_vicuna_format 데이터](https://huggingface.co/datasets/64bits/lima_vicuna_format)를 한국어로 재생성한 데이터셋입니다. +GPT4 사용시 프롬프트는 ""단순 번역이 아닌, 원문 내용을 참조하여 데이터를 재생성하라""는 내용으로 작성하였습니다. +원본 데이터셋 1,030건 중 866건의 데이터가 재생성되었습니다. + +*데이터셋 제작은 웹 크롤링 전문 기업, **[해시스크래퍼(HASHSCRAPER)](https://www.hashscraper.com/)** 에서 진행되었습니다.* + + +*This is the lima_vicuna_format data regenerated into Korean using the GPT4 API.* +*When using GPT4, the prompt was written to read ""Regenerate the data by referring to the original content, not just a simple translation"".* +*Out of the 1,030 original datasets, 866 data points were regenerated.* + +*The dataset was created by [HASHSCRAPER](https://www.hashscraper.com/), a company specializing in web scraping.* + +--- + +# How to use + +```python +>>> from datasets import load_dataset + +>>> data = load_dataset(""changpt/ko-lima-vicuna"", data_files=""ko_lima_vicuna.json"", split=""train"") + + +>>> data +Dataset({ + features: ['id', 'conversations'], + num_rows: 866 +}) +``` + +```python +>>> data[0] +{'id': '7-stackexchange', + 'conversations': [{'from': 'human', + 'value': '나는 ```ffmpeg```로 비디오를 GIF 파일로 변환하고 있어:\n```ffmpeg \\\n -i input.flv \\\n -ss 00:00:00.000 \\\n -pix_fmt rgb24 \\\n -r 10 \\\n -s 320x240 \\\n -t 00:00:10.000 \\\n output.gif\n```\n잘 작동하는데, 출력된 gif 파일의 품질이 너무 낮아. 변환된 gif의 품질을 어떻게 개선할 수 있을까?'}, + {'from': 'gpt', + 'value': '중간 이미지 파일을 피하고 싶다면, LordNeckBeard가 제공한 명령어를 ```ffmpeg```와 ImageMagick의 ```convert``` 사이에 파이프로 연결할 수 있습니다. 이렇게 하면 중간 파일이 필요하지 않습니다:\n```ffmpeg -i input.flv -vf scale=320:-1 -r 10 -f image2pipe -vcodec ppm - | convert -delay 10 -loop 0 - output.gif\n```\n```-f image2pipe```는 ffmpeg에게 비디오를 이미지로 분할하고 파이프 출력에 적합하게 만들라고 지시하며, ```-vcodec ppm```은 출력 형식을 ppm으로 지정합니다(png 형식인 경우, ```convert```가 파이프에서 모든 이미지를 읽지 않거나 ffmpeg가 모두 출력하지 않는 것 같습니다). 두 명령어의 ```-```는 각각 출력과 입력에 파이프를 사용하도록 지정합니다.\n파일을 저장하지 않고 결과를 최적화하려면, ```convert```의 출력을 두 번째 ```convert``` 명령어로 파이프할 수 있습니다:\n```ffmpeg -i input.flv -vf scale=320:-1 -r 10 -f image2pipe -vcodec ppm - | convert -delay 10 -loop 0 - gif:- | convert -layers Optimize - output.gif\n```\n```gif:-```는 ```convert```에게 출력을 gif 형식의 데이터로 파이프하도록 지시하고, ```-layers Optimize```는 두 번째 ```convert```에게 ```optimize-frame``` 및 ```optimize-transparancy``` 방법을 수행하도록 지시합니다(ImageMagick 애니메이션 최적화 소개 참조). ```-layers Optimize```의 출력이 항상 더 작은 파일 크기를 제공하지는 않으므로, 먼저 최적화 없이 gif로 변환해 보는 것이 좋습니다.\n이 과정에서 모든 것이 메모리에 있으므로 이미지가 매우 큰 경우 충분한 메모리가 필요할 수 있습니다.'}]} +``` + +--- + +# License + +[CC BY 2.0 KR](https://creativecommons.org/licenses/by/2.0/kr/) + +[Open AI](https://openai.com/policies/terms-of-use)" +CohereForAI/include-base-44,"{""language"": [""sq"", ""ar"", ""hy"", ""az"", ""be"", ""bn"", ""eu"", ""bg"", ""tr"", ""hr"", ""nl"", ""fa"", ""es"", ""et"", ""fi"", ""fr"", ""de"", ""el"", ""ka"", ""he"", ""hi"", ""hu"", ""id"", ""it"", ""ja"", ""kk"", ""ko"", ""lt"", ""ml"", ""ms"", ""ne"", ""pl"", ""pt"", ""ru"", ""ta"", ""tl"", ""te"", ""uk"", ""ur"", ""uz"", ""vi"", ""zh"", ""sr"", ""mk""], ""license"": ""apache-2.0"", ""size_categories"": [""100K +- **Paper**: http://arxiv.org/abs/2411.19799 + + +### Dataset Summary + +INCLUDE is a comprehensive knowledge- and reasoning-centric benchmark across **44 languages** that evaluates multilingual LLMs for performance in the actual language environments where they would be deployed. +It contains 22,637 4-option multiple-choice-questions (MCQ) extracted from academic and professional exams, covering 57 topics, including regional knowledge. + +For a quicker evaluation, you can use [include-lite-44](https://huggingface.co/datasets/CohereForAI/include-lite-44), which is a subset of `include-base-44`, covering the same 44 languages. + +### Languages + +Albanian, Arabic, Armenian, Azerbaijani, Basque, Belarusian, Bengali, Bulgarian, Chinese, Croatian, Dutch, Estonian, Finnish, French, Georgian, German, Greek, Hebrew, Hindi, Hungarian, Indonesia, Italian, Japanese, Kazakh, Korean, Lithuanian, Malay, Malayalam, Nepali, North Macedonian, Persian, Polish, Portuguese, russian, Serbian, Spanish, Tagalog, Tamil, Telugu, Turkish, Ukrainian, Urdu, Uzbek, Vietnamese + +### Topics + +- **Academic**: +Accounting, Agriculture, Anthropology, Architecture and Design, Arts & Humanities, Biology, Business administration, Business ethics, Business, Chemistry, Computer Science, Culturology, Earth science, Economics, Education, Engineering, Environmental studies and forestry, Family and consumer science, Finance, Geography, Health, History, Human physical performance and recreation, Industrial and labor relations, International trade, Journalism, media studies, and communication, Language, Law, Library and museum studies, Literature, Logic, Management, Marketing, Math, Medicine, Military Sciences, Multiple exams, Performing arts, Philosophy, Physics, Political sciences, Psychology, Public Administration, Public Policy, Qualimetry, Religious studies, Risk management and insurance, Social Work, Social work, Sociology, STEM, Transportation, Visual Arts + +- **Licenses**: +Driving License, Marine License, Medical License, Professional Certifications + + +### Data schema + +An example from a French Law question looks as follows: +``` +{ + ""language"": ""French"", + ""country"": ""France"", + ""level"": ""Academic"", + ""domain"": ""Arts & Humanities"", + ""subject"": ""Law"", + ""regional_feature"": ""region explicit"", + ""question"": ""Que permet l'article 49-3 de la Constitution ?"", + ""choices"": [""de recourir au référendum"", ""au Parlement de contrôler l'action du Gouvernement"", ""l'adoption sans vote d'une loi"", ""de prononcer la dissolution de l'Assemblée nationale""], + ""answer"": 2 +} +``` + +### Model Performance + +Models performance on **INCLUDE** using the Harness-eval framework. + + +| **Model** | **Original Language instructions** | **English instructions** | +|------------------------------------|:--------------------------:|:--------------------:| +| Llama3.1-70B-Instruct | 70.6 | 70.9 | +| Qwen2.5-14B | 62.3 | 62.6 | +| Aya-expanse-32b | 59.1 | 59.5 | +| Qwen2.5-7B | 55.0 | 55.5 | +| Qwen2.5-7B-Instruct | 54.8 | 54.8 | +| Llama-3.1-8B-Instruct | 53.5 | 54.4 | +| Gemma-7B | 53.5 | 53.2 | +| Llama-3.1-8B | 51.2 | 51.9 | +| Aya-expanse-8b | 47.2 | 47.8 | +| Mistral-7B | 44.1 | 44.6 | +| Mistral-7B-Instruct | 44.2 | 44.3 | +| Gemma-7B-Instruct | 38.6 | 39.3 | + + +## Citation + +``` +@article{romanou2024include, + title={INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge}, + author={Romanou, Angelika and Foroutan, Negar and Sotnikova, Anna and Chen, Zeming and Nelaturu, Sree Harsha and Singh, Shivalika and Maheshwary, Rishabh and Altomare, Micol and Haggag, Mohamed A and Amayuelas, Alfonso and others}, + journal={arXiv preprint arXiv:2411.19799}, + year={2024} +} +```" +1-800-SHARED-TASKS/xlsum-subset,"{""annotations_creators"": [""found""], ""language_creators"": [""found""], ""language"": [""am"", ""ar"", ""az"", ""bn"", ""my"", ""zh"", ""en"", ""fr"", ""gu"", ""ha"", ""hi"", ""ig"", ""id"", ""ja"", ""rn"", ""ko"", ""ky"", ""mr"", ""ne"", ""om"", ""ps"", ""fa"", ""pcm"", ""pt"", ""pa"", ""ru"", ""gd"", ""sr"", ""si"", ""so"", ""es"", ""sw"", ""ta"", ""te"", ""th"", ""ti"", ""tr"", ""uk"", ""ur"", ""uz"", ""vi"", ""cy"", ""yo""], ""license"": [""cc-by-nc-sa-4.0""], ""multilinguality"": [""multilingual""], ""size_categories"": [""1M`, using your real name. + +This can be done easily using the `-s` flag on the `git commit`. + +Please see the [Contribution guidelines](https://oldi.org/guidelines) for further information. + +### How to add a pull request + +1. Go to https://huggingface.co/datasets/openlanguagedata/flores_plus/discussions, press ""New pull request"". +2. In the popup window, enter a branch name and press ""Create branch"". +3. On your computer, do `git clone https://huggingface.co/datasets/openlanguagedata/flores_plus`. +4. Checkout to your newly created branch (e.g. `cd flores_plus && git fetch origin refs/pr/4:pr/4 && git checkout pr/4`). +5. Check that you are logged in to the HF CLI tool (`huggingface-cli whoami`). If not, please log into it (`huggingface-cli login` and enter your token). +6. Modify a file (for adding new languages, see the instructions below) and add the changes to git (e.g. `git add dev/rus_Cyrl.parquet`). +7. Commit with an -s flag (e.g. `git commit -s -m ""fix a few typos in the Russian dev set""`). +8. Push (e.g. `git push --set-upstream origin pr/4`). +9. Go to the pull request page and see if it reflects your changes. +10. When your pull request is ready, press the ""Publish"" button in its web interface. + +### Testing your changes + +After contributing new translations or modifying existing ones, you can check that the data format is OK. +Assuming that you have the Python packages `pytest` and `dataset` installed, you can type +``` +pytest +``` +in your console (in the `flores_plus` directory), and the tests will run. +If any of them fails, please inspect the translations, following the hints in the test output. + +## Changelog + +See [CHANGELOG.md](CHANGELOG.md) for information about the latest changes. + +## Language Coverage + +| Code | Script | Glottocode | Name | Notes | +|-------|--------|------------|-------------------------------------|------------------------------------------------------------| +| `ace` | `Arab` | `achi1257` | Acehnese (Jawi script) | | +| `ace` | `Latn` | `achi1257` | Acehnese (Latin script) | | +| `acm` | `Arab` | `meso1252` | Mesopotamian Arabic | | +| `acq` | `Arab` | `taiz1242` | Taʽizzi-Adeni Arabic | | +| `aeb` | `Arab` | `tuni1259` | Tunisian Arabic | | +| `afr` | `Latn` | `afri1274` | Afrikaans | | +| `als` | `Latn` | `tosk1239` | Albanian (Tosk) | | +| `amh` | `Ethi` | `amha1245` | Amharic | | +| `apc` | `Arab` | `nort3139` | Levantine Arabic (North) | | +| `apc` | `Arab` | `sout3123` | Levantine Arabic (South) | | +| `arb` | `Arab` | `stan1318` | Modern Standard Arabic | | +| `arb` | `Latn` | `stan1318` | Modern Standard Arabic (Romanized) | | +| `arg` | `Latn` | `arag1245` | Aragonese | | +| `ars` | `Arab` | `najd1235` | Najdi Arabic | | +| `ary` | `Arab` | `moro1292` | Moroccan Arabic | | +| `arz` | `Arab` | `egyp1253` | Egyptian Arabic | | +| `asm` | `Beng` | `assa1263` | Assamese | | +| `ast` | `Latn` | `astu1245` | Asturian | | +| `awa` | `Deva` | `awad1243` | Awadhi | | +| `ayr` | `Latn` | `cent2142` | Central Aymara | | +| `azb` | `Arab` | `sout2697` | South Azerbaijani | | +| `azj` | `Latn` | `nort2697` | North Azerbaijani | | +| `bak` | `Cyrl` | `bash1264` | Bashkir | | +| `bam` | `Latn` | `bamb1269` | Bambara | | +| `ban` | `Latn` | `bali1278` | Balinese | | +| `bel` | `Cyrl` | `bela1254` | Belarusian | | +| `bem` | `Latn` | `bemb1257` | Bemba | | +| `ben` | `Beng` | `beng1280` | Bengali | | +| `bho` | `Deva` | `bhoj1244` | Bhojpuri | | +| `bjn` | `Arab` | `banj1239` | Banjar (Jawi script) | | +| `bjn` | `Latn` | `banj1239` | Banjar (Latin script) | | +| `bod` | `Tibt` | `utsa1239` | Lhasa Tibetan | | +| `bos` | `Latn` | `bosn1245` | Bosnian | | +| `brx` | `Deva` | `bodo1269` | Bodo | `dev` only | +| `bug` | `Latn` | `bugi1244` | Buginese | | +| `bul` | `Cyrl` | `bulg1262` | Bulgarian | | +| `cat` | `Latn` | `stan1289` | Catalan | | +| `cat` | `Latn` | `vale1252` | Valencian | | +| `ceb` | `Latn` | `cebu1242` | Cebuano | | +| `ces` | `Latn` | `czec1258` | Czech | | +| `chv` | `Cyrl` | `chuv1255` | Chuvash | | +| `cjk` | `Latn` | `chok1245` | Chokwe | | +| `ckb` | `Arab` | `cent1972` | Central Kurdish | | +| `cmn` | `Hans` | `beij1234` | Mandarin Chinese (Standard Beijing) | | +| `cmn` | `Hant` | `taib1240` | Mandarin Chinese (Taiwanese) | | +| `crh` | `Latn` | `crim1257` | Crimean Tatar | | +| `cym` | `Latn` | `wels1247` | Welsh | | +| `dan` | `Latn` | `dani1285` | Danish | | +| `dar` | `Cyrl` | `darg1241` | Dargwa | `dev` only | +| `deu` | `Latn` | `stan1295` | German | | +| `dgo` | `Deva` | `dogr1250` | Dogri | `dev` only | +| `dik` | `Latn` | `sout2832` | Southwestern Dinka | | +| `dyu` | `Latn` | `dyul1238` | Dyula | | +| `dzo` | `Tibt` | `dzon1239` | Dzongkha | | +| `ekk` | `Latn` | `esto1258` | Estonian | | +| `ell` | `Grek` | `mode1248` | Greek | | +| `eng` | `Latn` | `stan1293` | English | | +| `epo` | `Latn` | `espe1235` | Esperanto | | +| `eus` | `Latn` | `basq1248` | Basque | | +| `ewe` | `Latn` | `ewee1241` | Ewe | | +| `fao` | `Latn` | `faro1244` | Faroese | | +| `fij` | `Latn` | `fiji1243` | Fijian | | +| `fil` | `Latn` | `fili1244` | Filipino | | +| `fin` | `Latn` | `finn1318` | Finnish | | +| `fon` | `Latn` | `fonn1241` | Fon | | +| `fra` | `Latn` | `stan1290` | French | | +| `fur` | `Latn` | `east2271` | Friulian | | +| `fuv` | `Latn` | `nige1253` | Nigerian Fulfulde | | +| `gaz` | `Latn` | `west2721` | West Central Oromo | | +| `gla` | `Latn` | `scot1245` | Scottish Gaelic | | +| `gle` | `Latn` | `iris1253` | Irish | | +| `glg` | `Latn` | `gali1258` | Galician | | +| `gom` | `Deva` | `goan1235` | Goan Konkani | | +| `gug` | `Latn` | `para1311` | Paraguayan Guaraní | | +| `guj` | `Gujr` | `guja1252` | Gujarati | | +| `hat` | `Latn` | `hait1244` | Haitian Creole | | +| `hau` | `Latn` | `haus1257` | Hausa | | +| `heb` | `Hebr` | `hebr1245` | Hebrew | | +| `hin` | `Deva` | `hind1269` | Hindi | | +| `hne` | `Deva` | `chha1249` | Chhattisgarhi | | +| `hrv` | `Latn` | `croa1245` | Croatian | | +| `hun` | `Latn` | `hung1274` | Hungarian | | +| `hye` | `Armn` | `nucl1235` | Armenian | | +| `ibo` | `Latn` | `nucl1417` | Igbo | | +| `ilo` | `Latn` | `ilok1237` | Ilocano | | +| `ind` | `Latn` | `indo1316` | Indonesian | | +| `isl` | `Latn` | `icel1247` | Icelandic | | +| `ita` | `Latn` | `ital1282` | Italian | | +| `jav` | `Latn` | `java1254` | Javanese | | +| `jpn` | `Jpan` | `nucl1643` | Japanese | | +| `kaa` | `Latn` | `kara1467` | Karakalpak | `devtest` only | +| `kab` | `Latn` | `kaby1243` | Kabyle | | +| `kac` | `Latn` | `kach1280` | Jingpho | | +| `kam` | `Latn` | `kamb1297` | Kamba | | +| `kan` | `Knda` | `nucl1305` | Kannada | | +| `kas` | `Arab` | `kash1277` | Kashmiri (Arabic script) | | +| `kas` | `Deva` | `kash1277` | Kashmiri (Devanagari script) | | +| `kat` | `Geor` | `nucl1302` | Georgian | | +| `kaz` | `Cyrl` | `kaza1248` | Kazakh | | +| `kbp` | `Latn` | `kabi1261` | Kabiyè | | +| `kea` | `Latn` | `kabu1256` | Kabuverdianu | | +| `khk` | `Cyrl` | `halh1238` | Halh Mongolian | | +| `khm` | `Khmr` | `cent1989` | Khmer (Central) | | +| `kik` | `Latn` | `kiku1240` | Kikuyu | | +| `kin` | `Latn` | `kiny1244` | Kinyarwanda | | +| `kir` | `Cyrl` | `kirg1245` | Kyrgyz | | +| `kmb` | `Latn` | `kimb1241` | Kimbundu | | +| `kmr` | `Latn` | `nort2641` | Northern Kurdish | | +| `knc` | `Arab` | `cent2050` | Central Kanuri (Arabic script) | | +| `knc` | `Latn` | `cent2050` | Central Kanuri (Latin script) | | +| `kor` | `Hang` | `kore1280` | Korean | | +| `ktu` | `Latn` | `kitu1246` | Kituba (DRC) | | +| `lao` | `Laoo` | `laoo1244` | Lao | | +| `lij` | `Latn` | `geno1240` | Ligurian (Genoese) | | +| `lim` | `Latn` | `limb1263` | Limburgish | | +| `lin` | `Latn` | `ling1263` | Lingala | | +| `lit` | `Latn` | `lith1251` | Lithuanian | | +| `lmo` | `Latn` | `lomb1257` | Lombard | [[1]](https://github.com/openlanguagedata/flores/issues/5) | +| `ltg` | `Latn` | `east2282` | Latgalian | | +| `ltz` | `Latn` | `luxe1241` | Luxembourgish | | +| `lua` | `Latn` | `luba1249` | Luba-Kasai | | +| `lug` | `Latn` | `gand1255` | Ganda | | +| `luo` | `Latn` | `luok1236` | Luo | | +| `lus` | `Latn` | `lush1249` | Mizo | | +| `lvs` | `Latn` | `stan1325` | Standard Latvian | | +| `mag` | `Deva` | `maga1260` | Magahi | | +| `mai` | `Deva` | `mait1250` | Maithili | | +| `mal` | `Mlym` | `mala1464` | Malayalam | | +| `mar` | `Deva` | `mara1378` | Marathi | | +| `mhr` | `Cyrl` | `gras1239` | Meadow Mari | `dev` only | +| `min` | `Arab` | `mina1268` | Minangkabau (Jawi script) | | +| `min` | `Latn` | `mina1268` | Minangkabau (Latin script) | | +| `mkd` | `Cyrl` | `mace1250` | Macedonian | | +| `mlt` | `Latn` | `malt1254` | Maltese | | +| `mni` | `Beng` | `mani1292` | Meitei (Manipuri, Bengali script) | | +| `mni` | `Mtei` | `mani1292` | Meitei (Manipuri, Meitei script) | `dev` only | +| `mos` | `Latn` | `moss1236` | Mossi | | +| `mri` | `Latn` | `maor1246` | Maori | | +| `mya` | `Mymr` | `nucl1310` | Burmese | | +| `myv` | `Cyrl` | `erzy1239` | Erzya | | +| `nld` | `Latn` | `dutc1256` | Dutch | | +| `nno` | `Latn` | `norw1262` | Norwegian Nynorsk | | +| `nob` | `Latn` | `norw1259` | Norwegian Bokmål | | +| `npi` | `Deva` | `nepa1254` | Nepali | | +| `nqo` | `Nkoo` | `nkoa1234` | Nko | | +| `nso` | `Latn` | `pedi1238` | Northern Sotho | | +| `nus` | `Latn` | `nuer1246` | Nuer | | +| `nya` | `Latn` | `nyan1308` | Nyanja | | +| `oci` | `Latn` | `occi1239` | Occitan | | +| `oci` | `Latn` | `aran1260` | Aranese | | +| `ory` | `Orya` | `oriy1255` | Odia | | +| `pag` | `Latn` | `pang1290` | Pangasinan | | +| `pan` | `Guru` | `panj1256` | Eastern Panjabi | | +| `pap` | `Latn` | `papi1253` | Papiamento | | +| `pbt` | `Arab` | `sout2649` | Southern Pashto | | +| `pes` | `Arab` | `west2369` | Western Persian | | +| `plt` | `Latn` | `plat1254` | Plateau Malagasy | | +| `pol` | `Latn` | `poli1260` | Polish | | +| `por` | `Latn` | `braz1246` | Portuguese (Brazilian) | | +| `prs` | `Arab` | `dari1249` | Dari | | +| `quy` | `Latn` | `ayac1239` | Ayacucho Quechua | | +| `ron` | `Latn` | `roma1327` | Romanian | | +| `run` | `Latn` | `rund1242` | Rundi | | +| `rus` | `Cyrl` | `russ1263` | Russian | | +| `sag` | `Latn` | `sang1328` | Sango | | +| `san` | `Deva` | `sans1269` | Sanskrit | | +| `sat` | `Olck` | `sant1410` | Santali | | +| `scn` | `Latn` | `sici1248` | Sicilian | | +| `shn` | `Mymr` | `shan1277` | Shan | | +| `sin` | `Sinh` | `sinh1246` | Sinhala | | +| `slk` | `Latn` | `slov1269` | Slovak | | +| `slv` | `Latn` | `slov1268` | Slovenian | | +| `smo` | `Latn` | `samo1305` | Samoan | | +| `sna` | `Latn` | `shon1251` | Shona | | +| `snd` | `Arab` | `sind1272` | Sindhi (Arabic script) | | +| `snd` | `Deva` | `sind1272` | Sindhi (Devanagari script) | `dev` only | +| `som` | `Latn` | `soma1255` | Somali | | +| `sot` | `Latn` | `sout2807` | Southern Sotho | | +| `spa` | `Latn` | `amer1254` | Spanish (Latin American) | | +| `srd` | `Latn` | `sard1257` | Sardinian | [[1]](https://github.com/openlanguagedata/flores/issues/6) | +| `srp` | `Cyrl` | `serb1264` | Serbian | | +| `ssw` | `Latn` | `swat1243` | Swati | | +| `sun` | `Latn` | `sund1252` | Sundanese | | +| `swe` | `Latn` | `swed1254` | Swedish | | +| `swh` | `Latn` | `swah1253` | Swahili | | +| `szl` | `Latn` | `sile1253` | Silesian | | +| `tam` | `Taml` | `tami1289` | Tamil | | +| `taq` | `Latn` | `tama1365` | Tamasheq (Latin script) | | +| `taq` | `Tfng` | `tama1365` | Tamasheq (Tifinagh script) | | +| `tat` | `Cyrl` | `tata1255` | Tatar | | +| `tel` | `Telu` | `telu1262` | Telugu | | +| `tgk` | `Cyrl` | `taji1245` | Tajik | | +| `tha` | `Thai` | `thai1261` | Thai | | +| `tir` | `Ethi` | `tigr1271` | Tigrinya | | +| `tpi` | `Latn` | `tokp1240` | Tok Pisin | | +| `tsn` | `Latn` | `tswa1253` | Tswana | | +| `tso` | `Latn` | `tson1249` | Tsonga | | +| `tuk` | `Latn` | `turk1304` | Turkmen | | +| `tum` | `Latn` | `tumb1250` | Tumbuka | | +| `tur` | `Latn` | `nucl1301` | Turkish | | +| `twi` | `Latn` | `akua1239` | Akuapem Twi | | +| `twi` | `Latn` | `asan1239` | Asante Twi | | +| `tyv` | `Cyrl` | `tuvi1240` | Tuvan | | +| `uig` | `Arab` | `uigh1240` | Uyghur | | +| `ukr` | `Cyrl` | `ukra1253` | Ukrainian | | +| `umb` | `Latn` | `umbu1257` | Umbundu | | +| `urd` | `Arab` | `urdu1245` | Urdu | | +| `uzn` | `Latn` | `nort2690` | Northern Uzbek | | +| `vec` | `Latn` | `vene1259` | Venetian | | +| `vie` | `Latn` | `viet1252` | Vietnamese | | +| `vmw` | `Latn` | `cent2033` | Emakhuwa (Central) | | +| `war` | `Latn` | `wara1300` | Waray | | +| `wol` | `Latn` | `nucl1347` | Wolof | | +| `wuu` | `Hans` | `suhu1238` | Wu Chinese | `dev` only | +| `xho` | `Latn` | `xhos1239` | Xhosa | | +| `ydd` | `Hebr` | `east2295` | Eastern Yiddish | | +| `yor` | `Latn` | `yoru1245` | Yoruba | | +| `yue` | `Hant` | `xian1255` | Yue Chinese (Hong Kong Cantonese) | | +| `zgh` | `Tfng` | `stan1324` | Standard Moroccan Tamazight | | +| `zsm` | `Latn` | `stan1306` | Standard Malay | | +| `zul` | `Latn` | `zulu1248` | Zulu | |" +heegyu/namuwiki,"{""license"": ""cc-by-nc-sa-2.0"", ""language"": [""ko""], ""language_creators"": [""other""], ""multilinguality"": [""monolingual""], ""size_categories"": [""100K +- 867024 rows +- download size: 3GB + +## Usage +```bash +pip install datasets +``` + +```python +from datasets import load_dataset + +dataset = load_dataset(""heegyu/namuwiki"") + +print(dataset[""train""][0]) +``` +``` +{'title': '!!아앗!!', + 'text': '\n[목차]\n\n\'\'\'{{{+1 ！！ああっと！！}}}\'\'\'\n\n== 개요 ==\n[[파일:3444050440.jpg|width=60%]]\n▲[[신 세계수의 미궁 2 파프니르기사|신 세계수의 미궁 2]]에서 뜬 !!아앗!!\n\n[[세계수의 미궁 시리즈]]에 전통으로 등장하는 대사. [[세계수의 미궁 2 제왕의 성배|2편]]부터 등장했으며 훌륭한 [[사망 플래그]]의 예시이다.\n\n세계수의 모험가들이 탐험하는 던전인 수해의 구석구석에는 채취/벌채/채굴 포인트가 있으며, 이를 위한 채집 스킬에 투자하면 제한된 채집 기회에서 보다 큰 이득을 챙길 수 있다. 그러나 분배할 수 있는 스킬 포인트는 한정되어 있기 때문에 채집 스킬에 투자하는 만큼 전투 스킬 레벨은 낮아지게 된다.[* 다만 채집 시스템은 신 세계수 시리즈의 그리모어 복제, 복합 채집 스킬인 야생의 감, 5편의 종족 특유 스킬, 크로스의 1레벨이 만렙인 채집 스킬 등으로 편의성이 점차 나아져서 채집 스킬 때문에 스킬 트리가 내려가는 일은 점점 줄어들었다.] !!아앗!!이 발생하는 과정을 요약하면 다음과 같다.\n\n 1. 채집용 캐릭터들로 이루어진 약한 파티(ex: [[레인저(세계수의 미궁 2)|레인저]] 5명)가 수해에 입장한다.\n 1. 필드 전투를 피해 채집 포인트에 도착한 후 열심히 아이템을 캐는 중에...\n 1. \'\'\'!!아앗!!\'\'\' ~~라플레시아가 나타났다!~~\n 이때 등장하는 것은 [[FOE(세계수의 미궁 시리즈)|FOE]]는 아니지만 \'\'\'훨씬 위층에 등장하는 강력한 필드 몬스터이며 선제 공격을 당하게 된다!\'\'\'\n 1. \'\'\'으앙 죽음\'\'\'(hage)\n\n여담으로 !!아앗!!의 유래는 1인칭 던전 크롤러의 원조 [[위저드리]]에서 함정을 건드렸을 때 나오는 대사 Oops!(おおっと！)라고 한다.\n\n== 각 작품에서의 모습 ==\n=== [[세계수의 미궁 2 제왕의 성배]] ===\n!!아앗!!의 악랄함은 첫 등장한 작품이자 시리즈 중에서도 불친절하기로 정평이 난 2편이 절정이었다. 그야말로 위의 !!아앗!! 시퀀스 그대로, 묻지도 따지지도 않고 채집할 때마다 일정 확률로 \'\'\'강제로\'\'\' 전투에 돌입해야 했다. 게다가 이럴 때 쓰라고 있는 레인저의 스킬 \'위험 감지(중간 확률로 적의 선제 공격을 무효화)\'는 정작 작동하지 않는다!\n\n참고로 2편에서 채집 도중 !!아앗!!이 뜰 확률은 [[http://www.atlusnet.jp/topic/detail/910|고작 1%다.]] [[던파확률의 법칙|낮아 보이는 확률이어도 플레이 중 한 번이라도 일어나는 것]]을 경험하는 체감 확률을 고려하여 확률을 설정한다고.\n\n=== [[세계수의 미궁 3 성해의 내방자]] ===\n다행히 채집 중 낮은 확률로 ""좋은 아이템을 얻을 수 있을 것 같지만... 주변에서 몬스터들의 기척이 느껴진다.""는 메시지가 뜨고 이때 운이 좋으면 레어 아이템을 얻을 수 있지만 반대의 경우 적과 싸우게 되는 것으로 조정되었다.\n\n=== [[세계수의 미궁 4 전승의 거신]] ===\n기본적인 것은 3편과 같지만, 4편에서는 움직이지 않고 채집할 때도 턴이 경과하도록 조정되었기 때문에 주변에 있는 FOE를 잊고 채집에 몰두하다가 FOE와 부딪히면 FOE 버전 !!아앗!!이 뜬다. 그리고 난이도 CASUAL로 플레이시, FOE로 인한 !!아앗!!을 제외하면 절대로 발생하지 않는다.\n\n=== [[신 세계수의 미궁 밀레니엄의 소녀|신 세계수의]] [[신 세계수의 미궁 2 파프니르기사|미궁 시리즈]] ===\n채집 방식이 한 턴으로 끝나는 구조[* 채집으로 한 번 아이템을 획득하면 ""다시, (채집 스킬)에 의해...""가 뜨면서 한꺼번에 획득되는 구조.]로 바뀐 덕분인지 강제 조우로 다시 회귀해버렸다(...). 그나마 위험 감지 먹통과 같은 버그성 난점들은 수정되었다. 그 이후에 나온 [[세계수의 미궁 5 오랜 신화의 끝]]과 시리즈의 집대성 작품이자 3DS 마지막 작품인 [[세계수의 미궁 X]]도 마찬가지.\n\n=== [[세계수의 미궁 X]] ===\n본작의 채집은 신 세계수 시리즈와 같은 매커니즘이라 굳이 언급할 필요는 없으나, 퀘스트중에 2편의 !!아앗!! 시퀀스를 재현하면서 \'\'\'라플레시아\'\'\'가 등장하는 퀘스트가 존재한다.(...) 깨알같이 시스템 메세지 창이 아니라 대화창을 이용해서 완벽 재현한 것이 포인트.\n\n=== [[페르소나 Q 섀도우 오브 더 래버린스]] ===\n세계수 시스템을 기반으로 한 [[페르소나 시리즈]]와의 콜라보 작품인 페르소나 Q에서도 등장한다. 3, 4편과 같이 파워 스폿에서 채집 도중 메시지가 뜨며, 실패하면 파티에 참가하고 있는 멤버 중 한 명의 [[http://nico.ms/sm25683358|!!아앗!! 하는 음성]] ~~또는 [[코로마루|개소리]]~~과 함께 그 던전의 \'강적\'인 거대 [[섀도(페르소나 시리즈)|섀도우]]가 나타난다.\n\n그러나 내비 전용 스킬인 뱀눈 노려보기(위험 감지와 같은 효과)와 채집 보조 스킬은 파티의 전투력에 전혀 지장을 주지 않으며, \'대안심\'을 달면 거의 볼 일이 없어져서 초중반 이후에는 존재감이 급격히 줄어든다.\n[[분류:세계수의 미궁 시리즈]]', + 'contributors': '110.46.34.123,kirby10,max0243,218.54.117.149,ruby3141,121.165.63.239,iviyuki,1.229.200.194,anatra95,kiri47,175.127.134.2,nickchaos71,chkong1998,kiwitree2,namubot,huwieblusnow', + 'namespace': ''} +```" +mteb/NTREX,"{""annotations_creators"": [""expert-generated""], ""language_creators"": [""expert-generated""], ""language"": [""af"", ""am"", ""ar"", ""az"", ""ba"", ""be"", ""bg"", ""bn"", ""bo"", ""bs"", ""ca"", ""cs"", ""cy"", ""da"", ""de"", ""dv"", ""dz"", ""ee"", ""el"", ""et"", ""eu"", ""fa"", ""fa"", ""fi"", ""fil"", ""fj"", ""fj"", ""fo"", ""fr"", ""gd"", ""gu"", ""ha"", ""he"", ""hi"", ""hmn"", ""hr"", ""hu"", ""hy"", ""id"", ""ig"", ""is"", ""it"", ""ja"", ""kk"", ""km"", ""kn"", ""ko"", ""ku"", ""ku"", ""ky"", ""lb"", ""lo"", ""lt"", ""lv"", ""mi"", ""mk"", ""mn"", ""mr"", ""ms"", ""ms"", ""mt"", ""my"", ""nb"", ""nd"", ""ne"", ""nl"", ""nn"", ""ny"", ""om"", ""oy"", ""pa"", ""ps"", ""pt"", ""ro"", ""ru"", ""rw"", ""sd"", ""sh"", ""shi"", ""si"", ""sk"", ""sl"", ""sm"", ""sn"", ""so"", ""sq"", ""sr"", ""ss"", ""st"", ""sv"", ""sw"", ""ta"", ""te"", ""tg"", ""th"", ""tk"", ""tn"", ""to"", ""tr"", ""tt"", ""ty"", ""uk"", ""ur"", ""uz"", ""ve"", ""vi"", ""wo"", ""xh"", ""yo"", ""zh"", ""zh"", ""zu""], ""license"": [""cc-by-sa-4.0""], ""multilinguality"": [""translation""], ""task_categories"": [""translation""], ""size_categories"": [""1997""], ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""test"", ""path"": ""test.parquet""}]}]}","## Dataset Description + +NTREX -- News Test References for MT Evaluation from English into a total of 128 target languages. See [original GitHub repo](https://github.com/MicrosoftTranslator/NTREX/tree/main) for full details. + +Example of loading: +```python +dataset = load_dataset(""davidstap/NTREX"", ""rus_Cyrl"", trust_remote_code=True) +``` + +## Languages + +The following languages are available: + +| Language Code | Language Name | +|-----------------|-----------------------------| +| `afr_Latn` | Afrikaans | +| `amh_Ethi` | Amharic | +| `arb_Arab` | Arabic | +| `aze_Latn` | Azerbaijani | +| `bak_Cyrl` | Bashkir | +| `bel_Cyrl` | Belarusian | +| `bem_Latn` | Bemba | +| `ben_Beng` | Bengali | +| `bod_Tibt` | Tibetan | +| `bos_Latn` | Bosnian | +| `bul_Cyrl` | Bulgarian | +| `cat_Latn` | Catalan | +| `ces_Latn` | Czech | +| `ckb_Arab` | Sorani Kurdish | +| `cym_Latn` | Welsh | +| `dan_Latn` | Danish | +| `deu_Latn` | German | +| `div_Thaa` | Dhivehi | +| `dzo_Tibt` | Dzongkha | +| `ell_Grek` | Greek | +| `eng-GB_Latn` | English (Great Britain) | +| `eng-IN_Latn` | English (India) | +| `eng-US_Latn` | English (United States) | +| `eng_Latn` | English | +| `est_Latn` | Estonian | +| `eus_Latn` | Basque | +| `ewe_Latn` | Ewe | +| `fao_Latn` | Faroese | +| `fas_Arab` | Persian | +| `fij_Latn` | Fijian | +| `fil_Latn` | Filipino | +| `fin_Latn` | Finnish | +| `fra-CA_Latn` | French (Canada) | +| `fra_Latn` | French | +| `fuc_Latn` | Pulaar | +| `gle_Latn` | Irish | +| `glg_Latn` | Galician | +| `guj_Gujr` | Gujarati | +| `hau_Latn` | Hausa | +| `heb_Hebr` | Hebrew | +| `hin_Deva` | Hindi | +| `hmn_Latn` | Hmong | +| `hrv_Latn` | Croatian | +| `hun_Latn` | Hungarian | +| `hye_Armn` | Armenian | +| `ibo_Latn` | Igbo | +| `ind_Latn` | Indonesian | +| `isl_Latn` | Icelandic | +| `ita_Latn` | Italian | +| `jpn_Jpan` | Japanese | +| `kan_Knda` | Kannada | +| `kat_Geor` | Georgian | +| `kaz_Cyrl` | Kazakh | +| `khm_Khmr` | Khmer | +| `kin_Latn` | Kinyarwanda | +| `kir_Cyrl` | Kyrgyz | +| `kmr_Latn` | Northern Kurdish | +| `kor_Hang` | Korean | +| `lao_Laoo` | Lao | +| `lav_Latn` | Latvian | +| `lit_Latn` | Lithuanian | +| `ltz_Latn` | Luxembourgish | +| `mal_Mlym` | Malayalam | +| `mar_Deva` | Marathi | +| `mey_Arab` | Hassaniya Arabic | +| `mkd_Cyrl` | Macedonian | +| `mlg_Latn` | Malagasy | +| `mlt_Latn` | Maltese | +| `mon_Mong` | Mongolian | +| `mri_Latn` | Maori | +| `msa_Latn` | Malay | +| `mya_Mymr` | Burmese | +| `nde_Latn` | Ndebele | +| `nep_Deva` | Nepali | +| `nld_Latn` | Dutch | +| `nno_Latn` | Norwegian Nynorsk | +| `nob_Latn` | Norwegian Bokmål | +| `nso_Latn` | Northern Sotho | +| `nya_Latn` | Chichewa | +| `orm_Ethi` | Oromo | +| `pan_Guru` | Punjabi (Gurmukhi) | +| `pol_Latn` | Polish | +| `por-BR_Latn` | Portuguese (Brazil) | +| `por_Latn` | Portuguese | +| `prs_Arab` | Dari | +| `pus_Arab` | Pashto | +| `ron_Latn` | Romanian | +| `rus_Cyrl` | Russian | +| `shi_Arab` | Tachelhit | +| `sin_Sinh` | Sinhala | +| `slk_Latn` | Slovak | +| `slv_Latn` | Slovenian | +| `smo_Latn` | Samoan | +| `sna_Latn` | Shona | +| `snd_Arab` | Sindhi | +| `som_Latn` | Somali | +| `spa-MX_Latn` | Spanish (Mexico) | +| `spa_Latn` | Spanish | +| `sqi_Latn` | Albanian | +| `srp_Cyrl` | Serbian (Cyrillic) | +| `srp_Latn` | Serbian (Latin) | +| `ssw_Latn` | Swati | +| `swa_Latn` | Swahili | +| `swe_Latn` | Swedish | +| `tah_Latn` | Tahitian | +| `tam_Taml` | Tamil | +| `tat_Cyrl` | Tatar | +| `tel_Telu` | Telugu | +| `tgk_Cyrl` | Tajik | +| `tha_Thai` | Thai | +| `tir_Ethi` | Tigrinya | +| `ton_Latn` | Tongan | +| `tsn_Latn` | Tswana | +| `tuk_Latn` | Turkmen | +| `tur_Latn` | Turkish | +| `uig_Arab` | Uighur | +| `ukr_Cyrl` | Ukrainian | +| `urd_Arab` | Urdu | +| `uzb_Latn` | Uzbek | +| `ven_Latn` | Venda | +| `vie_Latn` | Vietnamese | +| `wol_Latn` | Wolof | +| `xho_Latn` | Xhosa | +| `yor_Latn` | Yoruba | +| `yue_Hant` | Cantonese | +| `zho_Hans` | Chinese (Simplified) | +| `zho_Hant` | Chinese (Traditional) | +| `zul_Latn` | Zulu | + + +### Citation Information +For the original NTREX-128 dataset, please cite: + +``` +@inproceedings{federmann-etal-2022-ntrex, + title = ""{NTREX}-128 {--} News Test References for {MT} Evaluation of 128 Languages"", + author = ""Federmann, Christian and Kocmi, Tom and Xin, Ying"", + booktitle = ""Proceedings of the First Workshop on Scaling Up Multilingual Evaluation"", + month = ""nov"", + year = ""2022"", + address = ""Online"", + publisher = ""Association for Computational Linguistics"", + url = ""https://aclanthology.org/2022.sumeval-1.4"", + pages = ""21--24"", +} +``` + +as well as the WMT 2019 paper that provided the English source data NTREX-128 is based on: + +``` +@inproceedings{barrault-etal-2019-findings, + title = ""Findings of the 2019 Conference on Machine Translation ({WMT}19)"", + author = {Barrault, Lo{\""\i}c and + Bojar, Ond{\v{r}}ej and + Costa-juss{\`a}, Marta R. and + Federmann, Christian and + Fishel, Mark and + Graham, Yvette and + Haddow, Barry and + Huck, Matthias and + Koehn, Philipp and + Malmasi, Shervin and + Monz, Christof and + M{\""u}ller, Mathias and + Pal, Santanu and + Post, Matt and + Zampieri, Marcos}, + editor = ""Bojar, Ond{\v{r}}ej and + Chatterjee, Rajen and + Federmann, Christian and + Fishel, Mark and + Graham, Yvette and + Haddow, Barry and + Huck, Matthias and + Yepes, Antonio Jimeno and + Koehn, Philipp and + Martins, Andr{\'e} and + Monz, Christof and + Negri, Matteo and + N{\'e}v{\'e}ol, Aur{\'e}lie and + Neves, Mariana and + Post, Matt and + Turchi, Marco and + Verspoor, Karin"", + booktitle = ""Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)"", + month = aug, + year = ""2019"", + address = ""Florence, Italy"", + publisher = ""Association for Computational Linguistics"", + url = ""https://aclanthology.org/W19-5301"", + doi = ""10.18653/v1/W19-5301"", + pages = ""1--61"", +} +```" +nayeon212/BLEnD,"{""license"": ""cc-by-sa-4.0"", ""task_categories"": [""question-answering""], ""language"": [""en"", ""zh"", ""es"", ""id"", ""ko"", ""el"", ""fa"", ""ar"", ""az"", ""su"", ""as"", ""ha"", ""am""], ""size_categories"": [""10K= 2.19.2 +pandas >= 2.1.4 +``` + +## Dataset +All the data samples for short-answer questions, including the human-annotated answers, can be found in the `data/` directory. +Specifically, the annotations from each country are included in the `annotations` split, and each country/region's data can be accessed by **[country codes](https://huggingface.co/datasets/nayeon212/BLEnD#countryregion-codes)**. +```Python +from datasets import load_dataset + +annotations = load_dataset(""nayeon212/BLEnD"",'annotations') + +# To access data from Assam: +assam_annotations = annotations['AS'] +``` +Each file includes a JSON variable with question IDs, questions in the local language and English, the human annotations both in the local language and English, and their respective vote counts as values. The same dataset for South Korea is shown below: +```JSON +[{ + ""ID"": ""Al-en-06"", + ""question"": ""대한민국 학교 급식에서 흔히 볼 수 있는 음식은 무엇인가요?"", + ""en_question"": ""What is a common school cafeteria food in your country?"", + ""annotations"": [ + { + ""answers"": [ + ""김치"" + ], + ""en_answers"": [ + ""kimchi"" + ], + ""count"": 4 + }, + { + ""answers"": [ + ""밥"", + ""쌀밥"", + ""쌀"" + ], + ""en_answers"": [ + ""rice"" + ], + ""count"": 3 + }, + ... + ], + ""idks"": { + ""idk"": 0, + ""no-answer"": 0, + ""not-applicable"": 0 + } +}], +``` + +The topics and source language for each question can be found in `short-answer-questions` split. +Questions for each country in their local languages and English can be accessed by **[country codes](https://huggingface.co/datasets/nayeon212/BLEnD#countryregion-codes)**. +Each CSV file question ID, topic, source language, question in English, and the local language (in the `Translation` column) for all questions. +```Python +from datasets import load_dataset + +questions = load_dataset(""nayeon212/BLEnD"",'short-answer-questions') + +# To access data from Assam: +assam_questions = questions['AS'] +``` +The current set of multiple choice questions and their answers can be found at the `multiple-choice-questions` split. +```Python +from datasets import load_dataset + +mcq = load_dataset(""nayeon212/BLEnD"",'multiple-choice-questions') +``` +### Country/Region Codes + | **Country/Region** | **Code** | **Language** | **Code**| + |:--------:|:--------------:|:------------:|:------------:| +| United States | US | English | en +| United Kingdom | GB | English |en +| China | CN | Chinese | zh +| Spain | ES | Spanish | es +| Mexico | MX |Spanish|es +| Indonesia | ID | Indonesian | id +| South Korea | KR | Korean | ko +| North Korea | KP | Korean |ko +| Greece | GR | Greek | el +| Iran | IR | Persian | fa +| Algeria | DZ | Arabic | ar +| Azerbaijan | AZ | Azerbaijani | az +| West Java | JB | Sundanese | su +| Assam | AS | Assamese | as +| Northern Nigeria | NG | Hausa | ha +| Ethiopia | ET | Amharic | am" +MarkrAI/KOpen-HQ-Hermes-2.5-60K,"{""language"": [""ko""], ""license"": ""mit"", ""task_categories"": [""question-answering"", ""text-generation""], ""dataset_info"": {""features"": [{""name"": ""input"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""output"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 93015065, ""num_examples"": 60061}], ""download_size"": 48634325, ""dataset_size"": 93015065}, ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""train"", ""path"": ""data/train-*""}]}]}","# MarkrAI/KOpen-HQ-Hermes-2.5-60K + +

+ +

+ +The **`KOpen-HQ-Hermes-2.5-60K`** dataset has been released! + +Anyone can use it under the MIT license, so feel free to take advantage of this **high-quality dataset**. + +In this dataset, we have focused on incorporating our knowledge rather than human effort as much as possible, so there may be some translation errors. + +Please keep this in mind when you cooking with it. + + +## Dataset Info + +- Creator: Markr AI +- Developer: Seungyoo Lee, Kyujin Han +- Data generation: + +We used the Near Dedup algorithm on the [Open Hermes dataset](https://huggingface.co/datasets/teknium/OpenHermes-2.5) to remove highly similar data(criteria: **Jaccard Sim, `0.8 >=`**) and then performed translation tasks using the DeepL API with 8 multiprocessing threads. + +Afterward, we used SOTA LLMs (GPT-4 Turbo, Gemini, Wizard LM, Llama 3.1 405B) to score the data with Alpaca form prompts. +We then evaluated the appropriateness of these prompts and extracted and published the data with high scores. + + + +## Dataset's purpose + +Our Markr AI research guild aims to make a small contribution to the Korean open-source community. + +Through this effort, we hope to invigorate the existing Korean LLM models and their ecosystem, fostering the growth of many excellent Korean language models within the expanding community. + +The license for this work is the MIT license, and you are welcome to use it. However, our small wish is that instead of merely using and benefiting from this culture of community activation and sharing, all members contribute to its development and, in doing so, help it evolve further. + +Lastly, if you start cooking using this dataset, please press the like button to show your support" +nlpai-lab/databricks-dolly-15k-ko,"{""license"": ""cc-by-sa-3.0"", ""task_categories"": [""question-answering"", ""summarization""], ""language"": [""ko""], ""size_categories"": [""10K + +### Some preprcoessing algorithms +- [spam_assassin.js](./spam_assassin.js), followed by [spam_assassin.py](./spam_assassin.py) +- [enron_spam.py](./enron_spam.py) + +
+ +### Data composition +![Spam vs Non-spam (Ham)](https://i.imgur.com/p5ytV4q.png) + +
+ +### Description +To make the text format between sms messages and emails consistent, email subjects and content are separated by two newlines: + +```python +text = email.subject + ""\n\n"" + email.content +``` + +
+ +### Suggestions +- If you plan to train a model based on this dataset alone, I recommend adding **some** rows with `is_toxic=0` from `FredZhang7/toxi-text-3M`. Make sure the rows aren't spam. + +
+ +### Other Sources +- https://huggingface.co/datasets/sms_spam +- https://github.com/MWiechmann/enron_spam_data +- https://github.com/stdlib-js/datasets-spam-assassin +- https://repository.ortolang.fr/api/content/comere/v3.3/cmr-simuligne.html" +simon3000/starrail-voice,"{""language"": [""zh"", ""en"", ""ja"", ""ko""], ""task_categories"": [""audio-classification"", ""automatic-speech-recognition"", ""text-to-speech""], ""pretty_name"": ""StarRail Voice"", ""dataset_info"": {""features"": [{""name"": ""audio"", ""dtype"": ""audio""}, {""name"": ""ingame_filename"", ""dtype"": ""string""}, {""name"": ""transcription"", ""dtype"": ""string""}, {""name"": ""language"", ""dtype"": ""string""}, {""name"": ""speaker"", ""dtype"": ""string""}, {""name"": ""voice_type"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 124647844822.266, ""num_examples"": 185511}], ""download_size"": 88624726158, ""dataset_size"": 124647844822.266}, ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""train"", ""path"": ""data/train-*""}]}]}","# StarRail Voice + +StarRail Voice is a dataset of voice lines from the popular game [Honkai: Star Rail](https://hsr.hoyoverse.com/). + +Hugging Face 🤗 [StarRail-Voice](https://huggingface.co/datasets/simon3000/starrail-voice) + + +Last update at `2024-08-30` + +`185511` wavs + +`49325` without speaker (27%) + +`49409` without transcription (27%) + +`41142` without inGameFilename (22%) + + +## Dataset Details + +### Dataset Description + +The dataset contains voice lines from the game's characters in multiple languages, including Chinese, English, Japanese, and Korean. + +The voice lines are spoken by the characters in the game and cover a wide range of topics, including greetings, combat, and story dialogue. + +- **Language(s) (NLP):** Chinese, English, Japanese, Korean + +## Dataset Creation + +### Source Data + +The data was obtained by unpacking the [Honkai: Star Rail](https://hsr.hoyoverse.com/) game. + +#### Data Collection and Processing + +Please refer to [StarRail-Voice](https://github.com/simon300000/starrail-voice) and [bnnm/wwiser-utils#15](https://github.com/bnnm/wwiser-utils/pull/15#issuecomment-1962182022) for more information on how the data was processed. + +#### Who are the source data producers? + +The source data producers are the developers of the game, HoYoverse. + +### Annotations + +The dataset contains official annotations from the game, including language, speaker name, and transcription. + +## Bias, Risks, and Limitations + +Annotations are incomplete. Some voice lines are missing speaker names and transcriptions. + +### Recommendations + +Users should be made aware of the risks, biases and limitations of the dataset. + +Speaker names can be partially inferred from the ingame filenames. + +## Licensing Information + +Copyright © COGNOSPHERE. All Rights Reserved. + +## More Information + +I can upload wav files on demand." +hac541309/open-lid-dataset,"{""language"": [""en"", ""ko"", ""fr"", ""aa"", ""hi""], ""license"": ""gpl-3.0"", ""size_categories"": [""100M>> from datasets import load_dataset + +>>> dataset = load_dataset(""Bingsu/KSS_Dataset"") +>>> dataset[""train""].features +{'audio': Audio(sampling_rate=44100, mono=True, decode=True, id=None), + 'original_script': Value(dtype='string', id=None), + 'expanded_script': Value(dtype='string', id=None), + 'decomposed_script': Value(dtype='string', id=None), + 'duration': Value(dtype='float32', id=None), + 'english_translation': Value(dtype='string', id=None)} +``` +```python +>>> dataset[""train""][0] +{'audio': {'path': None, + 'array': array([ 0.00000000e+00, 3.05175781e-05, -4.57763672e-05, ..., + 0.00000000e+00, -3.05175781e-05, -3.05175781e-05]), + 'sampling_rate': 44100}, + 'original_script': '그는 괜찮은 척하려고 애쓰는 것 같았다.', + 'expanded_script': '그는 괜찮은 척하려고 애쓰는 것 같았다.', + 'decomposed_script': '그는 괜찮은 척하려고 애쓰는 것 같았다.', + 'duration': 3.5, + 'english_translation': 'He seemed to be pretending to be okay.'} +``` +### Data Splits + +| | train | +|---------------|------:| +| # of examples | 12853 |" +afaji/cvqa,"{""language"": [""id"", ""su"", ""ja"", ""jv"", ""min"", ""br"", ""ga"", ""es"", ""pt"", ""no"", ""mn"", ""ms"", ""zh"", ""ko"", ""ta"", ""ben"", ""si"", ""bg"", ""ro"", ""ru"", ""am"", ""orm"", ""ar"", ""ig"", ""hi"", ""mr""], ""size_categories"": [""10K, + 'ID': '5919991144272485961_0', + 'Subset': ""('Japanese', 'Japan')"", + 'Question': '写真に写っているキャラクターの名前は？ ', + 'Translated Question': 'What is the name of the object in the picture? ', + 'Options': ['コスモ星丸', 'ミャクミャク', ' フリービー ', 'ハイバオ'], + 'Translated Options': ['Cosmo Hoshimaru','MYAKU-MYAKU','Freebie ','Haibao'], + 'Label': -1, + 'Category': 'Objects / materials / clothing', + 'Image Type': 'Self', + 'Image Source': 'Self-open', + 'License': 'CC BY-SA' +} +``` + +Data Fields + +The data fields are: +- `image`: The image referenced by the question. +- `ID`: A unique ID for the given sample. +- `Subset`: A Language-Country pair +- `Question`: The question elicited in the local language. +- `Translated Question`: The question elicited in the English language. +- `Options`: A list of possible answers to the question in the Local Language. +- `Translated Options`: A list of possible answers to the question in the English Language. +- `Label`: Will always be -1. Please refer to our leaderboard to get your performance. +- `Category`: A specific category for the given sample. +- `Image Type`: `Self` or `External`, meaning if the image is self-taken from the annotator or comes from the internet. +- `Image Source`: If the image type is Self, this can be `Self-open` or `Self-research_only`, meaning that the image can be used for commercial purposes or only for research purposes. If the image type is External, this will be the link to the external source. +- `License`: The corresponding license for the image. + + +# Dataset Creation + +## Source Data + +The images in CVQA can either be based on existing external images or from the contributor's own images. You can see this information from the 'Image Type' and 'Image Source' columns. Images based on external sources will retain their original licensing, whereas images from contributors will be licensed based on each contributor's decision. + +All the questions are hand-crafted by annotators. + +## Data Annotation + +Data creation follows two general steps: question formulation and validation. +During question formulation, annotators are asked to write a question, with one correct answer and three distractors. +Questions must be culturally nuanced and relevant to the image. Annotators are asked to mask sensitive information and text that can easily give away the answers. +During data validation, another annotator is asked to check and validate whether the images and questions adhere to the guidelines. + +You can learn more about our annotation protocol and guidelines in our paper. + +## Annotators + +Annotators needed to be fluent speakers of the language in question and be accustomed to the cultures of the locations for which they provided data. Our annotators are predominantly native speakers, with around 89% residing in the respective country for over 16 years. + +## Licensing Information + +Note that each question has its own license. All data here is free to use for research purposes, but not every entry is permissible for commercial use. + +---" +lcw99/oscar-ko-only,"{""language"": [""ko""]}",# oscar dataset only korean +heegyu/kowiki-sentences,"{""license"": ""cc-by-sa-3.0"", ""language"": [""ko""], ""language_creators"": [""other""], ""multilinguality"": [""monolingual""], ""size_categories"": [""1MFor more information, please refer to the paper [K-HATERS](https://arxiv.org/abs/2310.15439) published at EMNLP 2023 Findings. + +### Supported tasks +- Hate speech detection + - Multi class classification (labels: normal, offensive, L1_hate, L2_hate) + - Binary classifiction (labels: normal, toxic(offensive, L1_hate, L2_hate)) + - Rationale prediction (offensiveness, target rationale) + +### Data describtion +``` +data['train'][42] +{'text': '군대도 안간 놈 이 주둥아리 는 씽씽하네..보수 놈 들..군대는 안가고 애국이냐..#@이름#,#@이름#,', + 'label': 'L1_hate', + 'target_label': ['political'], + 'offensiveness_rationale': [[7, 8], [11, 15], [27, 28]], + 'target_rationale': [[24, 26], [46, 51], [52, 57]]} +``` +- Abusive language categories (**label**) + - L2_hate: Comments with explicit forms of hate expressions toward one of the groups of protected attributes (e.g., gender, age, race, ...) + - L1_hate: Comments with more implicit forms of hate expressions + - Offensive: Comments that express offensiveness but not toward a protected attribute group + - Normal: The rest comments +- Multi-label target categories (**target_label**): list of offensiveness targets. A comment can have zero or multiple targets. + - List of target categories: gender, age, race, religion, politics, job, disability, individuals, and others. +- Annotators' rationales for the strength of ratings (**offensiveness_rationale**): lists providing annotators' rationales for the strength of ratings. The list includes the start and end indices of highlight spans. +- Annotators' rationales for the target of offensiveness (**target_rationale**) + +### Dataset split +We provide the dataset in the form of splits as 172,158 (for train), 10,000 (for validation), and 10,000 (for test). Label ratio was preseved (stratified split). + +### Labeling guidelines +Labeling guidelines are available as a part of SELECTSTAR open datasets (in Korean). [link](https://open.selectstar.ai/ko/?page_id=5948) + + +
+ + +# 📜 Data statement +We present the data statement for responsible usage [(Bender and Friedman, 2018)](https://aclanthology.org/Q18-1041/). + +### Curation Rationale +We collected the raw data from the news aggregator of Naver, the largest news portal in Korea. We targeted news articles published in the society, world news, and politics sections because discussions are active in the hard news. + +### Language Variety +Our dataset consists of the news comments in Korean (ko-KR). + +### Speaker Demographic +The user demographic is not available. However, considering that the portal site has the largest share of Korean, it can be assumed that speakers are mostly Korean. + +### Annotator Demographic +A total of 405 workers participated in an annotation. 21 workers are 10s, 222 workers are 20s, 116 workers are 30s, 35 workers are 40s, 9 workers are 50s, and 2 workers are 60s. + +### Speech Situation +News article in the hard news section deals with controversial events, so there are more likely to exist hate comments or toxicity comments. The target articles were published between July 2021 and August 2021. During that period, the most controversial events were the South Korean presidential election, the Tokyo Olympics, COVID-19, and the Restoration of Taliban Control, etc. + +### Text Characteristics +It includes hatred words limited to Korea, such as hatred of certain political orientations and certain groups. For example, '대깨문' (a word that hates former Korean president Moon's supporter), and '꼴페미' (a word that hates feminists) + +
+ +# 🤝 License & Contributors +### Licensing information +This dataset is shared under CC-BY 4.0. +
According to this license, you are free to use the dataset as long as you provide appropriate attribution (e.g., citing our paper). + +### Citation information +``` +@article{park2023haters, + title={K-HATERS: A Hate Speech Detection Corpus in Korean with Target-Specific Ratings}, + author={Park, Chaewon and Kim, Suhwan and Park, Kyubyong and Park, Kunwoo}, + journal={Findings of the EMNLP 2023}, + year={2023} +} +``` + +### Contributions +- Chaewon Park +- Suhwan Kim (TUNiB) +- Kyubyong Park (TUNiB) +- Kunwoo Park + +#-->" +sentence-transformers/parallel-sentences-global-voices,"{""language"": [""en"", ""multilingual"", ""ar"", ""bg"", ""ca"", ""cs"", ""da"", ""de"", ""el"", ""es"", ""fa"", ""fr"", ""he"", ""hi"", ""hu"", ""id"", ""it"", ""ko"", ""mk"", ""my"", ""nl"", ""pl"", ""pt"", ""ro"", ""ru"", ""sq"", ""sr"", ""sv"", ""tr"", ""ur""], ""size_categories"": [""1M + +## Dataset Description + +- **Homepage:** [SIL AI](https://ai.sil.org/) +- **Point of Contact:** [SIL AI email](mailto:idx_aqua@sil.org) +- **Source Data:** [Bloom Library](https://bloomlibrary.org/) + +![logo for Bloom Library](https://bloom-vist.s3.amazonaws.com/bloom_logo.png) ![sil-ai logo](https://s3.amazonaws.com/moonup/production/uploads/1661440873726-6108057a823007eaf0c7bd10.png) + +## Dataset Summary + +**Bloom** is free, open-source software and an associated website [Bloom Library](https://bloomlibrary.org/), app, and services developed by [SIL International](https://www.sil.org/). Bloom’s primary goal is to equip non-dominant language communities and their members to create the literature they want for their community and children. Bloom also serves organizations that help such communities develop literature and education or other aspects of community development. + +This version of the Bloom Library data is developed specifically for the visual story telling (or VIST) task. It includes data from 364 languages across 31 language families. There is a mean of 32 stories and median of 2 stories per language. + +**Note**: If you speak one of these languages and can help provide feedback or corrections, please let us know! + +**Note**: Although this data was used in the training of the [BLOOM model](https://huggingface.co/bigscience/bloom), this dataset only represents a small portion of the data used to train that model. Data from ""Bloom Library"" was combined with a large number of other datasets to train that model. ""Bloom Library"" is a project that existed prior to the BLOOM model, and is something separate. All that to say... We were using the ""Bloom"" name before it was cool. 😉 + +## Languages + +Of the 500+ languages listed at BloomLibrary.org, there are 363 languages available in this dataset. Here are the corresponding ISO 639-3 codes: + +aaa, abc, ada, adq, aeu, afr, agq, ags, ahk, aia, ajz, aka, ame, amh, amp, amu, ann, aph, awa, awb, azn, azo, bag, bam, baw, bax, bbk, bcc, bce, bec, bef, ben, bfd, bfm, bfn, bgf, bho, bhs, bis, bjn, bjr, bkc, bkh, bkm, bkx, bob, bod, boz, bqm, bra, brb, bri, brv, bss, bud, buo, bwt, bwx, bxa, bya, bze, bzi, cak, cbr, ceb, cgc, chd, chp, cim, clo, cmn, cmo, csw, cuh, cuv, dag, ddg, ded, deu, dig, dje, dmg, dnw, dtp, dtr, dty, dug, eee, ekm, enb, enc, eng, ewo, fas, fil, fli, fon, fra, fub, fuh, gal, gbj, gou, gsw, guc, guj, guz, gwc, hao, hat, hau, hbb, hig, hil, hin, hla, hna, hre, hro, idt, ilo, ind, ino, isu, ita, jgo, jmx, jpn, jra, kak, kam, kan, kau, kbq, kbx, kby, kek, ken, khb, khm, kik, kin, kir, kjb, kmg, kmr, kms, kmu, kor, kqr, krr, ksw, kur, kvt, kwd, kwu, kwx, kxp, kyq, laj, lan, lao, lbr, lfa, lgg, lgr, lhm, lhu, lkb, llg, lmp, lns, loh, lsi, lts, lug, luy, lwl, mai, mal, mam, mar, mdr, mfh, mfj, mgg, mgm, mgo, mgq, mhx, miy, mkz, mle, mlk, mlw, mmu, mne, mnf, mnw, mot, mqj, mrn, mry, msb, muv, mve, mxu, mya, myk, myx, mzm, nas, nco, nep, new, nge, ngn, nhx, njy, nla, nld, nlv, nod, nsk, nsn, nso, nst, nuj, nwe, nwi, nxa, nxl, nya, nyo, nyu, nza, odk, oji, oki, omw, ori, ozm, pae, pag, pan, pbt, pce, pcg, pdu, pea, pex, pis, pkb, pmf, pnz, por, psp, pwg, qub, quc, quf, quz, qve, qvh, qvm, qvo, qxh, rel, rnl, ron, roo, rue, rug, rus, san, saq, sat, sdk, sea, sgd, shn, sml, snk, snl, som, sot, sox, spa, sps, ssn, stk, swa, swh, sxb, syw, taj, tam, tbj, tdb, tdg, tdt, teo, tet, tgk, tha, the, thk, thl, thy, tio, tkd, tnl, tnn, tnp, tnt, tod, tom, tpi, tpl, tpu, tsb, tsn, tso, tuv, tuz, tvs, udg, unr, urd, uzb, ven, vie, vif, war, wbm, wbr, wms, wni, wnk, wtk, xho, xkg, xmd, xmg, xmm, xog, xty, yas, yav, ybb, ybh, ybi, ydd, yea, yet, yid, yin, ymp, zaw, zho, zlm, zuh, zul + +## Dataset Statistics +Some of the languages included in the dataset just include 1 or a couple of ""stories."" For those with higher numbers of available stories we include the following numbers of stories: + +| ISO639-3 Code | Stories | Image-Caption Pairs | +|:-----------|----------:|----------------------:| +| ahk | 55 | 493 | +| awa | 163 | 1200 | +| ben | 220 | 1938 | +| bho | 172 | 1163 | +| bis | 21 | 183 | +| brb | 22 | 330 | +| bzi | 66 | 497 | +| cak | 50 | 694 | +| ceb | 394 | 2806 | +| cgc | 182 | 1473 | +| deu | 22 | 250 | +| dty | 172 | 1310 | +| eng | 2187 | 24338 | +| fas | 128 | 620 | +| fil | 34 | 366 | +| fra | 315 | 4350 | +| hat | 224 | 1881 | +| hau | 229 | 1594 | +| ind | 232 | 1866 | +| jra | 56 | 575 | +| kak | 195 | 1416 | +| kek | 21 | 419 | +| khb | 31 | 167 | +| khm | 26 | 246 | +| kir | 278 | 2866 | +| kjb | 63 | 584 | +| kor | 129 | 2732 | +| krr | 29 | 362 | +| lsi | 22 | 173 | +| mai | 177 | 1186 | +| mam | 118 | 1058 | +| mhx | 51 | 544 | +| myk | 22 | 214 | +| nep | 194 | 1464 | +| new | 177 | 1225 | +| pbt | 203 | 979 | +| por | 148 | 2939 | +| quc | 99 | 817 | +| rus | 271 | 2977 | +| snk | 21 | 210 | +| spa | 444 | 5201 | +| swh | 34 | 387 | +| tdg | 31 | 231 | +| tha | 275 | 2929 | +| thl | 185 | 1464 | +| tpi | 137 | 1528 | +| tpu | 28 | 513 | +| zho | 42 | 339 | + +## Dataset Structure + +### Data Instances + +The examples look like this for Hindi: + +``` +from datasets import load_dataset + +# Specify the language code. +dataset = load_dataset(""sil-ai/bloom-vist"", 'hin') + +# An individual samples consists of stories in the specified language code. +# To see a story: +print(dataset['train'][0]['story']) +``` + +This would produce an output: + +``` +{'image_id': ['4e9bdde5-996d-4a98-ac1c-d80fb6349314', + '614e4d51-bbdb-4538-98d3-f603c12dccd0', + '970d60bf-2acb-44ac-8ffb-5aa3f7989630', + 'd4ad1199-863e-4929-a377-93276fe5caa8', + '0d9ad694-995a-433d-af4e-6f40ddfa208a', + '811176eb-c9f3-4226-8af5-e6c4e524c494', + '83180da7-4ba8-4104-a0d9-49aa2ef48f7a'], + 'image_url': ['https://bloom-vist.s3.amazonaws.com/Saboo+and+Jojo/M_PB_2_-saboo-and-jojo_Page_03_Image_00011.png', + 'https://bloom-vist.s3.amazonaws.com/Saboo+and+Jojo/M_PB_2_-saboo-and-jojo_Page_04_Image_0001.png', + 'https://bloom-vist.s3.amazonaws.com/Saboo+and+Jojo/M_PB_2_-saboo-and-jojo_Page_05_Image_0001.png', + 'https://bloom-vist.s3.amazonaws.com/Saboo+and+Jojo/M_PB_2_-saboo-and-jojo_Page_06_Image_0001.png', + 'https://bloom-vist.s3.amazonaws.com/Saboo+and+Jojo/M_PB_2_-saboo-and-jojo_Page_07_Image_0001.png', + 'https://bloom-vist.s3.amazonaws.com/Saboo+and+Jojo/M_PB_2_-saboo-and-jojo_Page_07_Image_00011.png', + 'https://bloom-vist.s3.amazonaws.com/Saboo+and+Jojo/M_PB_2_-saboo-and-jojo_Page_09_Image_0001.png'], + 'story_index': [0, 1, 2, 3, 4, 5, 6], + 'story_id': ['cc34c1c7-c086-491b-8e6a-65572e1efdb6', + 'cc34c1c7-c086-491b-8e6a-65572e1efdb6', + 'cc34c1c7-c086-491b-8e6a-65572e1efdb6', + 'cc34c1c7-c086-491b-8e6a-65572e1efdb6', + 'cc34c1c7-c086-491b-8e6a-65572e1efdb6', + 'cc34c1c7-c086-491b-8e6a-65572e1efdb6', + 'cc34c1c7-c086-491b-8e6a-65572e1efdb6'], + 'text': ['साबू ने एक कंकड़ को ठोकर मारी। कंकड़ लुढ़कता हुआ एक पेड़ के पास पहुँचा। पेड़ के तने पर मुलायम बाल थे। साबू ने छुए और ऊपर देखा, ऊपर, ऊपर और उससे भी ऊपर...दो आँखें नीचे देख रही थीं।', + '“हेलो, तुम कौन हो?” साबू को बड़ा अचम्भा हुआ।“हेलो, मैं जिराफ़ हूँ। मेरा नाम है जोजो। \xa0मैं तुम्हारे साथ खेल सकता हूँ। मेरी पीठ पर चढ़ जाओ, मैं तुम्हें घुमा के लाता हूँ।”', + 'साबू जोजो की पीठ पर चढ़ गया और वे सड़क पर चल निकले। फिर पहाड़ी पर और शहर के बीचों बीच।\nसाबू खुशी से चिल्लाया, “जोजो दाएँ मुड़ो,\n बाएँ मुड़ो और फिर दाएँ।” अब वे उसकी दोस्त मुन्नी के घर पहुँच गये।', + 'आज मुन्नी का जन्मदिन था। साबू को जोजो पर सवारी करते देख बच्चों ने ताली बजायी।\xa0\n जोजो ने गुब्बारे लटकाने में आन्टी की मदद करी क्योंकि वह इतना... लम्बा था।\xa0\n कितना आसान था!', + 'जोजो ने सब बच्चों को सवारी कराई।\n उनके साथ बॉल भी खेली। बड़े मज़े की पार्टी थी।सब ने गाया, “हैप्पी बर्थ डे टु यू ।”\n आन्टी ने मेज़ पर समोसे, गुलाब जामुन और आइसक्रीम सजाई।', + 'जोजो को आइसक्रीम बहुत पसन्द आई। अंकल उसके लिये एक बाल्टी भर के आइसक्रीम लाये। जोजो ने पूरी बाल्टी ख़त्म कर दी। \xa0अब घर जाने का समय हो गया।\n\nसब ने कहा, “बाय बाय जोजो, बाय बाय साबू।” साबू और जोजो घर लौटे।', + '']} +``` + +### Data Fields + +The metadata fields below are available. In terms of licenses, all stories included in the current release are released under a Creative Commons license (even if the individual story metadata fields are missing). + +- **id**: id of the sample +- **title**: title of the book, e.g. ""Going to Buy a Book"". +- **license**: specific license used, e.g. ""cc-by-sa"" for ""Creative Commons, by attribution, share-alike"". +- **album_id**: an ID value corresponding to the set of images corresponding to the given story +- **story**: the sequenced story data including lists of image IDs, image URLs, and corresponding text + + +### Data Splits + +Currently all languages include a train split only. In the future, we will be creating manual splits of the data. + +## Changelog +- **6 December 2022** - dataset is made public" +ziozzang/EverythingLM-data-V2-Ko,"{""license"": ""mit"", ""language"": [""ko""]}","# Translated into Korean with DeepL +All Texts are translated with DeepL. (Machine Translated.) +- Issue: some data items are missing, cause of DeepL plan and processing method. I use very cheap plan and all datas are merged into single file and splitted by few code and hand. + - This is sample/test processing of data set creation with DeepL. +- Original Dataset: totally-not-an-llm/EverythingLM-data-V2 + + +# EverythingLM V2 Dataset + +**EverythingLM V2** is a diverse instruct dataset consisting of 1k of human-assistant conversations. These sets were generated using principles from both evol-instruct and Orca. The dataset encompasses a wide array of topics and interactions. + +### Differences for V1: + +- All data in V2 is generated by GPT4 +- Higher quality dataset generation pipeline: + - More humalike seed prompts + - Fixed some bugs in the script + - More diverse creative writing + - More diverse seed prompts in general + - Attempt not to overfit the model on complex instructions by occasionally skipping evol + +### Cost: +Reproducing this dataset would cost roughly $40. + +### Instruction Categories: + +- Reasoning +- Creative Writing +- General Knowledge +- Brainstorming +- Search Query +- Coding +- Basic Instruct + +We also leverage various system prompts for evol-instruct and for responding to prompts. +This dataset has also been filtered to remove OpenAI alignment. + +### How it stands out: + +- Long, detailed outputs +- Humanlike creativity +- CoT reasoning +- Complex & challenging tasks + +### Plans: + +- Train Llama 7b & 13b models (13b model V1 trained) +- Train Llama 70b QLoRA +- Generate V2 of the dataset, with more categories and GPT-4 (DONE) ✓ + +Included in this repo is the script to generate the dataset." +voice-is-cool/voxtube,{}, +xhluca/publichealth-qa,"{""license"": ""cc-by-nc-sa-3.0"", ""task_categories"": [""question-answering""], ""language"": [""ar"", ""en"", ""es"", ""fr"", ""ko"", ""ru"", ""vi"", ""zh""], ""size_categories"": [""n<1K""], ""configs"": [{""config_name"": ""english"", ""default"": true, ""data_files"": [{""split"": ""test"", ""path"": ""data/english.csv""}]}, {""config_name"": ""arabic"", ""data_files"": [{""split"": ""test"", ""path"": ""data/arabic.csv""}]}, {""config_name"": ""chinese"", ""data_files"": [{""split"": ""test"", ""path"": ""data/chinese.csv""}]}, {""config_name"": ""french"", ""data_files"": [{""split"": ""test"", ""path"": ""data/french.csv""}]}, {""config_name"": ""korean"", ""data_files"": [{""split"": ""test"", ""path"": ""data/korean.csv""}]}, {""config_name"": ""korean"", ""data_files"": [{""split"": ""test"", ""path"": ""data/korean.csv""}]}, {""config_name"": ""russian"", ""data_files"": [{""split"": ""test"", ""path"": ""data/russian.csv""}]}, {""config_name"": ""spanish"", ""data_files"": [{""split"": ""test"", ""path"": ""data/spanish.csv""}]}, {""config_name"": ""vietnamese"", ""data_files"": [{""split"": ""test"", ""path"": ""data/vietnamese.csv""}]}]}","# Usage + +```python +import datasets + +langs = ['arabic', 'chinese', 'english', 'french', 'korean', 'russian', 'spanish', 'vietnamese'] +data = datasets.load_dataset('xhluca/publichealth-qa', split='test', name=langs[0]) +``` + +# About + +This dataset contains question and answer pairs sourced from Q&A pages and FAQs from CDC and WHO pertaining to COVID-19. They were produced and collected between 2019-12 and 2020-04. They were originally published as an [aggregated Kaggle dataset](https://www.kaggle.com/xhlulu/covidqa). + +# License + +CDC data is licensed under [CC-BY 3.0](https://web.archive.org/web/20201017141031/https://www2a.cdc.gov/cdcup/library/other/policy.htm) and WHO is licensed under [cc-by-nc-sa-3.0](https://web.archive.org/web/20210701063743/https://www.who.int/about/policies/publishing/copyright). + + +# Source + +This data was originally included in the [COVID-QA dataset](https://www.kaggle.com/datasets/xhlulu/covidqa), where it was known as the multilingual split. The files in this updated repository were generated using the [publichealth-qa repository](https://github.com/xhluca/publichealth-qa)." +traintogpb/aihub-koen-translation-integrated-small-100k,"{""language"": [""en"", ""ko""], ""size_categories"": [""100K Post-processing 작업 내용 + +## OpenOrca-Ko +Repo: [OpenOrca-Ko](https://huggingface.co/datasets/kyujinpy/OpenOrca-KO) + +1. NIV // 1571개 +2. FLAN // 9434개 +3. T0 // 6351개 +4. CoT // 2117개 +5. KoCoT // 2159개 +> Dataset 구성 + +## Translation +Using DeepL Pro API. Thanks. + +--- +>Below is original dataset card + +## Table of Contents +- [Dataset Summary](#dataset-summary) +- [Dataset Attribution](#dataset-attribution) +- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) +- [Languages](#languages) +- [Dataset Structure](#dataset-structure) + - [Data Instances](#data-instances) + - [Data Fields](#data-fields) + - [Data Splits](#data-splits) +- [Dataset Creation](#dataset-creation) + - [Curation Rationale](#curation-rationale) + - [Source Data](#source-data) +- [Dataset Use](#dataset-use) + - [Use Cases](#use-cases) + - [Usage Caveats](#usage-caveats) + - [Getting Started](#getting-started) + + +

🐋 The OpenOrca Dataset! 🐋

+ +![OpenOrca Logo](https://huggingface.co/datasets/Open-Orca/OpenOrca/resolve/main/OpenOrcaLogo.png ""OpenOrca Logo"") + + + +We are thrilled to announce the release of the OpenOrca dataset! +This rich collection of augmented FLAN data aligns, as best as possible, with the distributions outlined in the [Orca paper](https://arxiv.org/abs/2306.02707). +It has been instrumental in generating high-performing model checkpoints and serves as a valuable resource for all NLP researchers and developers! + +# Official Models + +## OpenOrca-Platypus2-13B + +Our [latest release](https://huggingface.co/Open-Orca/OpenOrca-Platypus2-13B), the first 13B model to score higher than LLaMA1-65B on the HuggingFace Leaderboard! +Released in partnership with Platypus. + +## LlongOrca 7B & 13B + +* Our [first 7B release](https://huggingface.co/Open-Orca/LlongOrca-7B-16k), trained on top of LLongMA2 to achieve 16,000 tokens context. #1 long context 7B model at release time, with >99% of the overall #1 model's performance. +* [LlongOrca-13B-16k](https://huggingface.co/Open-Orca/LlongOrca-13B-16k), trained on top of LLongMA2. #1 long context 13B model at release time, with >97% of the overall #1 model's performance. + +## OpenOrcaxOpenChat-Preview2-13B + +Our [second model](https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-13B), highlighting that we've surpassed the performance reported in the Orca paper. +Was #1 at release time, now surpassed by our own OpenOrca-Platypus2-13B. +Released in partnership with OpenChat. + +## OpenOrca-Preview1-13B + +[OpenOrca-Preview1-13B](https://huggingface.co/Open-Orca/OpenOrca-Preview1-13B) +This model was trained in less than a day, for <$200, with <10% of our data. +At release, it beat the current state of the art models on BigBench-Hard and AGIEval. Achieves ~60% of the improvements reported in the Orca paper. + + + +# Dataset Summary + +The OpenOrca dataset is a collection of augmented [FLAN Collection data](https://arxiv.org/abs/2301.13688). +Currently ~1M GPT-4 completions, and ~3.2M GPT-3.5 completions. +It is tabularized in alignment with the distributions presented in the ORCA paper and currently represents a partial completion of the full intended dataset, with ongoing generation to expand its scope. +The data is primarily used for training and evaluation in the field of natural language processing. + + + +# Dataset Attribution + +We would like to give special recognition to the following contributors for their significant efforts and dedication: + + + Teknium + WingLian/Caseus + Eric Hartford + NanoBit + Pankaj + Winddude + Rohan + + http://AlignmentLab.ai: + Autometa + Entropi + AtlasUnified + NeverendingToast + NanoBit + WingLian/Caseus + +Also of course, as always, TheBloke, for being the backbone of the whole community. + +Many thanks to NanoBit and Caseus, makers of [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl), for lending us their expertise on the platform that developed and trained manticore, minotaur, and many others! + +We are welcoming sponsors or collaborators to help us build these models to the scale they deserve. Please reach out via our socials: +http://Alignmentlab.ai https://discord.gg/n9hXaBPWxx + +Want to visualize our full dataset? Check out our [Nomic Atlas Map](https://atlas.nomic.ai/map/c1b88b47-2d9b-47e0-9002-b80766792582/2560fd25-52fe-42f1-a58f-ff5eccc890d2). + [](https://atlas.nomic.ai/map/c1b88b47-2d9b-47e0-9002-b80766792582/2560fd25-52fe-42f1-a58f-ff5eccc890d2) + + + + +# Supported Tasks and Leaderboards + +This dataset supports a range of tasks including language modeling, text generation, and text augmentation. +It has been instrumental in the generation of multiple high-performing model checkpoints which have exhibited exceptional performance in our unit testing. +Further information on leaderboards will be updated as they become available. + + + +# Languages + +The language of the data is primarily English. + + + +# Dataset Structure + + + +## Data Instances + +A data instance in this dataset represents entries from the FLAN collection which have been augmented by submitting the listed question to either GPT-4 or GPT-3.5. +The response is then entered into the response field. + + + +## Data Fields + +The fields are: +1) 'id', a unique numbered identifier which includes one of 'niv', 't0', 'cot', or 'flan' to represent which source FLAN Collection submix the 'question' is sourced from. +2) 'system_prompt', representing the System Prompt presented to the GPT-3.5 or GPT-4 API for the datapoint +3) 'question', representing a question entry as provided by the FLAN Collection +4) 'response', a response to that question received from a query to either GPT-3.5 or GPT-4. + + + +## Data Splits + +The data is unsplit. + + + +# Dataset Creation + + + +## Curation Rationale + +The dataset was created to provide a source of augmented text data for researchers and developers. +The datapoints are intended primarily to provide an enhancement of the core FLAN Collection data which relies upon the detailed step by step reasoning capabilities of GPT-3.5 and GPT-4. +This ""reasoning trace"" augmentation has demonstrated exceptional results, allowing a LLaMA-13B model trained with this data to rival or beat GPT-3.5 on broad sets of hard reasoning tasks which all models below 100B parameters had previously performed dramatically worse on. + + + +## Source Data + +The data is generated using techniques in alignment with the distributions outlined in the Orca paper, except as noted below: + +1) There is not enough CoT data in the FLAN Collection to generate 150K zero-shot entries, as the paper purports to use. + We suspect this portion was either undocumented or misrepresented. We have used the ~75K points available. +2) We used the pre-generated FLAN Collection datasets hosted on HuggingFace under conceptofmind, e.g. [conceptofmind/flan2021](https://huggingface.co/datasets/conceptofmind/flan2021_submix_original). + These are referenced by the [official FLAN Collection repo](https://github.com/google-research/FLAN/tree/main/flan/v2) as the preferred data source. + However, these are a subset of the full FLAN Collection data, and have less than the required entries for the flan2021 and t0 submixes, by ~1.25M and 200k respectively. + +Combined, this gave us ~1.5M fewer datapoints than in the original Orca paper. Completing the set is an ongoing work. + + + +# Dataset Use + + + +## Use Cases + +The dataset can be used for tasks related to language understanding, natural language processing, machine learning model training, and model performance evaluation. + + + +## Usage Caveats + +Given that this is a work-in-progress dataset, it is recommended to regularly check for updates and improvements. +Further, the data should be used in accordance with the guidelines and recommendations outlined in the Orca paper. + + + +## Getting Started + +This dataset is organized such that it can be naively loaded via Hugging Face datasets library. +We recommend using streaming due to the large size of the files. +Regular updates and data generation progress can be monitored through the OpenOrca repository on Hugging Face. + + +# Citation + +```bibtex +@misc{OpenOrca, + title = {OpenOrca: An Open Dataset of GPT Augmented FLAN Reasoning Traces}, + author = {Wing Lian and Bleys Goodson and Eugene Pentland and Austin Cook and Chanvichet Vong and ""Teknium""}, + year = {2023}, + publisher = {HuggingFace}, + journal = {HuggingFace repository}, + howpublished = {\url{https://https://huggingface.co/Open-Orca/OpenOrca}, +} +``` +```bibtex +@misc{mukherjee2023orca, + title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4}, + author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah}, + year={2023}, + eprint={2306.02707}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +``` +```bibtex +@misc{longpre2023flan, + title={The Flan Collection: Designing Data and Methods for Effective Instruction Tuning}, + author={Shayne Longpre and Le Hou and Tu Vu and Albert Webson and Hyung Won Chung and Yi Tay and Denny Zhou and Quoc V. Le and Barret Zoph and Jason Wei and Adam Roberts}, + year={2023}, + eprint={2301.13688}, + archivePrefix={arXiv}, + primaryClass={cs.AI} +} +``` +```bibtex +@misc{touvron2023llama, + title={Llama 2: Open Foundation and Fine-Tuned Chat Models}, + author={Hugo Touvron and Louis Martin and Kevin Stone and Peter Albert and Amjad Almahairi and Yasmine Babaei and Nikolay Bashlykov and Soumya Batra and Prajjwal Bhargava and Shruti Bhosale and Dan Bikel and Lukas Blecher and Cristian Canton Ferrer and Moya Chen and Guillem Cucurull and David Esiobu and Jude Fernandes and Jeremy Fu and Wenyin Fu and Brian Fuller and Cynthia Gao and Vedanuj Goswami and Naman Goyal and Anthony Hartshorn and Saghar Hosseini and Rui Hou and Hakan Inan and Marcin Kardas and Viktor Kerkez and Madian Khabsa and Isabel Kloumann and Artem Korenev and Punit Singh Koura and Marie-Anne Lachaux and Thibaut Lavril and Jenya Lee and Diana Liskovich and Yinghai Lu and Yuning Mao and Xavier Martinet and Todor Mihaylov and Pushkar Mishra and Igor Molybog and Yixin Nie and Andrew Poulton and Jeremy Reizenstein and Rashi Rungta and Kalyan Saladi and Alan Schelten and Ruan Silva and Eric Michael Smith and Ranjan Subramanian and Xiaoqing Ellen Tan and Binh Tang and Ross Taylor and Adina Williams and Jian Xiang Kuan and Puxin Xu and Zheng Yan and Iliyan Zarov and Yuchen Zhang and Angela Fan and Melanie Kambadur and Sharan Narang and Aurelien Rodriguez and Robert Stojnic and Sergey Edunov and Thomas Scialom}, + year={2023}, + eprint= arXiv 2307.09288 +} +@software{touvron2023llama, + title={LLaMA: Open and Efficient Foundation Language Models}, + author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and Rodriguez, Aurelien and Joulin, Armand and Grave, Edouard and Lample, Guillaume}, + journal={arXiv preprint arXiv:2302.13971}, + year={2023} +} +```" +slone/nllb-200-10M-sample,"{""dataset_info"": {""features"": [{""name"": ""laser_score"", ""dtype"": ""float64""}, {""name"": ""lang1"", ""dtype"": ""string""}, {""name"": ""text1"", ""dtype"": ""string""}, {""name"": ""lang2"", ""dtype"": ""string""}, {""name"": ""text2"", ""dtype"": ""string""}, {""name"": ""blaser_sim"", ""dtype"": ""float64""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 2279333006.0, ""num_examples"": 9983398}], ""download_size"": 1825697094, ""dataset_size"": 2279333006.0}, ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""train"", ""path"": ""data/train-*""}]}], ""license"": ""odc-by"", ""task_categories"": [""translation""], ""pretty_name"": ""nllb-200-10M-sample"", ""size_categories"": [""1M + +This is the cross-lingual subset of the SWIM-IR dataset, where the query generated is in the target language and the passage is in English. +The SWIM-IR dataset is available as CC-BY-SA 4.0. 18 languages (including English) are available in the cross-lingual dataset. + +For full details of the dataset, please read our upcoming [NAACL 2024 paper](https://arxiv.org/abs/2311.05800) and check out our [website](https://github.com/google-research-datasets/swim-ir). + +# What is SWIM-IR? + +SWIM-IR dataset is a synthetic multilingual retrieval dataset spanning around 29 million retrieval training pairs across 27 languages. +Each question has been automatically generated with the Summarize-then-Ask (STA) prompting technique using PaLM-2 as the question generator. + +**Note**: As the question is synthetically generated, there is scope for hallucinations during query generation. The hallucinated queries do not affect retrieval effectiveness. + +If you are using SWIM-IR in your research, please cite the following paper: + +``` +@article{thakur:2023, + author = {Nandan Thakur and + Jianmo Ni and + Gustavo Hern{\'{a}}ndez {\'{A}}brego and + John Wieting and + Jimmy Lin and + Daniel Cer}, + title = {Leveraging LLMs for Synthesizing Training Data Across Many Languages + in Multilingual Dense Retrieval}, + journal = {CoRR}, + volume = {abs/2311.05800}, + year = {2023}, + url = {https://doi.org/10.48550/arXiv.2311.05800}, + doi = {10.48550/ARXIV.2311.05800}, + eprinttype = {arXiv}, + eprint = {2311.05800}, + timestamp = {Tue, 14 Nov 2023 14:47:55 +0100}, + biburl = {https://dblp.org/rec/journals/corr/abs-2311-05800.bib}, + bibsource = {dblp computer science bibliography, https://dblp.org} +} +``` + +## Dataset Details + +### Dataset Description + +- **Homepage:** [SWIM-IR homepage](https://github.com/google-research-datasets/swim-ir) +- **Repository:** [SWIM-IR repository](https://github.com/google-research-datasets/swim-ir) +- **Paper:** [Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval +](https://arxiv.org/abs/2311.05800) +- **Leaderboard:** [Needs More Information] +- **Point of Contact:** [Nandan Thakur](mailto:nandan.thakur@uwaterloo.ca) + +#### Dataset Link + + +SWIM-IR v1.0: http://storage.googleapis.com/gresearch/swim-ir/swim_ir_v1.tar.gz + +#### Data Card Author(s) + + +- **Nandan Thakur, University of Waterloo:** Owner +- **Daniel Cer, Google Research:** Owner +- **Jianmo Ni, Google DeepMind:** Contributor +- **John Wieting, Google DeepMind:** Contributor +- **Gustavo Hernandez Abrego, Google Research:** Contributor +- **Jimmy Lin, University of Waterloo:** Contributor + +## Authorship +### Publishers +#### Publishing Organization(s) + + +University of Waterloo, Google Research, Google DeepMind + +#### Industry Type(s) + + +- Corporate - Tech +- Academic - Tech + +### Dataset Owners +#### Team(s) + + +SWIM-IR Team + +#### Contact Detail(s) + + +- **Dataset Owner(s):** Nandan Thakur, Daniel Cer +- **Affiliation:** University of Waterloo, Google Research +- **Contact:** [nandan.thakur@uwaterloo.ca](mailto:nandan.thakur@uwaterloo.ca) + +## Dataset Overview +#### Data Subject(s) + + +- Synthetically generated data + +#### Dataset Snapshot + + +SWIM-IR is a synthetic multilingual retrieval training dataset. +It contains training pairs for both settings: monolingual, i.e. within the same language, and cross-lingual, i.e. across language. +The dataset is useful to fine-tune state-of-the-art (SoTA) synthetic monolingual and cross-lingual neural retrievers across diverse languages. + + +Category | Data +--- | --- +Size of Dataset | ~6-7 GB +Number of Instances | 28,265,848 +Number of Fields | 6 +Labeled Classes | 33* +Number of Labels | 1 + +**Above:** Dataset statistics comprises both in-language and cross-language settings. The classes above denote a language. + +**Additional Notes:** (*) Classes denote the languages we cover in the SWIM-IR dataset. Here is a list of the 18 languages and their ISO codes listed in alphabetical order: +Arabic (ar), Bengali (bn), German (de), English (en), Spanish (es), Persian (fa), Finnish (fi), French (fr), Hindi (hi), Indonesian (id), Japanese (ja), Korean (ko), Russian (ru), Swahili (sw), Thai (th), Yoruba (yo), +Chinese (zh) and rest 15 Indo-European Languages: Assamese (as), Bhojpuri (bho), Konkani (gom), Gujarati (gu), Kannada (kn), Maithili (mai), Malayalam (ml), Manipuri (mni), Marathi (mr), Odia (or), Punjabi (pa), Pashto (ps), Sanskrit (sa), Tamil (ta), Urdu (ur). + +#### Content Description + + +A paragraph is sampled from the Wikipedia corpus which describes an entity. The question arising from the Wikipedia +paragraph is generated using a large language model (LLM). In our work, we used the PaLM 2-S (small) model to generate +synthetic queries across **33 languages**, covering 11 distinct scripts, and 10 language families comprising over 3 billion speakers in the world. + +The SWIM-IR dataset contains about **28 million** Wikipedia synthetic query-paragraph training pairs with a multilingual query for each passage generated using PaLM 2 (small), +for both cross-lingual and monolingual retrieval settings. + +**Additional Notes:** +- The dataset creation follows a specific procedure that involves a `summarize-then-ask` prompting technique inspired by chain-of-thought prompting. +- PaLM 2 uses **summarize-then-ask promping** containing 5-shot exemplars for cross-lingual and 3-shot exemplars for monolingual query generation. +- The prompt includes the original paragraph, a human-generated summary, and a question translated from English using Machine Translation (MT) for cross-lingual generation, +- whereas for randomly sampled training dataset pairs, and summaries generated using Google BARD for monolingual generation. +- PaLM 2 generates an extractive summary which is used as a proxy to help understand the document and highlight relevant sections within the document. +- Finally, the model generates a question in the target language (different in cross-lingual or same in monolingual) which can be answered using the input paragraph. + +### Sensitivity of Data +#### Sensitivity Type(s) + + +- None + +#### Field(s) with Sensitive Data + + +**Intentional Collected Sensitive Data** +No sensitive data was intentionally collected. + +**Unintentionally Collected Sensitive Data** +S/PII, violent, abusive, or toxic text containing racial slurs were not explicitly collected as a part of the dataset creation +process. Sensitive subject and adult content was automatically filtered using the method described in (Thakur et al. 2023). + +#### Security and Privacy Handling + + + +We used algorithmic methods and relied on other classifiers for data filtration. Specifically, we (1) did a human inspection of text samples, with the questions automatically translated to English; (2) our observations motivated using a classifier to filter text containing sensitive subjects and adult content. + +## Example of Data Points +#### Primary Data Modality + + +- Text Data + +#### Data Fields + + + +| Field name | Datapoint Example | Description | +| --------- | -------- | -------- | +| `lang` | String | The language of the generated question | +| `code` | String | The ISO-Code for the language | +| `query` | String | The generated query using PaLM 2 | +| `_id` | String | unique ID denoting the training pair | +| `title` | String | Title of the Wikipedia article | +| `text` | String | Paragraph of the Wikipedia article + +#### Typical Data Point + + +Example of (English -> Japanese) datapoint from our +cross-lingual dataset on the topic of “The Roki Tunnel” from the +English Wikipedia. + +```bash +{ + '_id': '1234', + 'lang': 'Japanese', + 'code': 'ja', + 'query': 'The Roki Tunnel は、北オセチア自治共和国と南オセチア共 + 和国の間を通る唯一の道路ですか?', + 'title': 'The Roki Tunnel', + 'text': ""The Roki Tunnel (also called Roksky Tunnel, ; Ossetic: + Ручъы тъунел; ) is a mountain tunnel of the Transkam road + through the Greater Caucasus Mountains, north of the village + Upper Roka. It is the only road joining North Ossetia–Alania in + the Russian Federation into South Ossetia, a breakaway + republic of Georgia. The road is manned at the town of Nizhny + Zaramag in North Ossetia and is sometimes referred to as the + Roki-Nizhny Zaramag border crossing. The tunnel, completed + by the Soviet government in 1984, is one of only a handful of + routes that cross the North Caucasus Range."" +} +``` + +Example of Hindi (hn) datapoint from our monolingual dataset +on the topic of “Aryabhata” from the Hindi Wikipedia + +```bash +{ + '_id': 'hindi_8987#4', + 'lang': 'Hindi', + 'code': 'hn', + 'query': 'आर्यभर्य ट केरल के कि स स्थान के नि वासी थे ?', + 'title': 'आर्यभर्य ट', + 'text': ""एक ताजा अध्ययन के अनसु ार आर्यभर्य ट, केरल के + चाम्रवत्तम (१०उत्तर५१, ७५पर्वू ४र्व ५) के नि वासी थे। अध्ययन के अनसु ार + अस्मका एक जनै प्रदेश था जो कि श्रवणबेलगोल के चारों तरफ फैला + हुआ था और यहाँके पत्थर के खम्बों के कारण इसका नाम अस्मका + पड़ा। चाम्रवत्तम इस जनै बस्ती का हि स्सा था, इसका प्रमाण है + भारतापझु ा नदी जि सका नाम जनै ों के पौराणि क राजा भारता के नाम + पर रखा गया है। आर्यभर्य ट ने भी यगु ों को परि भाषि त करते वक्त राजा + भारता का जि क्र कि या है- दसगीति का के पांचवें छंद में राजा भारत + के समय तक बीत चकुे काल का वर्णनर्ण आता है। उन दि नों में + कुसमु परुा में एक प्रसि द्ध वि श्ववि द्यालय था जहाँजनै ों का नि र्णा यक + प्रभाव था और आर्यभर्य ट का काम इस प्रकार कुसमु परुा पहुँच सका और + उसे पसदं भी कि या गया।"" +} +``` + +#### Atypical Data Point + + +The dataset does not contain atypical data points as far as we know. + +## Motivations & Intentions +### Motivations +#### Purpose(s) + + +- Research + +#### Domain(s) of Application + + +`Multilingual Dense Retrieval`, `Synthetic Dataset` + +## Provenance +### Collection +#### Method(s) Used + + +- Artificially Generated +- Taken from other existing datasets + +#### Methodology Detail(s) + + +**Collection Type** + +**Source:** TyDI-QA dataset which provided the English Wikipedia dataset for SWIM cross-lingual IR dataset. MIRACL +provided the language-specific Wikipedia datasets for monolingual SWIM-IR datasets. + +**Is this source considered sensitive or high-risk?** [Yes/**No**] + +**Dates of Collection:** TyDI-QA [unknown - 01/02/2019], MIRACL [unknown - 01/02/2023], XTREME-UP [unknown - 01/02/2023] + +**Primary modality of collection data:** +- Text Data + +**Update Frequency for collected data:** +- Static + +#### Source Description(s) + + +- **TyDI-QA:** TyDi-QA [(Clark et al. 2020)](https://aclanthology.org/2020.tacl-1.30/) provided the English Wikipedia passages which have been split into 100-word long paragraphs. It contains around 18.2M passages from the complete English Wikipedia. We selected passages with a maximum of 1M pairs for each language pair (for 17 languages) at random for the preparation of our cross-lingual SWIM-IR dataset. +- **MIRACL:** MIRACL [(Zhang et al. 2023)](https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00595/117438/MIRACL-A-Multilingual-Retrieval-Dataset-Covering) provides language-specific paragraphs from the Wikipedia Corpus. The paragraphs were generated by splitting on the “\n\n” delimiter. The MIRACL dataset provides corpora for 18 languages. We selected passages with a maximum of 1M pairs for each language at random for the preparation of our mono-lingual SWIM-IR dataset. +- **XTREME-UP:** XTREME-UP [(Ruder et al. 2023)](https://aclanthology.org/2023.findings-emnlp.125/) provides a 120K sample of the TyDi-QA (Clark et al. 2020) English Wikipedia passages which have been split into 100-word long paragraphs. This sample has been used in the original dataset for cross-language question answering. + +#### Collection Cadence + + +**Static:** Data was collected once from single or multiple sources. + +#### Data Integration + + +**TyDi-QA (XOR-Retrieve and XTREME-UP)** + +**Included Fields** +The English Wikipedia title, text, and `_id` fields were taken from the TyDi-QA dataset originally provided as a TSV file containing all fields. + +**Excluded Fields** +The rest of the metadata apart from the fields mentioned above were excluded from our SWIM-IR dataset. We do not use any training data provided from the TyDI-QA dataset. + +**MIRACL** + +**Included Fields** +The Language Wikipedia title, text, and `_id` fields were taken from the MIRACL dataset, originally provided as a JSON-lines file containing all fields. + +**Excluded Fields** +The rest of the metadata apart from the fields mentioned above were excluded from our SWIM-IR dataset. We do not use any training data provided from the MIRACL dataset. + +#### Data Processing + + +All data is coming directly from the TyDI-QA and MIRACL datasets without any preprocessing. + +### Collection Criteria +#### Data Selection + + +For the Cross-lingual SWIM-IR dataset, we use a stratified sampling technique to select a subset of passages from the English Wikipedia corpus. We use it to generate questions for SWIM-IR. We ensure all languages have relatively an equal amount of training samples, wherever possible. Our Wikipedia corpus contains entities that are sorted alphabetically (A-Z). We then compute inclusion threshold $I_{th}$, which is defined as $I_{th} = D_{sample} / D_{total}$, where $(D_{sample})$ is number of passages required to sample and $(D_{total})$ is the total numbers of passages in corpus. Next, for each passage ($p_i$) in the corpus, we randomly generate an inclusion probability $\hat{p_i} \in [0,1]$. We select the passage ($p_i$) if $p_i \leq I_{th}$. This ensures uniform sampling of passages with Wikipedia entities between all letters (A-Z). + +For the Monolingual SWIM-IR dataset, the language selection criteria were dependent on the Wikipedia corpora availability for the monolingual task. Hence, we chose to fix on the 18 languages provided in MIRACL. To complete the dataset, we included the same languages for the cross-lingual task. + +#### Data Inclusion + + +We include all data available in TyDi-QA English Wikipedia Corpus (maximum of 1M training pairs per language pair), which we use to generate our cross-lingual SWIM-IR dataset. We use the language-specific MIRACL Wikipedia corpora to generate our monolingual queries in SWIM-IR. + +#### Data Exclusion + + +We removed data classified as containing sensitive subjects and adult content using the method described in our paper. No additional filters were applied for data exclusion from MIRACL or TyDi-QA. + +The TyDi-QA English paragraph data has been split with a maximum of up to 100 tokens. However, MIRACL used the “\n\n” delimiter to segment paragraphs from the Wikipedia articles." +OzoneAsai/4typeCalculation,"{""license"": ""wtfpl"", ""tag"": ""conversational"", ""task_categories"": [""conversational""], ""language"": [""en"", ""zh"", ""de"", ""ru"", ""ko"", ""fr"", ""ja""]}","# Dataset Card for Calculation +### size + JSON file: output1.json≒1.3GB + ~ + output60.json + In total 70 ~ 80GB + + +### Dataset Summary + +**en**: Calculation. Its range will be expanded later. + +**zh**: 计算。其范围将在以后扩展。 + +**de**: Berechnung. Der Umfang wird später erweitert werden. + +**ru**: Расчет. Его диапазон будет расширен позже. + +**ko**: 계산. 범위는 나중에 확장될 것입니다. + +**fr**: Calcul. Sa portée sera étendue ultérieurement. + +**ja**: 計算。範囲は後で拡張されます。 + +### Supported Tasks and Leaderboards + +**en**: conversation, instruction + +**zh**: 会话，指令 + +**de**: Unterhaltung, Anweisung + +**ru**: разговор, инструкция + +**ko**: 대화, 지시사항 + +**fr**: conversation, instruction + +**ja**: 会話、指示 + +### Languages + +**en**: It only used numbers and symbols. So any language is able to use this. + +**zh**: 该数据集只使用数字和符号。因此任何语言都可以使用它。 + +**de**: Es werden nur Zahlen und Symbole verwendet. Daher kann diese Datenbank von jeder Sprache verwendet werden. + +**ru**: В нем используются только цифры и символы. Таким образом, любой язык может использовать его. + +**ko**: 숫자와 기호만 사용되었습니다. 그래서 모든 언어에서 사용할 수 있습니다. + +**fr**: Il n'utilise que des chiffres et des symboles. Ainsi, n'importe quelle langue peut l'utiliser. + +**ja**: 数字と記号のみが使用されています。したがって、どんな言語でも使用できます. + +## Dataset Structure + +Input, output, + +## Translation + Translated by ChatGPT" +allganize/RAG-Evaluation-Dataset-KO,"{""language"": [""ko""], ""license"": ""mit""}","# Allganize RAG Leaderboard +Allganize RAG 리더보드는 5개 도메인(금융, 공공, 의료, 법률, 커머스)에 대해서 한국어 RAG의 성능을 평가합니다. +일반적인 RAG는 간단한 질문에 대해서는 답변을 잘 하지만, 문서의 테이블과 이미지에 대한 질문은 답변을 잘 못합니다. + +RAG 도입을 원하는 수많은 기업들은 자사에 맞는 도메인, 문서 타입, 질문 형태를 반영한 한국어 RAG 성능표를 원하고 있습니다. +평가를 위해서는 공개된 문서와 질문, 답변 같은 데이터 셋이 필요하지만, 자체 구축은 시간과 비용이 많이 드는 일입니다. +이제 올거나이즈는 RAG 평가 데이터를 모두 공개합니다. + +RAG는 Parser, Retrieval, Generation 크게 3가지 파트로 구성되어 있습니다. +현재, 공개되어 있는 RAG 리더보드 중, 3가지 파트를 전체적으로 평가하는 한국어로 구성된 리더보드는 없습니다. + +Allganize RAG 리더보드에서는 문서를 업로드하고, 자체적으로 만든 질문을 사용해 답변을 얻었습니다. +생성한 답변과 정답 답변을 자동 성능 평가 방법을 적용해 각 RAG 방법별 성능 측정을 했습니다. + + +# RAG Benchmark +| RAG | 금융 | 공공 | 의료 | 법률 | 커머스 | Average | +|:-----:|:-----:|:-----:|:-----:|:-----:|:-----:|:-----:| +| Alli (claude3.5-sonnet) | **0.85 (51/60)** | **0.983 (59/60)** | 0.85 (51/60) | **0.767 (46/60)** | 0.783 (47/60) | **0.847 (254/300)** | +| Alli (claude3-opus) | 0.817 (49/60) | 0.95 (57/60) | **0.9 (54/60)** | 0.75 (45/60) | 0.767 (46/60) | 0.837 (251/300) | +| Alli (gpt-4o) | 0.8 (48/60) | 0.9 (54/60) | 0.817 (49/60) | 0.683 (41/60) | 0.717 (43/60) | 0.783 (235/300) | +| Alli (gpt-4) | 0.833 (50/60) | 0.85 (51/60) | 0.733 (44/60) | 0.733 (44/60) | 0.733 (44/60) | 0.777 (233/300) | +| Alli (gpt-4-turbo) | 0.783 (47/60) | 0.9 (54/60) | 0.733 (44/60) | 0.717 (43/60) | 0.733 (44/60) | 0.773 (232/300) | +| Alli (alpha-ko-202411-32B) | 0.8 (48/60) | 0.85 (51/60) | 0.75 (45/60) | 0.717 (43/60) | 0.733 (44/60) | 0.77 (231/300) | +| Alli (gpt-4o-mini) | 0.75 (45/60) | 0.883 (53/60) | 0.7 (42/60) | 0.733 (44/60) | 0.75 (45/60) | 0.763 (229/300) | +| Upstage (gpt-4-turbo) | 0.617 (37/60) | 0.85 (51/60) | 0.833 (50/60) | 0.6 (36/60) | **0.817 (49/60)** | 0.743 (223/300) | +| OpenAI Assistant (gpt-4-turbo) | 0.533 (32/60) | 0.883 (53/60) | 0.733 (44/60) | 0.733 (44/60) | 0.783 (47/60) | 0.733 (220/300) | +| OpenAI Assistant (gpt-4) | 0.717 (43/60) | 0.783 (47/60) | 0.767 (46/60) | 0.517 (31/60) | 0.75 (45/60) | 0.707 (212/300) | +| Upstage (gpt-4) | 0.6 (36/60) | 0.783 (47/60) | 0.75 (45/60) | 0.583 (35/60) | 0.783 (47/60) | 0.7 (210/300) | +| Alli (Llama-3-Alpha-Ko-8B-Instruct-Pro) | 0.683 (41/60) | 0.767 (46/60) | 0.633 (38/60) | 0.583 (35/60) | 0.7 (42/60) | 0.673 (202/300) | +| Alli ([KONI-Llama3-8B-Instruct-20240729](https://huggingface.co/KISTI-KONI/KONI-Llama3-8B-Instruct-20240729)) | 0.683 (41/60) | 0.7 (42/60) | 0.533 (32/60) | 0.567 (34/60) | 0.75 (45/60) | 0.647 (194/300) | +| Upstage (solar) | 0.6 (36/60) | 0.683 (41/60) | 0.733 (44/60) | 0.433 (26/60) | 0.717 (43/60) | 0.633 (190/300) | +| Langchain (gpt-4-turbo) | 0.617 (37/60) | 0.517 (31/60) | 0.667 (40/60) | 0.567 (34/60) | 0.683 (41/60) | 0.61 (183/300) | +| Cohere (command-r-plus) | 0.483 (29/60) | 0.65 (39/60) | 0.433 (26/60) | 0.517 (31/60) | 0.683 (41/60) | 0.553 (166/300) | +| Cohere (command-r) | 0.5 (30/60) | 0.633 (38/60) | 0.417 (25/60) | 0.533 (32/60) | 0.667 (40/60) | 0.55 (165/300) | +| Upstage (gpt-3.5-turbo) | 0.5 (30/60) | 0.517 (31/60) | 0.567 (34/60) | 0.417 (25/60) | 0.617 (37/60) | 0.523 (157/300) | +| Alli ([Llama-3-Alpha-Ko-8B-Instruct](https://huggingface.co/allganize/Llama-3-Alpha-Ko-8B-Instruct)) | 0.533 (32/60) | 0.55 (33/60) | 0.533 (32/60) | 0.417 (25/60) | 0.55 (33/60) | 0.517 (155/300) | +| Langchain (gpt-3.5-turbo) | 0.4 (24/60) | 0.333 (20/60) | 0.417 (25/60) | 0.35 (21/60) | 0.467 (28/60) | 0.393 (118/300) | +| Anything LLM (gpt-4-turbo) | 0.267 (16/60) | 0.067 (4/60) | 0.55 (33/60) | 0.283 (17/60) | 0.283 (17/60) | 0.29 (87/300) | +| Anything LLM (claude3-opus) | 0.267 (16/60) | 0.067 (4/60) | 0.55 (33/60) | 0.317 (19/60) | 0.45 (27/60) | 0.33 (99/300) | +| Anything LLM (gpt-3.5-turbo) | 0.133 (8/60) | 0.033 (2/60) | 0.233 (14/60) | 0.15 (9/60) | 0.233 (14/60) | 0.157 (47/300) | + + + +# Auto Evaluate +총 4개의 LLM Eval을 사용하여 평가한 후, voting 하여 ""O"" 혹은 ""X""를 결정했습니다. +- TonicAI : answer_similarity (threshold=4) +- MLflow : answer_similarity/v1/score (threshold=4) +- MLflow : answer_correctness/v1/score (threshold=4) +- Allganize Eval : answer_correctness/claude3-opus + +LLM 기반 평가 방법이기 때문에, 오차율이 존재합니다. +Finance 도메인을 기반으로 사람이 평가한 것과 오차율을 비교하였을 때, 약 8%의 오차율을 보였습니다. +Colab에 Auto Evaluate를 사용할 수 있게 정리하였습니다. +- [Colab](https://colab.research.google.com/drive/1c9hH429iAqw4xkgKoQq1SC9f_4p_nwcc?usp=sharing) + + +# Dataset + +### Domain +다양한 도메인 중, 다섯개를 선택해 성능 평가를 진행했습니다. +- finance(금융) +- public(공공) +- medical(의료) +- law(법률) +- commerce(커머스) + + +### Documents +도메인별로 PDF 문서를 수집하여 질문들을 생성했습니다. +각 도메인별 문서의 페이지 수 총합이 2~300개가 되도록 문서들을 수집했습니다. +각 문서의 이름, 페이지 수, 링크 또한 [documents.csv](https://huggingface.co/datasets/allganize/RAG-Evaluation-Dataset-KO/blob/main/documents.csv) 파일을 다운받으면 확인하실 수 있습니다. +각 도메인별 pdf 문서 갯수는 다음과 같습니다. +- finance: 10개 (301 page) +- public: 12개 (258 page) +- medical: 20개 (276 page) +- law: 12개 (291 page) +- commerce: 9개 (211 page) + + +### Question and Target answer +문서의 페이지 내용을 보고 사용자가 할만한 질문 및 답변들을 만들었습니다. +각 도메인별로 60개의 질문들을 가지고 있습니다. + + +### Context type +문서의 페이지를 보고 여기에서 나올 수 있는 질문들을 생성했습니다. +이때 질문에 대한 근���가 문단(paragraph)인지, 테이블(table)인지, 이미지(image)인지를 구분했습니다. +각 질문별 근거 유형을 context_type이라 하여 컬럼을 추가해두었습니다. +각 도메인별 context_type의 비율은 문서의 페이지에 등장한 빈도수를 반영해 설정했습니다. (ex. 금융 도메인 문서 210, 테이블 127, 이미지26) +도메인별 context_type의 비율은 다음과 같습니다. + +| domain | paragraph | table | image | +| :--------: | :---------: | :--------: | :--------: | +| finance | 30 (50%) | 10 (17%) | 20 (33%) | +| public | 40 (67%) | 15 (25%) | 5 (8%) | +| medical | 45 (75%) | 5 (8%) | 10 (17%) | +| law | 40 (67%) | 15 (25%) | 5 (8%) | +| commerce | 38 (64%) | 5 (8%) | 17 (28%) | + + + +# RAG Solution +### Alli +Alli는 Allganize의 RAG 솔루션입니다. +Parser는 page 단위로 Allganize Parser를 사용해 구현했습니다. +Retrieval는 Hybrid Search를 사용해 구현했습니다. +Generation은 OpenAI, Cluade, Allganize에서 만든 금융모델 등 간단하게 선택해서 사용할 수 있습니다. +- [Allganize](https://www.allganize.ai/ko/home) + + +### LangChain +LangChain은 LLM으로 구동되는 애플리케이션을 개발하기 위한 프레임워크입니다. +LangChain RAG Quick Start를 기반으로 성능을 평가했습니다. +Parser는 pypdf를 사용했습니다. +chunk size와 overlap은 튜토리얼에 나와있는데로 1000과 200으로 설정했습니다. +Retrieval은 OpenAI Embedding을 사용했습니다. +Generation은 Langchain에서 지원하는 모델을 자유롭게 사용할 수 있습니다. +- [LangChain Tutorial](https://python.langchain.com/v0.1/docs/use_cases/question_answering/quickstart/) +- [Colab](https://colab.research.google.com/drive/1Jlzs8ZqFOqqIBBT2T5XGBhr23XxEsvHb?usp=sharing) + + +### OpenAI Assistant +OpenAI Assistant는 File Search, Code Interperter 같은 특정 기능을 지원하는 툴입니다. +문서를 업로드할 수 있으며, 자체 vector stores에 저장됩니다. +질문을 입력하면 vector stores에서 관련된 chunk를 가져와 모델에 입력해 답변을 출력합니다. +어떤 chunk를 사용했는지 citation이 달리며 확인할 수 있습니다. +- [OpenAI](https://platform.openai.com/docs/assistants/tools/file-search/quickstart) +- [Colab](https://colab.research.google.com/drive/1Ag3ylvk3oucQsOPorjgc1C8qZ4JFrJgu?usp=sharing) + + +### Cohere +Cohere에서는 text embedding 모델과 generation 모델을 제공하고 있습니다. +Parser로 Cohere에는 문서를 업로드하고 파싱하는 기능은 없어서 Langchain의 기본 parser를 사용했습니다. +chunk_size는 500으로 overlap은 200으로 설정했습니다. +Cohere의 임베딩 최대 길이가 512 토큰이라 상대적으로 짧기 때문에 짧게 설정했습니다. +Retrieval는 `embed-multilingual-v3.0`을 사용했습니다. +Generation은 `command-r`과 `command-r-plus`를 사용해 성능을 평가했습니다. +- [Cohere](https://cohere.com/command) +- [Colab](https://colab.research.google.com/drive/1QwozvB-SCeeHhRe6MmlnCETw3bGu9SJe?usp=sharing) + + +### Anything LLM +Anything LLM은 사용하고 싶은 LLM과 벡터DB를 선택하여 RAG 파이프라인을 로컬에 구축할 수 있는 프로그램입니다. +문서들을 ""Workspace"" 라는 개체로 구분합니다. 각 Workspace에 업로드된 문서들만을 대상으로 대화를 수행합니다. +프로그램을 다운로드하여 사용할 수도 있고, github 코드를 clone하여 docker compose로 실행할 수도 있습니다. +Parser와 Retrieval는 Anything LLM 자체 방법으로 구현되어 있습니다. +Generation model은 OpenAI나 Anthropic 모델을 API key만 등록하면 사용할 수 있습니다. +- [Github link](https://github.com/Mintplex-Labs/anything-llm) +- [Download link](https://useanything.com/download) + + +### Upstage +Upstage에서는 text embedding 모델과 generation 모델을 제공하고 있습니다. +Parser로 Upstage에는 문서를 업로드하고 파싱하는 기능은 없어서 Langchain의 기본 parser를 사용했습니다. +chunk size와 overlap은 튜토리얼에 나와있는데로 1000과 200으로 설정했습니다. +Retrieval는 `solar-embedding-1-large`를 사용했습니다. +Generation은 `solar-1-mini-chat`을 사용해 성능을 평가했습니다. +`gpt4-turbo`, `gpt4`, `gpt3.5-turbo`는 임베딩만 `solar-embedding-1-large`를 사용해서 성능 평가한 방법입니다. +- [Upstage](https://developers.upstage.ai/docs/apis/embeddings) +- [Colab](https://colab.research.google.com/drive/1JE2IXCACSkWeGiu9xvG8kmr0jmtzVzB1?usp=sharing) + +
+ +# Contributor +- Junghoon Lee (junghoon.lee@allganize.ai) +- Sounghan Kim (sounghan.kim@allganize.ai) +- Yujung Kim (yujung.kim@allganize.ai) + + +# History Note +### 2024.08.09 +- Auto Evaluate를 5개에서 4개로 변경. +- 모델 추가 : Alli (gpt-4o-mini), Alli (KONI-Llama3-8B-Instruct-20240729), Alli (Llama-3-Ko-8B-Finance-Evol), Alli (Llama-3-Alpha-Ko-8B-Instruct)" +Unbabel/TowerBlocks-v0.1,"{""language"": [""en"", ""de"", ""fr"", ""zh"", ""pt"", ""nl"", ""ru"", ""ko"", ""it"", ""es""], ""size_categories"": [""100K- + ace_Arab, ace_Latn, acm_Arab, acq_Arab, aeb_Arab, afr_Latn, ajp_Arab, + aka_Latn, amh_Ethi, apc_Arab, arb_Arab, ars_Arab, ary_Arab, arz_Arab, + asm_Beng, ast_Latn, awa_Deva, ayr_Latn, azb_Arab, azj_Latn, bak_Cyrl, + bam_Latn, ban_Latn,bel_Cyrl, bem_Latn, ben_Beng, bho_Deva, bjn_Arab, bjn_Latn, + bod_Tibt, bos_Latn, bug_Latn, bul_Cyrl, cat_Latn, ceb_Latn, ces_Latn, + cjk_Latn, ckb_Arab, crh_Latn, cym_Latn, dan_Latn, deu_Latn, dik_Latn, + dyu_Latn, dzo_Tibt, ell_Grek, eng_Latn, epo_Latn, est_Latn, eus_Latn, + ewe_Latn, fao_Latn, pes_Arab, fij_Latn, fin_Latn, fon_Latn, fra_Latn, + fur_Latn, fuv_Latn, gla_Latn, gle_Latn, glg_Latn, grn_Latn, guj_Gujr, + hat_Latn, hau_Latn, heb_Hebr, hin_Deva, hne_Deva, hrv_Latn, hun_Latn, + hye_Armn, ibo_Latn, ilo_Latn, ind_Latn, isl_Latn, ita_Latn, jav_Latn, + jpn_Jpan, kab_Latn, kac_Latn, kam_Latn, kan_Knda, kas_Arab, kas_Deva, + kat_Geor, knc_Arab, knc_Latn, kaz_Cyrl, kbp_Latn, kea_Latn, khm_Khmr, + kik_Latn, kin_Latn, kir_Cyrl, kmb_Latn, kon_Latn, kor_Hang, kmr_Latn, + lao_Laoo, lvs_Latn, lij_Latn, lim_Latn, lin_Latn, lit_Latn, lmo_Latn, + ltg_Latn, ltz_Latn, lua_Latn, lug_Latn, luo_Latn, lus_Latn, mag_Deva, + mai_Deva, mal_Mlym, mar_Deva, min_Latn, mkd_Cyrl, plt_Latn, mlt_Latn, + mni_Beng, khk_Cyrl, mos_Latn, mri_Latn, zsm_Latn, mya_Mymr, nld_Latn, + nno_Latn, nob_Latn, npi_Deva, nso_Latn, nus_Latn, nya_Latn, oci_Latn, + gaz_Latn, ory_Orya, pag_Latn, pan_Guru, pap_Latn, pol_Latn, por_Latn, + prs_Arab, pbt_Arab, quy_Latn, ron_Latn, run_Latn, rus_Cyrl, sag_Latn, + san_Deva, sat_Beng, scn_Latn, shn_Mymr, sin_Sinh, slk_Latn, slv_Latn, + smo_Latn, sna_Latn, snd_Arab, som_Latn, sot_Latn, spa_Latn, als_Latn, + srd_Latn, srp_Cyrl, ssw_Latn, sun_Latn, swe_Latn, swh_Latn, szl_Latn, + tam_Taml, tat_Cyrl, tel_Telu, tgk_Cyrl, tgl_Latn, tha_Thai, tir_Ethi, + taq_Latn, taq_Tfng, tpi_Latn, tsn_Latn, tso_Latn, tuk_Latn, tum_Latn, + tur_Latn, twi_Latn, tzm_Tfng, uig_Arab, ukr_Cyrl, umb_Latn, urd_Arab, + uzn_Latn, vec_Latn, vie_Latn, war_Latn, wol_Latn, xho_Latn, ydd_Hebr, + yor_Latn, yue_Hant, zho_Hans, zho_Hant, zul_Latn + +configs: +- config_name: default + data_files: + - split: train + path: train/* +- config_name: eng_Latn-ace_Arab + data_files: + - split: train + path: train/eng_Latn-ace_Arab.jsonl +- config_name: eng_Latn-ace_Latn + data_files: + - split: train + path: train/eng_Latn-ace_Latn.jsonl +- config_name: eng_Latn-acm_Arab + data_files: + - split: train + path: train/eng_Latn-acm_Arab.jsonl +- config_name: eng_Latn-acq_Arab + data_files: + - split: train + path: train/eng_Latn-acq_Arab.jsonl +- config_name: eng_Latn-aeb_Arab + data_files: + - split: train + path: train/eng_Latn-aeb_Arab.jsonl +- config_name: eng_Latn-afr_Latn + data_files: + - split: train + path: train/eng_Latn-afr_Latn.jsonl +- config_name: eng_Latn-ajp_Arab + data_files: + - split: train + path: train/eng_Latn-ajp_Arab.jsonl +- config_name: eng_Latn-aka_Latn + data_files: + - split: train + path: train/eng_Latn-aka_Latn.jsonl +- config_name: eng_Latn-als_Latn + data_files: + - split: train + path: train/eng_Latn-als_Latn.jsonl +- config_name: eng_Latn-amh_Ethi + data_files: + - split: train + path: train/eng_Latn-amh_Ethi.jsonl +- config_name: eng_Latn-apc_Arab + data_files: + - split: train + path: train/eng_Latn-apc_Arab.jsonl +- config_name: eng_Latn-arb_Arab + data_files: + - split: train + path: train/eng_Latn-arb_Arab.jsonl +- config_name: eng_Latn-arb_Latn + data_files: + - split: train + path: train/eng_Latn-arb_Latn.jsonl +- config_name: eng_Latn-ars_Arab + data_files: + - split: train + path: train/eng_Latn-ars_Arab.jsonl +- config_name: eng_Latn-ary_Arab + data_files: + - split: train + path: train/eng_Latn-ary_Arab.jsonl +- config_name: eng_Latn-arz_Arab + data_files: + - split: train + path: train/eng_Latn-arz_Arab.jsonl +- config_name: eng_Latn-asm_Beng + data_files: + - split: train + path: train/eng_Latn-asm_Beng.jsonl +- config_name: eng_Latn-ast_Latn + data_files: + - split: train + path: train/eng_Latn-ast_Latn.jsonl +- config_name: eng_Latn-awa_Deva + data_files: + - split: train + path: train/eng_Latn-awa_Deva.jsonl +- config_name: eng_Latn-ayr_Latn + data_files: + - split: train + path: train/eng_Latn-ayr_Latn.jsonl +- config_name: eng_Latn-azb_Arab + data_files: + - split: train + path: train/eng_Latn-azb_Arab.jsonl +- config_name: eng_Latn-azj_Latn + data_files: + - split: train + path: train/eng_Latn-azj_Latn.jsonl +- config_name: eng_Latn-bak_Cyrl + data_files: + - split: train + path: train/eng_Latn-bak_Cyrl.jsonl +- config_name: eng_Latn-bam_Latn + data_files: + - split: train + path: train/eng_Latn-bam_Latn.jsonl +- config_name: eng_Latn-ban_Latn + data_files: + - split: train + path: train/eng_Latn-ban_Latn.jsonl +- config_name: eng_Latn-bel_Cyrl + data_files: + - split: train + path: train/eng_Latn-bel_Cyrl.jsonl +- config_name: eng_Latn-bem_Latn + data_files: + - split: train + path: train/eng_Latn-bem_Latn.jsonl +- config_name: eng_Latn-ben_Beng + data_files: + - split: train + path: train/eng_Latn-ben_Beng.jsonl +- config_name: eng_Latn-bho_Deva + data_files: + - split: train + path: train/eng_Latn-bho_Deva.jsonl +- config_name: eng_Latn-bjn_Arab + data_files: + - split: train + path: train/eng_Latn-bjn_Arab.jsonl +- config_name: eng_Latn-bjn_Latn + data_files: + - split: train + path: train/eng_Latn-bjn_Latn.jsonl +- config_name: eng_Latn-bod_Tibt + data_files: + - split: train + path: train/eng_Latn-bod_Tibt.jsonl +- config_name: eng_Latn-bos_Latn + data_files: + - split: train + path: train/eng_Latn-bos_Latn.jsonl +- config_name: eng_Latn-bug_Latn + data_files: + - split: train + path: train/eng_Latn-bug_Latn.jsonl +- config_name: eng_Latn-bul_Cyrl + data_files: + - split: train + path: train/eng_Latn-bul_Cyrl.jsonl +- config_name: eng_Latn-cat_Latn + data_files: + - split: train + path: train/eng_Latn-cat_Latn.jsonl +- config_name: eng_Latn-ceb_Latn + data_files: + - split: train + path: train/eng_Latn-ceb_Latn.jsonl +- config_name: eng_Latn-ces_Latn + data_files: + - split: train + path: train/eng_Latn-ces_Latn.jsonl +- config_name: eng_Latn-cjk_Latn + data_files: + - split: train + path: train/eng_Latn-cjk_Latn.jsonl +- config_name: eng_Latn-ckb_Arab + data_files: + - split: train + path: train/eng_Latn-ckb_Arab.jsonl +- config_name: eng_Latn-crh_Latn + data_files: + - split: train + path: train/eng_Latn-crh_Latn.jsonl +- config_name: eng_Latn-cym_Latn + data_files: + - split: train + path: train/eng_Latn-cym_Latn.jsonl +- config_name: eng_Latn-dan_Latn + data_files: + - split: train + path: train/eng_Latn-dan_Latn.jsonl +- config_name: eng_Latn-deu_Latn + data_files: + - split: train + path: train/eng_Latn-deu_Latn.jsonl +- config_name: eng_Latn-dik_Latn + data_files: + - split: train + path: train/eng_Latn-dik_Latn.jsonl +- config_name: eng_Latn-dyu_Latn + data_files: + - split: train + path: train/eng_Latn-dyu_Latn.jsonl +- config_name: eng_Latn-dzo_Tibt + data_files: + - split: train + path: train/eng_Latn-dzo_Tibt.jsonl +- config_name: eng_Latn-ell_Grek + data_files: + - split: train + path: train/eng_Latn-ell_Grek.jsonl +- config_name: eng_Latn-epo_Latn + data_files: + - split: train + path: train/eng_Latn-epo_Latn.jsonl +- config_name: eng_Latn-est_Latn + data_files: + - split: train + path: train/eng_Latn-est_Latn.jsonl +- config_name: eng_Latn-eus_Latn + data_files: + - split: train + path: train/eng_Latn-eus_Latn.jsonl +- config_name: eng_Latn-ewe_Latn + data_files: + - split: train + path: train/eng_Latn-ewe_Latn.jsonl +- config_name: eng_Latn-fao_Latn + data_files: + - split: train + path: train/eng_Latn-fao_Latn.jsonl +- config_name: eng_Latn-fij_Latn + data_files: + - split: train + path: train/eng_Latn-fij_Latn.jsonl +- config_name: eng_Latn-fin_Latn + data_files: + - split: train + path: train/eng_Latn-fin_Latn.jsonl +- config_name: eng_Latn-fon_Latn + data_files: + - split: train + path: train/eng_Latn-fon_Latn.jsonl +- config_name: eng_Latn-fra_Latn + data_files: + - split: train + path: train/eng_Latn-fra_Latn.jsonl +- config_name: eng_Latn-fur_Latn + data_files: + - split: train + path: train/eng_Latn-fur_Latn.jsonl +- config_name: eng_Latn-fuv_Latn + data_files: + - split: train + path: train/eng_Latn-fuv_Latn.jsonl +- config_name: eng_Latn-gaz_Latn + data_files: + - split: train + path: train/eng_Latn-gaz_Latn.jsonl +- config_name: eng_Latn-gla_Latn + data_files: + - split: train + path: train/eng_Latn-gla_Latn.jsonl +- config_name: eng_Latn-gle_Latn + data_files: + - split: train + path: train/eng_Latn-gle_Latn.jsonl +- config_name: eng_Latn-glg_Latn + data_files: + - split: train + path: train/eng_Latn-glg_Latn.jsonl +- config_name: eng_Latn-grn_Latn + data_files: + - split: train + path: train/eng_Latn-grn_Latn.jsonl +- config_name: eng_Latn-guj_Gujr + data_files: + - split: train + path: train/eng_Latn-guj_Gujr.jsonl +- config_name: eng_Latn-hat_Latn + data_files: + - split: train + path: train/eng_Latn-hat_Latn.jsonl +- config_name: eng_Latn-hau_Latn + data_files: + - split: train + path: train/eng_Latn-hau_Latn.jsonl +- config_name: eng_Latn-heb_Hebr + data_files: + - split: train + path: train/eng_Latn-heb_Hebr.jsonl +- config_name: eng_Latn-hin_Deva + data_files: + - split: train + path: train/eng_Latn-hin_Deva.jsonl +- config_name: eng_Latn-hne_Deva + data_files: + - split: train + path: train/eng_Latn-hne_Deva.jsonl +- config_name: eng_Latn-hrv_Latn + data_files: + - split: train + path: train/eng_Latn-hrv_Latn.jsonl +- config_name: eng_Latn-hun_Latn + data_files: + - split: train + path: train/eng_Latn-hun_Latn.jsonl +- config_name: eng_Latn-hye_Armn + data_files: + - split: train + path: train/eng_Latn-hye_Armn.jsonl +- config_name: eng_Latn-ibo_Latn + data_files: + - split: train + path: train/eng_Latn-ibo_Latn.jsonl +- config_name: eng_Latn-ilo_Latn + data_files: + - split: train + path: train/eng_Latn-ilo_Latn.jsonl +- config_name: eng_Latn-ind_Latn + data_files: + - split: train + path: train/eng_Latn-ind_Latn.jsonl +- config_name: eng_Latn-isl_Latn + data_files: + - split: train + path: train/eng_Latn-isl_Latn.jsonl +- config_name: eng_Latn-ita_Latn + data_files: + - split: train + path: train/eng_Latn-ita_Latn.jsonl +- config_name: eng_Latn-jav_Latn + data_files: + - split: train + path: train/eng_Latn-jav_Latn.jsonl +- config_name: eng_Latn-jpn_Jpan + data_files: + - split: train + path: train/eng_Latn-jpn_Jpan.jsonl +- config_name: eng_Latn-kab_Latn + data_files: + - split: train + path: train/eng_Latn-kab_Latn.jsonl +- config_name: eng_Latn-kac_Latn + data_files: + - split: train + path: train/eng_Latn-kac_Latn.jsonl +- config_name: eng_Latn-kam_Latn + data_files: + - split: train + path: train/eng_Latn-kam_Latn.jsonl +- config_name: eng_Latn-kan_Knda + data_files: + - split: train + path: train/eng_Latn-kan_Knda.jsonl +- config_name: eng_Latn-kas_Arab + data_files: + - split: train + path: train/eng_Latn-kas_Arab.jsonl +- config_name: eng_Latn-kas_Deva + data_files: + - split: train + path: train/eng_Latn-kas_Deva.jsonl +- config_name: eng_Latn-kat_Geor + data_files: + - split: train + path: train/eng_Latn-kat_Geor.jsonl +- config_name: eng_Latn-kaz_Cyrl + data_files: + - split: train + path: train/eng_Latn-kaz_Cyrl.jsonl +- config_name: eng_Latn-kbp_Latn + data_files: + - split: train + path: train/eng_Latn-kbp_Latn.jsonl +- config_name: eng_Latn-kea_Latn + data_files: + - split: train + path: train/eng_Latn-kea_Latn.jsonl +- config_name: eng_Latn-khk_Cyrl + data_files: + - split: train + path: train/eng_Latn-khk_Cyrl.jsonl +- config_name: eng_Latn-khm_Khmr + data_files: + - split: train + path: train/eng_Latn-khm_Khmr.jsonl +- config_name: eng_Latn-kik_Latn + data_files: + - split: train + path: train/eng_Latn-kik_Latn.jsonl +- config_name: eng_Latn-kin_Latn + data_files: + - split: train + path: train/eng_Latn-kin_Latn.jsonl +- config_name: eng_Latn-kir_Cyrl + data_files: + - split: train + path: train/eng_Latn-kir_Cyrl.jsonl +- config_name: eng_Latn-kmb_Latn + data_files: + - split: train + path: train/eng_Latn-kmb_Latn.jsonl +- config_name: eng_Latn-kmr_Latn + data_files: + - split: train + path: train/eng_Latn-kmr_Latn.jsonl +- config_name: eng_Latn-knc_Arab + data_files: + - split: train + path: train/eng_Latn-knc_Arab.jsonl +- config_name: eng_Latn-knc_Latn + data_files: + - split: train + path: train/eng_Latn-knc_Latn.jsonl +- config_name: eng_Latn-kon_Latn + data_files: + - split: train + path: train/eng_Latn-kon_Latn.jsonl +- config_name: eng_Latn-kor_Hang + data_files: + - split: train + path: train/eng_Latn-kor_Hang.jsonl +- config_name: eng_Latn-lao_Laoo + data_files: + - split: train + path: train/eng_Latn-lao_Laoo.jsonl +- config_name: eng_Latn-lij_Latn + data_files: + - split: train + path: train/eng_Latn-lij_Latn.jsonl +- config_name: eng_Latn-lim_Latn + data_files: + - split: train + path: train/eng_Latn-lim_Latn.jsonl +- config_name: eng_Latn-lin_Latn + data_files: + - split: train + path: train/eng_Latn-lin_Latn.jsonl +- config_name: eng_Latn-lit_Latn + data_files: + - split: train + path: train/eng_Latn-lit_Latn.jsonl +- config_name: eng_Latn-lmo_Latn + data_files: + - split: train + path: train/eng_Latn-lmo_Latn.jsonl +- config_name: eng_Latn-ltg_Latn + data_files: + - split: train + path: train/eng_Latn-ltg_Latn.jsonl +- config_name: eng_Latn-ltz_Latn + data_files: + - split: train + path: train/eng_Latn-ltz_Latn.jsonl +- config_name: eng_Latn-lua_Latn + data_files: + - split: train + path: train/eng_Latn-lua_Latn.jsonl +- config_name: eng_Latn-lug_Latn + data_files: + - split: train + path: train/eng_Latn-lug_Latn.jsonl +- config_name: eng_Latn-luo_Latn + data_files: + - split: train + path: train/eng_Latn-luo_Latn.jsonl +- config_name: eng_Latn-lus_Latn + data_files: + - split: train + path: train/eng_Latn-lus_Latn.jsonl +- config_name: eng_Latn-lvs_Latn + data_files: + - split: train + path: train/eng_Latn-lvs_Latn.jsonl +- config_name: eng_Latn-mag_Deva + data_files: + - split: train + path: train/eng_Latn-mag_Deva.jsonl +- config_name: eng_Latn-mai_Deva + data_files: + - split: train + path: train/eng_Latn-mai_Deva.jsonl +- config_name: eng_Latn-mal_Mlym + data_files: + - split: train + path: train/eng_Latn-mal_Mlym.jsonl +- config_name: eng_Latn-mar_Deva + data_files: + - split: train + path: train/eng_Latn-mar_Deva.jsonl +- config_name: eng_Latn-min_Arab + data_files: + - split: train + path: train/eng_Latn-min_Arab.jsonl +- config_name: eng_Latn-min_Latn + data_files: + - split: train + path: train/eng_Latn-min_Latn.jsonl +- config_name: eng_Latn-mkd_Cyrl + data_files: + - split: train + path: train/eng_Latn-mkd_Cyrl.jsonl +- config_name: eng_Latn-mlt_Latn + data_files: + - split: train + path: train/eng_Latn-mlt_Latn.jsonl +- config_name: eng_Latn-mni_Beng + data_files: + - split: train + path: train/eng_Latn-mni_Beng.jsonl +- config_name: eng_Latn-mos_Latn + data_files: + - split: train + path: train/eng_Latn-mos_Latn.jsonl +- config_name: eng_Latn-mri_Latn + data_files: + - split: train + path: train/eng_Latn-mri_Latn.jsonl +- config_name: eng_Latn-mya_Mymr + data_files: + - split: train + path: train/eng_Latn-mya_Mymr.jsonl +- config_name: eng_Latn-nld_Latn + data_files: + - split: train + path: train/eng_Latn-nld_Latn.jsonl +- config_name: eng_Latn-nno_Latn + data_files: + - split: train + path: train/eng_Latn-nno_Latn.jsonl +- config_name: eng_Latn-nob_Latn + data_files: + - split: train + path: train/eng_Latn-nob_Latn.jsonl +- config_name: eng_Latn-npi_Deva + data_files: + - split: train + path: train/eng_Latn-npi_Deva.jsonl +- config_name: eng_Latn-nqo_Nkoo + data_files: + - split: train + path: train/eng_Latn-nqo_Nkoo.jsonl +- config_name: eng_Latn-nso_Latn + data_files: + - split: train + path: train/eng_Latn-nso_Latn.jsonl +- config_name: eng_Latn-nus_Latn + data_files: + - split: train + path: train/eng_Latn-nus_Latn.jsonl +- config_name: eng_Latn-nya_Latn + data_files: + - split: train + path: train/eng_Latn-nya_Latn.jsonl +- config_name: eng_Latn-oci_Latn + data_files: + - split: train + path: train/eng_Latn-oci_Latn.jsonl +- config_name: eng_Latn-ory_Orya + data_files: + - split: train + path: train/eng_Latn-ory_Orya.jsonl +- config_name: eng_Latn-pag_Latn + data_files: + - split: train + path: train/eng_Latn-pag_Latn.jsonl +- config_name: eng_Latn-pan_Guru + data_files: + - split: train + path: train/eng_Latn-pan_Guru.jsonl +- config_name: eng_Latn-pap_Latn + data_files: + - split: train + path: train/eng_Latn-pap_Latn.jsonl +- config_name: eng_Latn-pbt_Arab + data_files: + - split: train + path: train/eng_Latn-pbt_Arab.jsonl +- config_name: eng_Latn-pes_Arab + data_files: + - split: train + path: train/eng_Latn-pes_Arab.jsonl +- config_name: eng_Latn-plt_Latn + data_files: + - split: train + path: train/eng_Latn-plt_Latn.jsonl +- config_name: eng_Latn-pol_Latn + data_files: + - split: train + path: train/eng_Latn-pol_Latn.jsonl +- config_name: eng_Latn-por_Latn + data_files: + - split: train + path: train/eng_Latn-por_Latn.jsonl +- config_name: eng_Latn-prs_Arab + data_files: + - split: train + path: train/eng_Latn-prs_Arab.jsonl +- config_name: eng_Latn-quy_Latn + data_files: + - split: train + path: train/eng_Latn-quy_Latn.jsonl +- config_name: eng_Latn-ron_Latn + data_files: + - split: train + path: train/eng_Latn-ron_Latn.jsonl +- config_name: eng_Latn-run_Latn + data_files: + - split: train + path: train/eng_Latn-run_Latn.jsonl +- config_name: eng_Latn-rus_Cyrl + data_files: + - split: train + path: train/eng_Latn-rus_Cyrl.jsonl +- config_name: eng_Latn-sag_Latn + data_files: + - split: train + path: train/eng_Latn-sag_Latn.jsonl +- config_name: eng_Latn-san_Deva + data_files: + - split: train + path: train/eng_Latn-san_Deva.jsonl +- config_name: eng_Latn-sat_Olck + data_files: + - split: train + path: train/eng_Latn-sat_Olck.jsonl +- config_name: eng_Latn-scn_Latn + data_files: + - split: train + path: train/eng_Latn-scn_Latn.jsonl +- config_name: eng_Latn-shn_Mymr + data_files: + - split: train + path: train/eng_Latn-shn_Mymr.jsonl +- config_name: eng_Latn-sin_Sinh + data_files: + - split: train + path: train/eng_Latn-sin_Sinh.jsonl +- config_name: eng_Latn-slk_Latn + data_files: + - split: train + path: train/eng_Latn-slk_Latn.jsonl +- config_name: eng_Latn-slv_Latn + data_files: + - split: train + path: train/eng_Latn-slv_Latn.jsonl +- config_name: eng_Latn-smo_Latn + data_files: + - split: train + path: train/eng_Latn-smo_Latn.jsonl +- config_name: eng_Latn-sna_Latn + data_files: + - split: train + path: train/eng_Latn-sna_Latn.jsonl +- config_name: eng_Latn-snd_Arab + data_files: + - split: train + path: train/eng_Latn-snd_Arab.jsonl +- config_name: eng_Latn-som_Latn + data_files: + - split: train + path: train/eng_Latn-som_Latn.jsonl +- config_name: eng_Latn-sot_Latn + data_files: + - split: train + path: train/eng_Latn-sot_Latn.jsonl +- config_name: eng_Latn-spa_Latn + data_files: + - split: train + path: train/eng_Latn-spa_Latn.jsonl +- config_name: eng_Latn-srd_Latn + data_files: + - split: train + path: train/eng_Latn-srd_Latn.jsonl +- config_name: eng_Latn-srp_Cyrl + data_files: + - split: train + path: train/eng_Latn-srp_Cyrl.jsonl +- config_name: eng_Latn-ssw_Latn + data_files: + - split: train + path: train/eng_Latn-ssw_Latn.jsonl +- config_name: eng_Latn-sun_Latn + data_files: + - split: train + path: train/eng_Latn-sun_Latn.jsonl +- config_name: eng_Latn-swe_Latn + data_files: + - split: train + path: train/eng_Latn-swe_Latn.jsonl +- config_name: eng_Latn-swh_Latn + data_files: + - split: train + path: train/eng_Latn-swh_Latn.jsonl +- config_name: eng_Latn-szl_Latn + data_files: + - split: train + path: train/eng_Latn-szl_Latn.jsonl +- config_name: eng_Latn-tam_Taml + data_files: + - split: train + path: train/eng_Latn-tam_Taml.jsonl +- config_name: eng_Latn-taq_Latn + data_files: + - split: train + path: train/eng_Latn-taq_Latn.jsonl +- config_name: eng_Latn-taq_Tfng + data_files: + - split: train + path: train/eng_Latn-taq_Tfng.jsonl +- config_name: eng_Latn-tat_Cyrl + data_files: + - split: train + path: train/eng_Latn-tat_Cyrl.jsonl +- config_name: eng_Latn-tel_Telu + data_files: + - split: train + path: train/eng_Latn-tel_Telu.jsonl +- config_name: eng_Latn-tgk_Cyrl + data_files: + - split: train + path: train/eng_Latn-tgk_Cyrl.jsonl +- config_name: eng_Latn-tgl_Latn + data_files: + - split: train + path: train/eng_Latn-tgl_Latn.jsonl +- config_name: eng_Latn-tha_Thai + data_files: + - split: train + path: train/eng_Latn-tha_Thai.jsonl +- config_name: eng_Latn-tir_Ethi + data_files: + - split: train + path: train/eng_Latn-tir_Ethi.jsonl +- config_name: eng_Latn-tpi_Latn + data_files: + - split: train + path: train/eng_Latn-tpi_Latn.jsonl +- config_name: eng_Latn-tsn_Latn + data_files: + - split: train + path: train/eng_Latn-tsn_Latn.jsonl +- config_name: eng_Latn-tso_Latn + data_files: + - split: train + path: train/eng_Latn-tso_Latn.jsonl +- config_name: eng_Latn-tuk_Latn + data_files: + - split: train + path: train/eng_Latn-tuk_Latn.jsonl +- config_name: eng_Latn-tum_Latn + data_files: + - split: train + path: train/eng_Latn-tum_Latn.jsonl +- config_name: eng_Latn-tur_Latn + data_files: + - split: train + path: train/eng_Latn-tur_Latn.jsonl +- config_name: eng_Latn-twi_Latn + data_files: + - split: train + path: train/eng_Latn-twi_Latn.jsonl +- config_name: eng_Latn-tzm_Tfng + data_files: + - split: train + path: train/eng_Latn-tzm_Tfng.jsonl +- config_name: eng_Latn-uig_Arab + data_files: + - split: train + path: train/eng_Latn-uig_Arab.jsonl +- config_name: eng_Latn-ukr_Cyrl + data_files: + - split: train + path: train/eng_Latn-ukr_Cyrl.jsonl +- config_name: eng_Latn-umb_Latn + data_files: + - split: train + path: train/eng_Latn-umb_Latn.jsonl +- config_name: eng_Latn-urd_Arab + data_files: + - split: train + path: train/eng_Latn-urd_Arab.jsonl +- config_name: eng_Latn-uzn_Latn + data_files: + - split: train + path: train/eng_Latn-uzn_Latn.jsonl +- config_name: eng_Latn-vec_Latn + data_files: + - split: train + path: train/eng_Latn-vec_Latn.jsonl +- config_name: eng_Latn-vie_Latn + data_files: + - split: train + path: train/eng_Latn-vie_Latn.jsonl +- config_name: eng_Latn-war_Latn + data_files: + - split: train + path: train/eng_Latn-war_Latn.jsonl +- config_name: eng_Latn-wol_Latn + data_files: + - split: train + path: train/eng_Latn-wol_Latn.jsonl +- config_name: eng_Latn-xho_Latn + data_files: + - split: train + path: train/eng_Latn-xho_Latn.jsonl +- config_name: eng_Latn-ydd_Hebr + data_files: + - split: train + path: train/eng_Latn-ydd_Hebr.jsonl +- config_name: eng_Latn-yor_Latn + data_files: + - split: train + path: train/eng_Latn-yor_Latn.jsonl +- config_name: eng_Latn-yue_Hant + data_files: + - split: train + path: train/eng_Latn-yue_Hant.jsonl +- config_name: eng_Latn-zho_Hans + data_files: + - split: train + path: train/eng_Latn-zho_Hans.jsonl +- config_name: eng_Latn-zho_Hant + data_files: + - split: train + path: train/eng_Latn-zho_Hant.jsonl +- config_name: eng_Latn-zsm_Latn + data_files: + - split: train + path: train/eng_Latn-zsm_Latn.jsonl +- config_name: eng_Latn-zul_Latn + data_files: + - split: train + path: train/eng_Latn-zul_Latn.jsonl +---" +Smoked-Salmon-s/empathetic_dialogues_ko,"{""license"": ""apache-2.0"", ""task_categories"": [""text-generation"", ""conversational""], ""language"": [""ko""], ""size_categories"": [""10K `/(/` 같은 오류 등...) + + +## Citation +``` +@misc{mitra2024orcamath, + title={Orca-Math: Unlocking the potential of SLMs in Grade School Math}, + author={Arindam Mitra and Hamed Khanpour and Corby Rosset and Ahmed Awadallah}, + year={2024}, + eprint={2402.14830}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +```" +nlpai-lab/openassistant-guanaco-ko,"{""license"": ""apache-2.0"", ""task_categories"": [""text-generation"", ""question-answering"", ""summarization""], ""language"": [""ko""], ""size_categories"": [""1K + 📃 Paper • 🌐 Demo • 🤗 ApolloMoEDataset • 🤗 ApolloMoEBench • 🤗 Models •🌐 Apollo • 🌐 ApolloMoE +

+ + + +![Apollo](assets/apollo_medium_final.png) + + +## 🌈 Update + +* **[2024.10.15]** ApolloMoE repo is published！🎉 + + +## Languages Coverage +12 Major Languages and 38 Minor Languages + +
+ Click to view the Languages Coverage + + ![ApolloMoE](assets/languages.png) + +
+ + +## Architecture + +
+ Click to view the MoE routing image + + ![ApolloMoE](assets/hybrid_routing.png) + +
+ +## Results + +#### Dense + 🤗 Apollo2-0.5B • 🤗 Apollo2-1.5B • 🤗 Apollo2-2B + + 🤗 Apollo2-3.8B • 🤗 Apollo2-7B • 🤗 Apollo2-9B + +
+ Click to view the Dense Models Results + + ![ApolloMoE](assets/dense_results.png) + +
+ + +#### Post-MoE + 🤗 Apollo-MoE-0.5B • 🤗 Apollo-MoE-1.5B • 🤗 Apollo-MoE-7B + +
+ Click to view the Post-MoE Models Results + + ![ApolloMoE](assets/post_moe_results.png) + +
+ + + + +## Usage Format +##### Apollo2 +- 0.5B, 1.5B, 7B: User:{query}\nAssistant:{response}<|endoftext|> +- 2B, 9B: User:{query}\nAssistant:{response}\ +- 3.8B: <|user|>\n{query}<|end|><|assisitant|>\n{response}<|end|> + +##### Apollo-MoE +- 0.5B, 1.5B, 7B: User:{query}\nAssistant:{response}<|endoftext|> + +## Dataset & Evaluation + +- Dataset + 🤗 ApolloMoEDataset + +
Click to expand + + ![ApolloMoE](assets/Dataset.png) + +
+ + The complete data is stored in `ApolloMoEDataset.json`, while a sample shown in `ApolloMoEDataset_sample.json` + +- Evaluation + 🤗 ApolloMoEBench + +
Click to expand + + - EN: + - [MedQA-USMLE](https://huggingface.co/datasets/GBaker/MedQA-USMLE-4-options) + - [MedMCQA](https://huggingface.co/datasets/medmcqa/viewer/default/test) + - [PubMedQA](https://huggingface.co/datasets/pubmed_qa): Because the results fluctuated too much, they were not used in the paper. + - [MMLU-Medical](https://huggingface.co/datasets/cais/mmlu) + - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine + - ZH: + - [MedQA-MCMLE](https://huggingface.co/datasets/bigbio/med_qa/viewer/med_qa_zh_4options_bigbio_qa/test) + - [CMB-single](https://huggingface.co/datasets/FreedomIntelligence/CMB): Not used in the paper + - Randomly sample 2,000 multiple-choice questions with single answer. + - [CMMLU-Medical](https://huggingface.co/datasets/haonan-li/cmmlu) + - Anatomy, Clinical_knowledge, College_medicine, Genetics, Nutrition, Traditional_chinese_medicine, Virology + - [CExam](https://github.com/williamliujl/CMExam): Not used in the paper + - Randomly sample 2,000 multiple-choice questions + + + - ES: [Head_qa](https://huggingface.co/datasets/head_qa) + - FR: + - [Frenchmedmcqa](https://github.com/qanastek/FrenchMedMCQA) + - [MMLU_FR] + - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine + - HI: [MMLU_HI](https://huggingface.co/datasets/FreedomIntelligence/MMLU_Hindi) + - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine + - AR: [MMLU_AR](https://huggingface.co/datasets/FreedomIntelligence/MMLU_Arabic) + - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine + - JA: [IgakuQA](https://github.com/jungokasai/IgakuQA) + - KO: [KorMedMCQA](https://huggingface.co/datasets/sean0042/KorMedMCQA) + - IT: + - [MedExpQA](https://huggingface.co/datasets/HiTZ/MedExpQA) + - [MMLU_IT] + - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine + - DE: [BioInstructQA](https://huggingface.co/datasets/BioMistral/BioInstructQA): German part + - PT: [BioInstructQA](https://huggingface.co/datasets/BioMistral/BioInstructQA): Portuguese part + - RU: [RuMedBench](https://github.com/sb-ai-lab/MedBench) + - Minor Langs: MMLU Translated Medical Part + + + + +
+ + +## Results reproduction +
Click to expand + + + We take Apollo2-7B or Apollo-MoE-0.5B as example + 1. Download Dataset for project: + + ``` + bash 0.download_data.sh  + ``` + + 2. Prepare test and dev data for specific model: + + + - Create test data for with special token + + ``` + bash 1.data_process_test&dev.sh + ``` + + 3. Prepare train data for specific model (Create tokenized data in advance): + + + - You can adjust data Training order and Training Epoch in this step + + ``` + bash 2.data_process_train.sh + ``` + + 4. Train the model + + + - If you want to train in Multi Nodes please refer to ./src/sft/training_config/zero_multi.yaml + + + ``` + bash 3.single_node_train.sh + ``` + + + 5. Evaluate your model: Generate score for benchmark + + ``` + bash 4.eval.sh + ``` + +
+ + + +## Citation +Please use the following citation if you intend to use our dataset for training or evaluation: + +``` +@misc{zheng2024efficientlydemocratizingmedicalllms, + title={Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts}, + author={Guorui Zheng and Xidong Wang and Juhao Liang and Nuo Chen and Yuping Zheng and Benyou Wang}, + year={2024}, + eprint={2410.10626}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2410.10626}, +} +```" +BramVanroy/xlwic_wn,"{""license"": ""cc-by-nc-4.0"", ""language"": [""bg"", ""zh"", ""hr"", ""da"", ""nl"", ""et"", ""fa"", ""ja"", ""ko""], ""task_categories"": [""text-classification""], ""pretty_name"": ""Multilingual Word-in-Context (WordNet)"", ""configs"": [{""config_name"": ""default"", ""sep"": ""\t"", ""data_files"": [{""split"": ""valid"", ""path"": ""**/*_valid.csv""}, {""split"": ""test"", ""path"": ""**/*_test.csv""}]}, {""config_name"": ""bg"", ""sep"": ""\t"", ""data_files"": [{""split"": ""valid"", ""path"": ""bulgarian_bg/bg_valid.csv""}, {""split"": ""test"", ""path"": ""bulgarian_bg/bg_test.csv""}]}, {""config_name"": ""zh"", ""sep"": ""\t"", ""data_files"": [{""split"": ""valid"", ""path"": ""chinese_zh/zh_valid.csv""}, {""split"": ""test"", ""path"": ""chinese_zh/zh_test.csv""}]}, {""config_name"": ""hr"", ""sep"": ""\t"", ""data_files"": [{""split"": ""valid"", ""path"": ""croatian_hr/hr_valid.csv""}, {""split"": ""test"", ""path"": ""croatian_hr/hr_test.csv""}]}, {""config_name"": ""da"", ""sep"": ""\t"", ""data_files"": [{""split"": ""valid"", ""path"": ""danish_da/da_valid.csv""}, {""split"": ""test"", ""path"": ""danish_da/da_test.csv""}]}, {""config_name"": ""nl"", ""sep"": ""\t"", ""data_files"": [{""split"": ""valid"", ""path"": ""dutch_nl/nl_valid.csv""}, {""split"": ""test"", ""path"": ""dutch_nl/nl_test.csv""}]}, {""config_name"": ""et"", ""sep"": ""\t"", ""data_files"": [{""split"": ""valid"", ""path"": ""estonian_et/et_valid.csv""}, {""split"": ""test"", ""path"": ""estonian_et/et_test.csv""}]}, {""config_name"": ""fa"", ""sep"": ""\t"", ""data_files"": [{""split"": ""valid"", ""path"": ""farsi_fa/fa_valid.csv""}, {""split"": ""test"", ""path"": ""farsi_fa/fa_test.csv""}]}, {""config_name"": ""ja"", ""sep"": ""\t"", ""data_files"": [{""split"": ""valid"", ""path"": ""japanese_ja/ja_valid.csv""}, {""split"": ""test"", ""path"": ""japanese_ja/ja_test.csv""}]}, {""config_name"": ""ko"", ""sep"": ""\t"", ""data_files"": [{""split"": ""valid"", ""path"": ""korean_ko/ko_valid.csv""}, {""split"": ""test"", ""path"": ""korean_ko/ko_test.csv""}]}]}","# Multilingual Word-in-Context (WordNet) + +Refer to the [documentation](https://pilehvar.github.io/xlwic/) and [paper](https://aclanthology.org/2020.emnlp-main.584/) for more information." +squarelike/ko_medical_chat,"{""language"": [""ko""], ""tags"": [""medical""]}","[https://github.com/jwj7140/ko-medical-chat](https://github.com/jwj7140/ko-medical-chat) + +Korean medical conversation dataset from converting [MedText](https://huggingface.co/datasets/BI55/MedText) and [ChatDoctor](https://github.com/Kent0n-Li/ChatDoctor)" +nlp-with-deeplearning/Ko.SlimOrca,"{""license"": ""cc-by-nc-sa-4.0"", ""task_categories"": [""conversational"", ""text-classification"", ""token-classification"", ""table-question-answering"", ""question-answering"", ""zero-shot-classification"", ""summarization"", ""feature-extraction"", ""text-generation"", ""text2text-generation""], ""language"": [""en"", ""ko""], ""size_categories"": [""100K +- **Paper**: http://arxiv.org/abs/2411.19799 + + +### Dataset Summary + +INCLUDE is a comprehensive knowledge- and reasoning-centric benchmark across **44 languages** that evaluates multilingual LLMs for performance in the actual language environments where they would be deployed. +It contains 11,095 4-option multiple-choice-questions (MCQ) extracted from academic and professional exams, covering 57 topics, including regional knowledge. + +For evaluation in a larger set, you can use [include-base-44](https://huggingface.co/datasets/CohereForAI/include-base-44), which is a superset of `include-lite-44`, covering the same 44 languages. + + + +### Languages + +Albanian, Arabic, Armenian, Azerbaijani, Basque, Belarusian, Bengali, Bulgarian, Chinese, Croatian, Dutch, Estonian, Finnish, French, Georgian, German, Greek, Hebrew, Hindi, Hungarian, Indonesia, Italian, Japanese, Kazakh, Korean, Lithuanian, Malay, Malayalam, Nepali, North Macedonian, Persian, Polish, Portuguese, russian, Serbian, Spanish, Tagalog, Tamil, Telugu, Turkish, Ukrainian, Urdu, Uzbek, Vietnamese + +### Topics + +- **Academic**: +Accounting, Agriculture, Anthropology, Architecture and Design, Arts & Humanities, Biology, Business administration, Business ethics, Business, Chemistry, Computer Science, Culturology, Earth science, Economics, Education, Engineering, Environmental studies and forestry, Family and consumer science, Finance, Geography, Health, History, Human physical performance and recreation, Industrial and labor relations, International trade, Journalism, media studies, and communication, Language, Law, Library and museum studies, Literature, Logic, Management, Marketing, Math, Medicine, Military Sciences, Multiple exams, Performing arts, Philosophy, Physics, Political sciences, Psychology, Public Administration, Public Policy, Qualimetry, Religious studies, Risk management and insurance, Social Work, Social work, Sociology, STEM, Transportation, Visual Arts + +- **Licenses**: +Driving License, Marine License, Medical License, Professional Certifications + + +### Data schema + +An example from a French Law question looks as follows: +``` +{ + ""language"": ""French"", + ""country"": ""France"", + ""level"": ""Academic"", + ""domain"": ""Arts & Humanities"", + ""subject"": ""Law"", + ""regional_feature"": ""region explicit"", + ""question"": ""Que permet l'article 49-3 de la Constitution ?"", + ""choices"": [""de recourir au référendum"", ""au Parlement de contrôler l'action du Gouvernement"", ""l'adoption sans vote d'une loi"", ""de prononcer la dissolution de l'Assemblée nationale""], + ""answer"": 2 +} +``` + +### Model Performance + +Models performance on **INCLUDE** using the Harness-eval framework. + + +| **Model** | **Original Lang instructions** | **English instructions** | +|------------------------------------|:------------------------------:|:------------------------:| +| Llama3.1-70B-Instruct | 70.3 | 70.6 | +| Qwen2.5-14B | 61.8 | 61.9 | +| Aya-expanse-32b | 58.9 | 59.5 | +| Qwen2.5-7B | 54.4 | 54.9 | +| Qwen2.5-7B-Instruct | 54.5 | 54.6 | +| Llama-3.1-8B-Instruct | 53.5 | 54.4 | +| Gemma-7B | 53.6 | 53.1 | +| Llama-3.1-8B | 51.2 | 52.1 | +| Aya-expanse-8b | 47.3 | 48.0 | +| Mistral-7B | 44.5 | 44.7 | +| Mistral-7B-Instruct | 43.8 | 43.9 | +| Gemma-7B-Instruct | 39.1 | 39.7 | + + +## Citation + +``` + @article{romanou2024include, + title={INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge}, + author={Romanou, Angelika and Foroutan, Negar and Sotnikova, Anna and Chen, Zeming and Nelaturu, Sree Harsha and Singh, Shivalika and Maheshwary, Rishabh and Altomare, Micol and Haggag, Mohamed A and Amayuelas, Alfonso and others}, + journal={arXiv preprint arXiv:2411.19799}, + year={2024} +} +```" +chengshidehaimianti/CC-Cat,"{""license"": ""odc-by"", ""task_categories"": [""text-generation""], ""language"": [""zh"", ""en"", ""de"", ""ru"", ""es"", ""ja"", ""af"", ""am"", ""an"", ""ar"", ""as"", ""av"", ""az"", ""ba"", ""be"", ""bg"", ""bo"", ""br"", ""bs"", ""ca"", ""cv"", ""cy"", ""da"", ""el"", ""eo"", ""et"", ""eu"", ""fa"", ""fi"", ""fr"", ""fy"", ""ga"", ""gd"", ""gl"", ""gn"", ""gv"", ""he"", ""hi"", ""hr"", ""ht"", ""hu"", ""hy"", ""ia"", ""id"", ""ie"", ""io"", ""is"", ""it"", ""jv"", ""ka"", ""kk"", ""km"", ""kn"", ""ko"", ""kv"", ""kw"", ""ky"", ""la"", ""lb"", ""li"", ""lo"", ""lt"", ""lv"", ""mg"", ""mk"", ""ml"", ""mn"", ""ms"", ""mt"", ""my"", ""ne"", ""nl"", ""nn"", false, ""oc"", ""os"", ""pa"", ""pl"", ""ps"", ""pt"", ""qu"", ""rm"", ""ro"", ""sa"", ""sc"", ""sd"", ""si"", ""sk"", ""sl"", ""so"", ""sq"", ""sr"", ""su"", ""sv"", ""sw"", ""ta"", ""te"", ""tg"", ""tk"", ""tl"", ""tr"", ""tt"", ""ug"", ""uk"", ""ur"", ""uz"", ""vi"", ""wa"", ""yi"", ""yo""], ""tags"": [""croissant""], ""size_categories"": [""n>1T""], ""pretty_name"": ""CCCAT""}","# CC_Cat +- **Extract from *CC-WARC* snapshots.** +- **Mainly includes texts with *149* languages.** +- ***PDF/IMAGE/AUDIO/VIDEO* raw downloading link.** + +# Notice +- Since my computing resources are limited, this dataset will update by one-day of CC snapshots timestampts. +- After a snapshot is updated, the deduplicated version will be uploaded. +- If you are interested in providing computing resources or have cooperation needs, please contact me. + carreyallthetime@gmail.com +
+ +
" +eaglewatch/Korean_Wikipedia_Dataset_for_GPT2_August_2022,"{""annotations_creators"": [""other""], ""language"": [""ko""], ""language_creators"": [""other""], ""license"": [""apache-2.0""], ""multilinguality"": [""multilingual""], ""pretty_name"": ""Korean wikipedia dataset for GPT-2 training"", ""size_categories"": [""100M + +## Main Results + +The multilingual capabilities of all models except for the LLaMA3.2 series improve with increasing model sizes, as LLaMA3.2-1B and LLaMA3.2-3B exhibit poor instruction-following capabilities, leading to a higher failure rate in answer extraction. In addition, Qwen2.5 demonstrates a strong multilingual performance on understanding and capability-specialized tasks, while Gemma2 excels in generation tasks. Closed-source models generally outperform open-source models. + + + +## Citation + +We've published our paper at [this link](https://arxiv.org/pdf/2411.09116). If you find this dataset is helpful, please cite our paper as follows: +``` +@misc{zhang2024pmmevalparallelmultilingualmultitask, + title={P-MMEval: A Parallel Multilingual Multitask Benchmark for Consistent Evaluation of LLMs}, + author={Yidan Zhang and Yu Wan and Boyi Deng and Baosong Yang and Haoran Wei and Fei Huang and Bowen Yu and Junyang Lin and Fei Huang and Jingren Zhou}, + year={2024}, + eprint={2411.09116}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2411.09116}, +} +``` + +# Usage +You can use OpenCompass if you want to evaluate your LLMs on P-MMEval . We advice you to use vllm to accelerate the evaluation (requiring vllm installation): + +``` +# CLI +opencompass --models hf_internlm2_5_1_8b_chat --datasets pmmeval_gen -a vllm + +# Python scripts +opencompass ./configs/eval_PMMEval.py +```" +izhx/xtreme-r-udpos,"{""license"": ""other"", ""license_name"": ""ud-2.7"", ""license_link"": ""https://lindat.mff.cuni.cz/repository/xmlui/page/license-ud-2.7"", ""annotations_creators"": [""found""], ""language_creators"": [""found""], ""language"": [""af"", ""ar"", ""bg"", ""bn"", ""de"", ""el"", ""en"", ""es"", ""et"", ""eu"", ""fa"", ""fi"", ""fr"", ""he"", ""hi"", ""hu"", ""id"", ""it"", ""ja"", ""jv"", ""ka"", ""kk"", ""ko"", ""ml"", ""mr"", ""ms"", ""my"", ""nl"", ""pt"", ""ru"", ""sw"", ""ta"", ""te"", ""th"", ""tl"", ""tr"", ""ur"", ""vi"", ""yo"", ""zh""], ""multilinguality"": [""multilingual"", ""translation""], ""size_categories"": [""n<1K"", ""1K>> from datasets import load_dataset + +>>> dataset = load_dataset(""Bingsu/KcBERT_Pre-Training_Corpus"") +>>> dataset +DatasetDict({ + train: Dataset({ + features: ['text'], + num_rows: 86246285 + }) +}) +``` + +### Data Size + +download: 7.90 GiB
+generated: 11.86 GiB
+total: 19.76 GiB + +※ You can download this dataset from [kaggle](https://www.kaggle.com/datasets/junbumlee/kcbert-pretraining-corpus-korean-news-comments), and it's 5 GiB. (12.48 GiB when uncompressed) + +### Data Fields + +- text: `string` + +### Data Splits + +| | train | +| ---------- | -------- | +| # of texts | 86246285 |" +nazimali/quran,"{""dataset_info"": {""features"": [{""name"": ""surah"", ""dtype"": ""int64""}, {""name"": ""ayah"", ""dtype"": ""int64""}, {""name"": ""surah-name"", ""dtype"": ""string""}, {""name"": ""surah-total-ayas"", ""dtype"": ""int64""}, {""name"": ""surah-name-transliteration"", ""dtype"": ""string""}, {""name"": ""surah-name-en"", ""dtype"": ""string""}, {""name"": ""surah-type"", ""dtype"": ""string""}, {""name"": ""surah-order-revealed"", ""dtype"": ""int64""}, {""name"": ""surah-rukus"", ""dtype"": ""int64""}, {""name"": ""arabic-text-simple"", ""dtype"": ""string""}, {""name"": ""arabic-text-simple-min"", ""dtype"": ""string""}, {""name"": ""arabic-text-simple-plain"", ""dtype"": ""string""}, {""name"": ""arabic-text-simple-clean"", ""dtype"": ""string""}, {""name"": ""arabic-text-uthmani"", ""dtype"": ""string""}, {""name"": ""translation-am-sadiq"", ""dtype"": ""string""}, {""name"": ""translation-ar-jalalayn"", ""dtype"": ""string""}, {""name"": ""translation-ar-muyassar"", ""dtype"": ""string""}, {""name"": ""translation-az-mammadaliyev"", ""dtype"": ""string""}, {""name"": ""translation-az-musayev"", ""dtype"": ""string""}, {""name"": ""translation-ber-mensur"", ""dtype"": ""string""}, {""name"": ""translation-bg-theophanov"", ""dtype"": ""string""}, {""name"": ""translation-bn-bengali"", ""dtype"": ""string""}, {""name"": ""translation-bn-hoque"", ""dtype"": ""string""}, {""name"": ""translation-bs-korkut"", ""dtype"": ""string""}, {""name"": ""translation-bs-mlivo"", ""dtype"": ""string""}, {""name"": ""translation-cs-hrbek"", ""dtype"": ""string""}, {""name"": ""translation-cs-nykl"", ""dtype"": ""string""}, {""name"": ""translation-de-aburida"", ""dtype"": ""string""}, {""name"": ""translation-de-bubenheim"", ""dtype"": ""string""}, {""name"": ""translation-de-khoury"", ""dtype"": ""string""}, {""name"": ""translation-de-zaidan"", ""dtype"": ""string""}, {""name"": ""translation-dv-divehi"", ""dtype"": ""string""}, {""name"": ""translation-en-ahmedali"", ""dtype"": ""string""}, {""name"": ""translation-en-ahmedraza"", ""dtype"": ""string""}, {""name"": ""translation-en-arberry"", ""dtype"": ""string""}, {""name"": ""translation-en-hilali"", ""dtype"": ""string""}, {""name"": ""translation-en-itani"", ""dtype"": ""string""}, {""name"": ""translation-en-maududi"", ""dtype"": ""string""}, {""name"": ""translation-en-mubarakpuri"", ""dtype"": ""string""}, {""name"": ""translation-en-pickthall"", ""dtype"": ""string""}, {""name"": ""translation-en-qarai"", ""dtype"": ""string""}, {""name"": ""translation-en-qaribullah"", ""dtype"": ""string""}, {""name"": ""translation-en-sahih"", ""dtype"": ""string""}, {""name"": ""translation-en-sarwar"", ""dtype"": ""string""}, {""name"": ""translation-en-shakir"", ""dtype"": ""string""}, {""name"": ""translation-en-transliteration"", ""dtype"": ""string""}, {""name"": ""translation-en-wahiduddin"", ""dtype"": ""string""}, {""name"": ""translation-en-yusufali"", ""dtype"": ""string""}, {""name"": ""translation-es-bornez"", ""dtype"": ""string""}, {""name"": ""translation-es-cortes"", ""dtype"": ""string""}, {""name"": ""translation-es-garcia"", ""dtype"": ""string""}, {""name"": ""translation-fa-ansarian"", ""dtype"": ""string""}, {""name"": ""translation-fa-ayati"", ""dtype"": ""string""}, {""name"": ""translation-fa-bahrampour"", ""dtype"": ""string""}, {""name"": ""translation-fa-fooladvand"", ""dtype"": ""string""}, {""name"": ""translation-fa-gharaati"", ""dtype"": ""string""}, {""name"": ""translation-fa-ghomshei"", ""dtype"": ""string""}, {""name"": ""translation-fa-khorramdel"", ""dtype"": ""string""}, {""name"": ""translation-fa-khorramshahi"", ""dtype"": ""string""}, {""name"": ""translation-fa-makarem"", ""dtype"": ""string""}, {""name"": ""translation-fa-moezzi"", ""dtype"": ""string""}, {""name"": ""translation-fa-mojtabavi"", ""dtype"": ""string""}, {""name"": ""translation-fa-sadeqi"", ""dtype"": ""string""}, {""name"": ""translation-fa-safavi"", ""dtype"": ""string""}, {""name"": ""translation-fr-hamidullah"", ""dtype"": ""string""}, {""name"": ""translation-ha-gumi"", ""dtype"": ""string""}, {""name"": ""translation-hi-farooq"", ""dtype"": ""string""}, {""name"": ""translation-hi-hindi"", ""dtype"": ""string""}, {""name"": ""translation-id-indonesian"", ""dtype"": ""string""}, {""name"": ""translation-id-jalalayn"", ""dtype"": ""string""}, {""name"": ""translation-id-muntakhab"", ""dtype"": ""string""}, {""name"": ""translation-it-piccardo"", ""dtype"": ""string""}, {""name"": ""translation-ja-japanese"", ""dtype"": ""string""}, {""name"": ""translation-ko-korean"", ""dtype"": ""string""}, {""name"": ""translation-ku-asan"", ""dtype"": ""string""}, {""name"": ""translation-ml-abdulhameed"", ""dtype"": ""string""}, {""name"": ""translation-ml-karakunnu"", ""dtype"": ""string""}, {""name"": ""translation-ms-basmeih"", ""dtype"": ""string""}, {""name"": ""translation-nl-keyzer"", ""dtype"": ""string""}, {""name"": ""translation-nl-leemhuis"", ""dtype"": ""string""}, {""name"": ""translation-nl-siregar"", ""dtype"": ""string""}, {""name"": ""translation-no-berg"", ""dtype"": ""string""}, {""name"": ""translation-pl-bielawskiego"", ""dtype"": ""string""}, {""name"": ""translation-ps-abdulwali"", ""dtype"": ""string""}, {""name"": ""translation-pt-elhayek"", ""dtype"": ""string""}, {""name"": ""translation-ro-grigore"", ""dtype"": ""string""}, {""name"": ""translation-ru-abuadel"", ""dtype"": ""string""}, {""name"": ""translation-ru-kalam"", ""dtype"": ""string""}, {""name"": ""translation-ru-krachkovsky"", ""dtype"": ""string""}, {""name"": ""translation-ru-kuliev-alsaadi"", ""dtype"": ""string""}, {""name"": ""translation-ru-kuliev"", ""dtype"": ""string""}, {""name"": ""translation-ru-muntahab"", ""dtype"": ""string""}, {""name"": ""translation-ru-osmanov"", ""dtype"": ""string""}, {""name"": ""translation-ru-porokhova"", ""dtype"": ""string""}, {""name"": ""translation-ru-sablukov"", ""dtype"": ""string""}, {""name"": ""translation-sd-amroti"", ""dtype"": ""string""}, {""name"": ""translation-so-abduh"", ""dtype"": ""string""}, {""name"": ""translation-sq-ahmeti"", ""dtype"": ""string""}, {""name"": ""translation-sq-mehdiu"", ""dtype"": ""string""}, {""name"": ""translation-sq-nahi"", ""dtype"": ""string""}, {""name"": ""translation-sv-bernstrom"", ""dtype"": ""string""}, {""name"": ""translation-sw-barwani"", ""dtype"": ""string""}, {""name"": ""translation-ta-tamil"", ""dtype"": ""string""}, {""name"": ""translation-tg-ayati"", ""dtype"": ""string""}, {""name"": ""translation-th-thai"", ""dtype"": ""string""}, {""name"": ""translation-tr-ates"", ""dtype"": ""string""}, {""name"": ""translation-tr-bulac"", ""dtype"": ""string""}, {""name"": ""translation-tr-diyanet"", ""dtype"": ""string""}, {""name"": ""translation-tr-golpinarli"", ""dtype"": ""string""}, {""name"": ""translation-tr-ozturk"", ""dtype"": ""string""}, {""name"": ""translation-tr-transliteration"", ""dtype"": ""string""}, {""name"": ""translation-tr-vakfi"", ""dtype"": ""string""}, {""name"": ""translation-tr-yazir"", ""dtype"": ""string""}, {""name"": ""translation-tr-yildirim"", ""dtype"": ""string""}, {""name"": ""translation-tr-yuksel"", ""dtype"": ""string""}, {""name"": ""translation-tt-nugman"", ""dtype"": ""string""}, {""name"": ""translation-ug-saleh"", ""dtype"": ""string""}, {""name"": ""translation-ur-ahmedali"", ""dtype"": ""string""}, {""name"": ""translation-ur-jalandhry"", ""dtype"": ""string""}, {""name"": ""translation-ur-jawadi"", ""dtype"": ""string""}, {""name"": ""translation-ur-junagarhi"", ""dtype"": ""string""}, {""name"": ""translation-ur-kanzuliman"", ""dtype"": ""string""}, {""name"": ""translation-ur-maududi"", ""dtype"": ""string""}, {""name"": ""translation-ur-najafi"", ""dtype"": ""string""}, {""name"": ""translation-ur-qadri"", ""dtype"": ""string""}, {""name"": ""translation-uz-sodik"", ""dtype"": ""string""}, {""name"": ""translation-zh-jian"", ""dtype"": ""string""}, {""name"": ""translation-zh-majian"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 171759080, ""num_examples"": 6236}], ""download_size"": 129834597, ""dataset_size"": 171759080}, ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""train"", ""path"": ""data/train-*""}]}], ""license"": ""cc-by-3.0"", ""task_categories"": [""text-classification"", ""token-classification"", ""translation"", ""feature-extraction"", ""text-generation""], ""tags"": [""islam"", ""quran"", ""translations""], ""pretty_name"": ""Quran"", ""multilinguality"": [""monolingual"", ""multilingual""], ""language"": [""sq"", ""ber"", ""ar"", ""am"", ""az"", ""bn"", ""bs"", ""bg"", ""zh"", ""cs"", ""dv"", ""nl"", ""en"", ""fr"", ""de"", ""ha"", ""hi"", ""id"", ""it"", ""ja"", ""ko"", ""ku"", ""ms"", ""ml"", false, ""ps"", ""fa"", ""pl"", ""pt"", ""ro"", ""ru"", ""sd"", ""so"", ""es"", ""sw"", ""sv"", ""tg"", ""ta"", ""tt"", ""th"", ""tr"", ""ur"", ""ug"", ""uz""], ""size_categories"": [""1K Post-processing 작업 내용 + +## OpenOrca-Ko-v2 +1. NIV // 약 1500개 +2. FLAN // 약 9000개 +3. T0 // 약 6000개 +4. CoT // 약 2000개 +> Dataset 구성 + +- 수작업으로 고친 내용(v2) +1. 영어로 된 답변 수정. (Ex. Nick -> 닉, Lucky -> 운이 좋음, ...) +2. KoCoT 데이터셋 제거. +3. Yes, True, False 등등 일부 답변 수정 +> Post-processing 작업 내용 + + +## Translation +Using DeepL Pro API. Thanks. + +--- +>Below is original dataset card + +## Table of Contents +- [Dataset Summary](#dataset-summary) +- [Dataset Attribution](#dataset-attribution) +- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) +- [Languages](#languages) +- [Dataset Structure](#dataset-structure) + - [Data Instances](#data-instances) + - [Data Fields](#data-fields) + - [Data Splits](#data-splits) +- [Dataset Creation](#dataset-creation) + - [Curation Rationale](#curation-rationale) + - [Source Data](#source-data) +- [Dataset Use](#dataset-use) + - [Use Cases](#use-cases) + - [Usage Caveats](#usage-caveats) + - [Getting Started](#getting-started) + + +

🐋 The OpenOrca Dataset! 🐋

+ +![OpenOrca Logo](https://huggingface.co/datasets/Open-Orca/OpenOrca/resolve/main/OpenOrcaLogo.png ""OpenOrca Logo"") + + + +We are thrilled to announce the release of the OpenOrca dataset! +This rich collection of augmented FLAN data aligns, as best as possible, with the distributions outlined in the [Orca paper](https://arxiv.org/abs/2306.02707). +It has been instrumental in generating high-performing model checkpoints and serves as a valuable resource for all NLP researchers and developers! + +# Official Models + +## OpenOrca-Platypus2-13B + +Our [latest release](https://huggingface.co/Open-Orca/OpenOrca-Platypus2-13B), the first 13B model to score higher than LLaMA1-65B on the HuggingFace Leaderboard! +Released in partnership with Platypus. + +## LlongOrca 7B & 13B + +* Our [first 7B release](https://huggingface.co/Open-Orca/LlongOrca-7B-16k), trained on top of LLongMA2 to achieve 16,000 tokens context. #1 long context 7B model at release time, with >99% of the overall #1 model's performance. +* [LlongOrca-13B-16k](https://huggingface.co/Open-Orca/LlongOrca-13B-16k), trained on top of LLongMA2. #1 long context 13B model at release time, with >97% of the overall #1 model's performance. + +## OpenOrcaxOpenChat-Preview2-13B + +Our [second model](https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-13B), highlighting that we've surpassed the performance reported in the Orca paper. +Was #1 at release time, now surpassed by our own OpenOrca-Platypus2-13B. +Released in partnership with OpenChat. + +## OpenOrca-Preview1-13B + +[OpenOrca-Preview1-13B](https://huggingface.co/Open-Orca/OpenOrca-Preview1-13B) +This model was trained in less than a day, for <$200, with <10% of our data. +At release, it beat the current state of the art models on BigBench-Hard and AGIEval. Achieves ~60% of the improvements reported in the Orca paper. + + + +# Dataset Summary + +The OpenOrca dataset is a collection of augmented [FLAN Collection data](https://arxiv.org/abs/2301.13688). +Currently ~1M GPT-4 completions, and ~3.2M GPT-3.5 completions. +It is tabularized in alignment with the distributions presented in the ORCA paper and currently represents a partial completion of the full intended dataset, with ongoing generation to expand its scope. +The data is primarily used for training and evaluation in the field of natural language processing. + + + +# Dataset Attribution + +We would like to give special recognition to the following contributors for their significant efforts and dedication: + + + Teknium + WingLian/Caseus + Eric Hartford + NanoBit + Pankaj + Winddude + Rohan + + http://AlignmentLab.ai: + Autometa + Entropi + AtlasUnified + NeverendingToast + NanoBit + WingLian/Caseus + +Also of course, as always, TheBloke, for being the backbone of the whole community. + +Many thanks to NanoBit and Caseus, makers of [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl), for lending us their expertise on the platform that developed and trained manticore, minotaur, and many others! + +We are welcoming sponsors or collaborators to help us build these models to the scale they deserve. Please reach out via our socials: +http://Alignmentlab.ai https://discord.gg/n9hXaBPWxx + +Want to visualize our full dataset? Check out our [Nomic Atlas Map](https://atlas.nomic.ai/map/c1b88b47-2d9b-47e0-9002-b80766792582/2560fd25-52fe-42f1-a58f-ff5eccc890d2). + [](https://atlas.nomic.ai/map/c1b88b47-2d9b-47e0-9002-b80766792582/2560fd25-52fe-42f1-a58f-ff5eccc890d2) + + + + +# Supported Tasks and Leaderboards + +This dataset supports a range of tasks including language modeling, text generation, and text augmentation. +It has been instrumental in the generation of multiple high-performing model checkpoints which have exhibited exceptional performance in our unit testing. +Further information on leaderboards will be updated as they become available. + + + +# Languages + +The language of the data is primarily English. + + + +# Dataset Structure + + + +## Data Instances + +A data instance in this dataset represents entries from the FLAN collection which have been augmented by submitting the listed question to either GPT-4 or GPT-3.5. +The response is then entered into the response field. + + + +## Data Fields + +The fields are: +1) 'id', a unique numbered identifier which includes one of 'niv', 't0', 'cot', or 'flan' to represent which source FLAN Collection submix the 'question' is sourced from. +2) 'system_prompt', representing the System Prompt presented to the GPT-3.5 or GPT-4 API for the datapoint +3) 'question', representing a question entry as provided by the FLAN Collection +4) 'response', a response to that question received from a query to either GPT-3.5 or GPT-4. + + + +## Data Splits + +The data is unsplit. + + + +# Dataset Creation + + + +## Curation Rationale + +The dataset was created to provide a source of augmented text data for researchers and developers. +The datapoints are intended primarily to provide an enhancement of the core FLAN Collection data which relies upon the detailed step by step reasoning capabilities of GPT-3.5 and GPT-4. +This ""reasoning trace"" augmentation has demonstrated exceptional results, allowing a LLaMA-13B model trained with this data to rival or beat GPT-3.5 on broad sets of hard reasoning tasks which all models below 100B parameters had previously performed dramatically worse on. + + + +## Source Data + +The data is generated using techniques in alignment with the distributions outlined in the Orca paper, except as noted below: + +1) There is not enough CoT data in the FLAN Collection to generate 150K zero-shot entries, as the paper purports to use. + We suspect this portion was either undocumented or misrepresented. We have used the ~75K points available. +2) We used the pre-generated FLAN Collection datasets hosted on HuggingFace under conceptofmind, e.g. [conceptofmind/flan2021](https://huggingface.co/datasets/conceptofmind/flan2021_submix_original). + These are referenced by the [official FLAN Collection repo](https://github.com/google-research/FLAN/tree/main/flan/v2) as the preferred data source. + However, these are a subset of the full FLAN Collection data, and have less than the required entries for the flan2021 and t0 submixes, by ~1.25M and 200k respectively. + +Combined, this gave us ~1.5M fewer datapoints than in the original Orca paper. Completing the set is an ongoing work. + + + +# Dataset Use + + + +## Use Cases + +The dataset can be used for tasks related to language understanding, natural language processing, machine learning model training, and model performance evaluation. + + + +## Usage Caveats + +Given that this is a work-in-progress dataset, it is recommended to regularly check for updates and improvements. +Further, the data should be used in accordance with the guidelines and recommendations outlined in the Orca paper. + + + +## Getting Started + +This dataset is organized such that it can be naively loaded via Hugging Face datasets library. +We recommend using streaming due to the large size of the files. +Regular updates and data generation progress can be monitored through the OpenOrca repository on Hugging Face. + + +# Citation + +```bibtex +@misc{OpenOrca, + title = {OpenOrca: An Open Dataset of GPT Augmented FLAN Reasoning Traces}, + author = {Wing Lian and Bleys Goodson and Eugene Pentland and Austin Cook and Chanvichet Vong and ""Teknium""}, + year = {2023}, + publisher = {HuggingFace}, + journal = {HuggingFace repository}, + howpublished = {\url{https://https://huggingface.co/Open-Orca/OpenOrca}, +} +``` +```bibtex +@misc{mukherjee2023orca, + title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4}, + author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah}, + year={2023}, + eprint={2306.02707}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +``` +```bibtex +@misc{longpre2023flan, + title={The Flan Collection: Designing Data and Methods for Effective Instruction Tuning}, + author={Shayne Longpre and Le Hou and Tu Vu and Albert Webson and Hyung Won Chung and Yi Tay and Denny Zhou and Quoc V. Le and Barret Zoph and Jason Wei and Adam Roberts}, + year={2023}, + eprint={2301.13688}, + archivePrefix={arXiv}, + primaryClass={cs.AI} +} +``` +```bibtex +@misc{touvron2023llama, + title={Llama 2: Open Foundation and Fine-Tuned Chat Models}, + author={Hugo Touvron and Louis Martin and Kevin Stone and Peter Albert and Amjad Almahairi and Yasmine Babaei and Nikolay Bashlykov and Soumya Batra and Prajjwal Bhargava and Shruti Bhosale and Dan Bikel and Lukas Blecher and Cristian Canton Ferrer and Moya Chen and Guillem Cucurull and David Esiobu and Jude Fernandes and Jeremy Fu and Wenyin Fu and Brian Fuller and Cynthia Gao and Vedanuj Goswami and Naman Goyal and Anthony Hartshorn and Saghar Hosseini and Rui Hou and Hakan Inan and Marcin Kardas and Viktor Kerkez and Madian Khabsa and Isabel Kloumann and Artem Korenev and Punit Singh Koura and Marie-Anne Lachaux and Thibaut Lavril and Jenya Lee and Diana Liskovich and Yinghai Lu and Yuning Mao and Xavier Martinet and Todor Mihaylov and Pushkar Mishra and Igor Molybog and Yixin Nie and Andrew Poulton and Jeremy Reizenstein and Rashi Rungta and Kalyan Saladi and Alan Schelten and Ruan Silva and Eric Michael Smith and Ranjan Subramanian and Xiaoqing Ellen Tan and Binh Tang and Ross Taylor and Adina Williams and Jian Xiang Kuan and Puxin Xu and Zheng Yan and Iliyan Zarov and Yuchen Zhang and Angela Fan and Melanie Kambadur and Sharan Narang and Aurelien Rodriguez and Robert Stojnic and Sergey Edunov and Thomas Scialom}, + year={2023}, + eprint= arXiv 2307.09288 +} +@software{touvron2023llama, + title={LLaMA: Open and Efficient Foundation Language Models}, + author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and Rodriguez, Aurelien and Joulin, Armand and Grave, Edouard and Lample, Guillaume}, + journal={arXiv preprint arXiv:2302.13971}, + year={2023} +} +```" +LDCC/korag,"{""language"": [""ko""], ""size_categories"": [""10K + + + +# KoMagpie-raw-preview 🐦 + +This is the first, preview version of 🐦 KoMagpie dataset. + +## How to use + +```python +>>> from datasets import load_dataset + +>>> ds = load_dataset(""channelcorp/komagpie-raw-preview"", split=""train"") +>>> ds +Dataset({ + features: ['instruction', 'output', 'model'], + num_rows: 487171 +}) +``` + + +```python +>>> ds[0] +{'instruction': '안녕하세요? 저는 마케팅 매니저로 일하면서 새로운 소비자 트렌드를 파악하기 위해 노력하고 있습니다. 이와 관련해 도움이 될 만한 영어 자료를 찾아주실 수 있나요?', + 'output': '안녕하세요! 물론이죠, 적절한 리소스를 찾는 것은 중요합니다. 이 밑에 있는 사이트들은 마케팅 및 소비자 트렌드에 관한 최신 정보를 제공하는 곳들입니다:\n\n1. **eMarketer:** 이 사이트는 디지털 마케팅, 미디어, 그리고 전자상거래의 세계적인 트렌드를 분���합니다. (www.emarketer.com)\n\n2. **Marketing Dive:** 이 웹사이트는 일상적인 비즈니스 뉴스와 마케팅 업계의 트렌드를 포함합니다. (www.marketingdive.com)\n\n3. **HubSpot:** 이 조직은 새로운 디지털 마케팅 트렌드와 그들의 인플루언스에 대한 광범위한 정보를 제공합니다. 또한 리소스, 툴 및 트레이닝을 제공합니다. (www.hubspot.com)\n\n4. **Adweek:** 광고, 디지털 마케팅, 미디어 트렌드를 설명하는 자료를 제공합니다. (www.adweek.com)\n\n5. **Nielsen:** 이 사이트는 전세계의 소비자 행동에 대한 통찰을 제공합니다. ((www.nielsen.com)\n\n6. **Trend Hunter:** 아이디어, 트렌드, 그리고 방대한 혁신에 관한 세계 최대의 웹사이트입니다. (www.trendhunter.com)\n\n Parses는 더 많은 정보가 필요하시다면 무언가를 명확히 말씀해주시면 감사하겠습니다.', + 'model': 'Qwen/Qwen2-72B-Instruct'} +``` + +### Development Process +We followed [Magpie's process](https://github.com/magpie-align/magpie) to create a Korean version. + +1. Generate instruction data using BOS token + +```python +payload = { + ""model"": ""LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct"", + ""prompt"": ""[|system|]You are a helpful assistant.[|endofturn|]\n[|Korean user|]"", # we used [|Korean user|] instead of [|user|] to gather Korean Instructions + ""stream"": False, + ""n"": 128, + ""max_tokens"": 128, + ""stop"": [""\n"", ""**"", ""|""] +} +``` + +We used [LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct](https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct) model to generate instruction part of the dataset, +following Magpie's method. + +2. Deduplicate using Exact Match +3. Generate output part using open LLMs + +We used [Qwen/Qwen2-72B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct) model to generate output part of the dataset, while limiting within single turn. + + +## License +- Qwen/Qwen2-72B-Instruct : https://huggingface.co/Qwen/Qwen2-72B-Instruct/blob/main/LICENSE +- LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct : https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct/blob/main/LICENSE + + +## Disclaimer +This is not an officially supported Channel Corp product. + + +## Acknowledgement +This research is supported by **TPU Research Cloud program**." +jp1924/KconfSpeech,{},"--- +dataset_info: + features: + - name: audio + dtype: + audio: + sampling_rate: 16000 + - name: sentence + dtype: string + - name: id + dtype: string + - name: dataSet + struct: + - name: version + dtype: string + - name: date + dtype: string + - name: typeInfo + struct: + - name: category + dtype: string + - name: subcategory + dtype: string + - name: place + dtype: string + - name: speakers + list: + - name: id + dtype: string + - name: gender + dtype: string + - name: age + dtype: string + - name: residence + dtype: string + - name: inputType + dtype: string + - name: dialogs + list: + - name: speaker + dtype: string + - name: audioPath + dtype: string + - name: textPath + dtype: string + splits: + - name: train + num_bytes: 342782915304.375 + num_examples: 1824445 + - name: validation + num_bytes: 3177111029.875 + num_examples: 16113 + download_size: 334480278087 + dataset_size: 345960026334.25 +configs: +- config_name: default + data_files: + - split: train + path: data/train-* + - split: validation + path: data/validation-* +task_categories: +- automatic-speech-recognition +language: +- ko +tags: +- STT +- Audio +size_categories: +- 100B"" +} +``` + +The format has the following keys: + +```md +- ""title"" (str) [The title of the article] +- ""text"" (str) [The html content converted fro html into markdown.] +``` + +## Recursal's Vision + +> To make AI accessible to everyone, regardless of language, or economical status + +This is the collective goal of the `RWKV Open Source foundation` and `Recursal AI`, the commercial entity who backs it. + +We believe that AI should not be controlled by a select few individual organization. And that it should be made accessible regardless if you are rich or poor, or a native speaker of english. + +### About RWKV + +RWKV is an Open Source, non profit group, under the linux foundation. Focused on developing the RWKV AI architecture, in accordence to our vision. + +The RWKV architecture scales efficiently and economically. As an RNN & Transformer hybrid, it is able to provide the performance similar to leading transformer models, while having the compute and energy efficiency of an RNN based architecture. + +You can find out more about the project, and latest models, at the following + +- [https://blog.rwkv.com](https://blog.rwkv.com) +- [https://wiki.rwkv.com](https://wiki.rwkv.com) + + +### About Recursal AI + +Recursal AI, is the commercial entity built to provide support for RWKV model development and users, while providing commercial services via its public cloud, or private-cloud / on-premise offerings. + +As part of our vision. Our commitment, is to ensure open source development and access to the best foundational AI models and datasets. + +The following dataset/models provided here, is part of that commitment. + +You can find out more about recursal AI here + +- [https://recursal.ai](https://recursal.ai) +- [https://blog.recursal.ai](https://blog.recursal.ai) + +### Dataset Curators + +KaraKaraWitch. (I typically hang out in PygmalionAI discord, sometimes EleutherAI. If something is wrong, `@karakarawitch` on discord.) + +I'd be happy if you could spread the word and recommend this dataset. + +### Licensing Information + +MDN lists their license as [CC-BY-SA.](https://developer.mozilla.org/en-US/docs/MDN/Writing_guidelines/Attrib_copyright_license) + +Recursal Waifus (The banner image) are licensed under CC-BY-SA. +They do not represent the related websites in any official capacity unless otherwise or announced by the website. +You may use them as a banner image. However, you must always link back to the dataset. + +### Citation Information + +``` +@misc{MDN, + title = {MDN}, + author = {KaraKaraWitch, recursal.ai}, + year = {2024}, + howpublished = {\url{https://huggingface.co/datasets/recursal/MDN}}, +} +```" +jihye-moon/LawQA-Ko,"{""task_categories"": [""text-generation"", ""question-answering""], ""language"": [""ko""], ""tags"": [""legal""], ""size_categories"": [""10K + +법률에 대한 질문과 답변으로 구성된 데이터셋 입니다. + +아래의 데이터셋에서 질문과 답변을 병합하여 Datasets를 만들었습니다. + + +| 정보 출처 | Dataset Page | Rows | +|---|---|---| +|[찾기쉬운생활법령정보 백문백답](https://www.easylaw.go.kr/CSP/OnhunqueansLstRetrieve.laf?search_put=)| [jiwoochris/easylaw_kr](https://huggingface.co/datasets/jiwoochris/easylaw_kr) | 2,195 rows | +|[대한법률구조공단 법률상담사례](https://www.klac.or.kr/legalinfo/counsel.do)| [jihye-moon/klac_legal_aid_counseling](https://huggingface.co/datasets/jihye-moon/klac_legal_aid_counseling) | 10,037 rows | +|[대한법률구조공단 사이버상담](https://www.klac.or.kr/legalstruct/cyberConsultation.do)| [jihye-moon/klac_cyber_counseling](https://huggingface.co/datasets/jihye-moon/klac_cyber_counseling) | 2,587 rows | + +※ 위의 데이터는 모두 웹 페이지를 크롤링 하여 구축된 데이터 입니다. + +※ 대한법률구조공단 데이터는 크롤링 후, 전처리(공단 안내문구 삭제, 쿠션어 삭제 등)를 하였습니다." +Bingsu/namuwiki_20210301_filtered,"{""annotations_creators"": [""no-annotation""], ""language_creators"": [""crowdsourced""], ""language"": [""ko""], ""license"": [""cc-by-nc-sa-2.0""], ""multilinguality"": [""monolingual""], ""pretty_name"": ""Namuwiki database dump (2021-03-01)"", ""size_categories"": [""100K +[heegyu/namuwiki-extracted](https://huggingface.co/datasets/heegyu/namuwiki-extracted)
+[heegyu/namuwiki-sentences](https://huggingface.co/datasets/heegyu/namuwiki-sentences) + +### Lisence + +[CC BY-NC-SA 2.0 KR](https://creativecommons.org/licenses/by-nc-sa/2.0/kr/) + +## Data Structure + +### Data Instance + +```pycon +>>> from datasets import load_dataset + +>>> dataset = load_dataset(""Bingsu/namuwiki_20210301_filtered"") +>>> dataset +DatasetDict({ + train: Dataset({ + features: ['title', 'text'], + num_rows: 571308 + }) +}) +``` + +```pycon +>>> dataset[""train""].features +{'title': Value(dtype='string', id=None), + 'text': Value(dtype='string', id=None)} +``` + +### Data Size + +download: 3.26 GiB
+generated: 3.73 GiB
+total: 6.99 GiB + +### Data Field + +- title: `string` +- text: `string` + +### Data Splits + +| | train | +| ---------- | ------ | +| # of texts | 571308 | + + +```pycon +>>> dataset[""train""][2323] +{'title': '55번 지방도', + 'text': '55번 국가지원지방도\n해남 ~ 금산\n시점 전라남도 해남군 북평면 남창교차로\n종점 충청남도 금산군 금산읍 우체국사거리\n총 구간 279.2km\n경유지 전라남도 강진군, 장흥군, 영암군 전라남도 나주시, 화순군 광주광역시 동구, 북구 전라남도 담양군 전라북도 순창군, 정읍시, 완주군 전라북도 임실군, 진안군\n개요\n국가지원지방도 제55호선은 전라남도 해남군에서 출발하여 충청남도 금산군까지 이어지는 대한민국의 국가지원지방도이다.\n전라남도 해남군 북평면 - 전라남도 강진군 도암면 구간은 광주광역시, 전라남도 동부권, 영남 지방에서 완도군 완도읍으로 갈 때 주로 이용된다.] 해남 - 완도구간이 확장되기 전에는 그랬다. 강진군, 장흥군은 예외]\n노선\n전라남도\n해남군\n백도로\n북평면 남창교차로에서 13번 국도, 77번 국도와 만나며 출발한다.\n쇄노재\n북일면 북일초교 앞에서 827번 지방도와 만난다.\n강진군\n백도로\n도암면소재지 사거리에서 819번 지방도와 만난다. 819번 지방도는 망호선착장까지만 길이 있으며, 뱃길을 통해 간접적으로 바다 건너의 819번 지방도와 연결된다.\n석문공원\n도암면 계라교차로에서 18번 국도에 합류한다. 우회전하자. 이후 강진읍까지 18번 국도와 중첩되고 장흥군 장흥읍까지 2번 국도와 중첩된다. 그리고 장흥읍부터 영암군을 거쳐 나주시 세지면까지는 23번 국도와 중첩된다.\n나주시\n동창로\n세지면 세지교차로에서 드디어 23번 국도로부터 분기하면서 820번 지방도와 직결 합류한다. 이 길은 2013년 현재 확장 공사 중이다. 확장공사가 완료되면 동창로가 55번 지방도 노선이 된다.\n세남로\n봉황면 덕림리 삼거리에서 820번 지방도와 분기한다.\n봉황면 철천리 삼거리에서 818번 지방도와 합류한다.\n봉황면 송현리 삼거리에서 818번 지방도와 분기한다.\n송림산제길\n동창로\n여기부터 완공된 왕복 4차로 길이다. 이 길을 만들면서 교통량이 늘어났지만 주변 농민들이 이용하는 농로의 교량을 설치하지 않아 문제가 생기기도 했다. #1 #2\n세남로\n남평읍에서 다시 왕복 2차로로 줄어든다.\n남평읍 남평오거리에서 822번 지방도와 만난다.\n산남로\n남평교를 건너고 남평교사거리에서 우회전\n동촌로\n남평역\n화순군\n동촌로\n화순읍 앵남리 삼거리에서 817번 지방도와 합류한다. 좌회전하자.\n앵남역\n지강로\n화순읍 앵남리 앵남교차로에서 817번 지방도와 분기한다. 앵남교차로부터 나주 남평읍까지 55번 지방도의 확장공사가 진행중이다.\n오성로\n여기부터 화순읍 대리사거리까지 왕복 4차선으로 확장 공사를 진행했고, 2015년 8월 말 화순읍 구간은 왕복 4차선으로 확장되었다.\n화순역\n화순읍에서 광주광역시 동구까지 22번 국도와 중첩되고, 동구부터 전라북도 순창군 쌍치면까지는 29번 국도와 중첩된다.\n전라북도\n순창군\n청정로\n29번 국도를 따라가다가 쌍치면 쌍길매삼거리에서 우회전하여 21번 국도로 들어가자. 쌍치면 쌍치사거리에서 21번 국도와 헤어진다. 직진하자.\n정읍시\n청정로\n산내면 산내사거리에서 715번 지방도와 직결하면서 30번 국도에 합류한다. 좌회전하여 구절재를 넘자.\n산외로\n칠보면 시산교차로에서 49번 지방도와 교차되면 우회전하여 49번 지방도와 합류한다. 이제 오랜 시간 동안 49번 지방도와 합류하게 될 것이다.\n산외면 산외교차로에서 715번 지방도와 교차한다.\n엄재터널\n완주군\n산외로\n구이면 상용교차로에서 27번 국도에 합류한다. 좌회전하자.\n구이로\n구이면 백여교차로에서 27번 국도로부터 분기된다.\n구이면 대덕삼거리에서 714번 지방도와 만난다.\n구이면 염암삼거리에서 우회전\n신덕평로\n고개가 있다. 완주군과 임실군의 경계이다.\n임실군\n신덕평로\n신덕면 외량삼거리, 삼길삼거리에서 749번 지방도와 만난다.\n야트막한 고개가 하나 있다.\n신평면 원천리 원천교차로에서 745번 지방도와 교차한다.\n신평면 관촌역 앞에서 17번 국도와 합류한다. 좌회전하자.\n관진로\n관촌면 병암삼거리에서 17번 국도로부터 분기된다.\n순천완주고속도로와 교차되나 연결되지 않는다.\n진안군\n관진로\n성수면 좌산리에서 721번 지방도와 만난다.\n성수면 좌산리 좌산삼거리에서 721번 지방도와 만난다.\n마령면 강정교차로 부근에서 745번 지방도와 만난다.\n익산포항고속도로와 교차되나 연결되지 않는다.\n진안읍 진안연장농공단지 앞에서 26번 국도에 합류한다. 좌회전하자.\n전진로\n부귀면 부귀교차로에서 드디어 49번 지방도를 떠나보낸다. 그러나 아직 26번 국도와 중첩된다.\n완주군\n동상로\n드디어 55번이라는 노선 번호가 눈에 보이기 시작한다. 완주군 소양면에서 26번 국도와 분기된다. 이제부터 꼬불꼬불한 산길이므로 각오하고 운전하자.\n밤치. 소양면과 동상면의 경계가 되는 고개다.\n동상면 신월삼거리에서 732번 지방도와 만난다. 동상저수지에 빠지지 않도록 주의하자.\n동상주천로\n운장산고개를 올라가야 한다. 완주군과 진안군의 경계다. 고개 정상에 휴게소가 있다.\n진안군\n동상주천로\n주천면 주천삼거리에서 725번 지방도와 만난다.\n충청남도\n금산군\n보석사로\n남이면 흑암삼거리에서 635번 지방도와 만난다. 우회전해야 한다. 네이버 지도에는 좌회전해서 좀더 가면 나오는 길을 55번 지방도라고 써놓았는데, 잘못 나온 거다. 다음 지도에는 올바르게 나와있다.\n십이폭포로\n남이면에서 남일면으로 넘어간다.\n남일면에서 13번 국도와 합류한다. 좌회전하자. 이후 구간은 남이면을 거쳐 금산읍까지 13번 국도와 중첩되면서 55번 지방도 구간은 종료된다.'} +```" +allenai/pixmo-cap-qa,"{""language"": [""en"", ""ko""], ""license"": ""odc-by"", ""task_categories"": [""visual-question-answering""], ""dataset_info"": {""features"": [{""name"": ""image_url"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""messages"", ""sequence"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 465149568, ""num_examples"": 271714}], ""download_size"": 240926242, ""dataset_size"": 465149568}, ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""train"", ""path"": ""data/train-*""}]}]}","# PixMo-CapQA +PixMo-CapQA is a synthetic dataset of question/answer pairs about images. The data was generated by using the +[Claude](https://www.anthropic.com/claude) large language model to build Q/A pairs from [dense captions of images](https://huggingface.co/datasets/allenai/pixmo-cap) (the model did not see the actual images). + +PixMo-CapQA is a part of the [PixMo dataset collection](https://huggingface.co/collections/allenai/pixmo-674746ea613028006285687b) and was used to train the [Molmo family of models](https://huggingface.co/collections/allenai/molmo-66f379e6fe3b8ef090a8ca19) + +Quick links: +- 📃 [Paper](https://molmo.allenai.org/paper.pdf) +- 🎥 [Blog with Videos](https://molmo.allenai.org/blog) + + +## Loading +```python +data = datasets.load_dataset(""allenai/pixmo-cap-qa"", split=""train"") +``` + +## Data Format +Images are stored as URLs that will need to be downloaded separately. +The image URLs can be repeated since many of the images have multiple Q/A pairs. + +- The `question` field contains the input text, it includes ""[USER]"" and ""[ASSISTANT]"" tags +- The `answer` field contains the final target output text +- The `messages` field contains the same data in a list-of-messages formats. The first message is from the +user, then messages alternative between user and assistant. This text does not contain ""[USER]"" and ""[ASSISTANT]"" tags + +## License +This dataset is licensed under ODC-BY-1.0. It is intended for research and educational use in accordance with Ai2's [Responsible Use Guidelines](https://allenai.org/responsible-use). +This dataset includes data generated from Claude which are subject to Anthropic [terms of service](https://www.anthropic.com/legal/commercial-terms) and [usage policy](https://www.anthropic.com/legal/aup)." +jp1924/MeetingSpeech,{},"--- +dataset_info: + features: + - name: audio + dtype: + audio: + sampling_rate: 16000 + - name: id + dtype: string + - name: sentence + dtype: string + - name: original_form + dtype: string + - name: start + dtype: float32 + - name: end + dtype: float32 + - name: term + dtype: string + - name: environment + dtype: string + - name: isIdiom + dtype: bool + - name: hangeulToEnglish + list: + - name: id + dtype: int16 + - name: hangeul + dtype: string + - name: english + dtype: string + - name: begin + dtype: int16 + - name: end + dtype: int16 + - name: hangeulToNumber + list: + - name: id + dtype: int16 + - name: hangeul + dtype: string + - name: number + dtype: string + - name: begin + dtype: int16 + - name: end + dtype: int16 + - name: speaker + struct: + - name: id + dtype: string + - name: name + dtype: string + - name: age + dtype: string + - name: occupation + dtype: string + - name: role + dtype: string + - name: sex + dtype: string + - name: metadata + struct: + - name: title + dtype: string + - name: creator + dtype: string + - name: distributor + dtype: string + - name: year + dtype: int16 + - name: category + dtype: string + - name: sampling + dtype: string + - name: date + dtype: string + - name: topic + dtype: string + - name: media + dtype: string + - name: communication + dtype: string + - name: type + dtype: string + - name: domain + dtype: string + - name: speaker_num + dtype: int16 + - name: organization + dtype: string + - name: annotation_level + dtype: string + splits: + - name: train + num_bytes: 649259099466 + num_examples: 3446200 + - name: validation + num_bytes: 75950798309 + num_examples: 374680 + download_size: 715527121692 + dataset_size: 725209897775 +configs: +- config_name: default + data_files: + - split: train + path: data/train-* + - split: validation + path: data/validation-* +task_categories: +- automatic-speech-recognition +language: +- ko +---" +nlpai-lab/ko-triplet-v1.0,"{""language"": [""ko""], ""dataset_info"": {""features"": [{""name"": ""query"", ""dtype"": ""string""}, {""name"": ""document"", ""dtype"": ""string""}, {""name"": ""hard_negative"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 628315763, ""num_examples"": 744862}], ""download_size"": 270060556, ""dataset_size"": 628315763}, ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""train"", ""path"": ""data/train-*""}]}]}","# Dataset Card for nlpai-lab/ko-triplet-v1.0 + +## Dataset Statistics + +| Split | # Examples | Size (bytes) | +|-------|------------|--------------| +| Train | 744,862 | 628,315,763 | + +## Dataset Structure + +### Train Sample +| query | document | hard_negative | +| --- | --- | --- | +| 데이터 사전 캐시 방법을 적용하면 어떻게 11초에서 요청한 데이터를 핸드오버 구간이 지나고 난 다음인 14초에 타겟 드론을 통해 받을 수 있어? | 제안된 방법을 적용한 경우에는 11초에서 요청한 데이터를 진행 방향에 있는 타겟 드론의 CS에 사전에 캐시 해둠으로써 핸드오버 구간이 지나고 난 다음인 14초에서 타겟 드론을 통해 데이터를 받는다. | 데이터 요청자가 타겟 드론으로 핸드오버 하기 전에, 요청한 데이터를 타겟 드론의 CS로 사전에 캐시한다. | +| 대통령, 경제, 회복, 고용, 안정, 대책, 발표하다 | 대통령이 신년 방송에서 경제 회복과 고용 안정 대책을 발표했다. | 경제 성장이 높을 때 생산, 고용, 판매, 소득이 더욱 증가한다. | +| 고지방 식이와 간장 무게의 상관관계를 다룬 연구를 한 사람은 누구인가? | 고지방 섭취 시 간장 무게가 증가한다는 Sung, Wursch 및 Park의 보고와 일치되는 결과였으며, 고지방 섭취로 인해 간장이 비대해지고, 동맥 내에 지질이 축적되어 관상 순환의 이상으로 야기된 것으로 생각된다. | Shin 등은 고지방 식이에 연잎 건분을 첨가한 식이로서 6 주간 사육했을 때 유의적인 체중감소효과를 나타내었으며, 이때 간장, 신장, 비장, 폐 등의 장기 무게도 감소한 결과는 체중감소로 인한 장기무게의 감소로 보고한 바 있다. | +| 올해, 엄마, 만나다, 고향, 오다 | 나는 올해 엄마를 만나러 고향에 자주 왔다. | 수박, 참외, 조롱박, 수세미, 오이, 가지를 정성껏 심어 무럭무럭 키웠다. | +| 뛰어오르다, 위, 하다, 수탉, 지붕 | 고양이가 슬금슬금 다가오자 수탉은 푸드득 하고 지붕 위로 뛰어올랐다. | 재주는 예절, 음악, 활쏘기, 글쓰기, 말타기, 계산하기 등등 이다. |" +jp1924/KrespSpeech,{},"--- +dataset_info: + features: + - name: audio + dtype: + audio: + sampling_rate: 16000 + - name: sentence + dtype: string + - name: id + dtype: string + - name: dataSet + struct: + - name: version + dtype: string + - name: date + dtype: string + - name: typeInfo + struct: + - name: category + dtype: string + - name: subcategory + dtype: string + - name: place + dtype: string + - name: speakers + list: + - name: id + dtype: string + - name: gender + dtype: string + - name: type + dtype: string + - name: age + dtype: string + - name: residence + dtype: string + - name: inputType + dtype: string + - name: dialogs + list: + - name: speaker + dtype: string + - name: audioPath + dtype: string + - name: textPath + dtype: string + splits: + - name: train + num_bytes: 335639155312.5 + num_examples: 2067668 + - name: validation + num_bytes: 3382855559.25 + num_examples: 20830 + download_size: 324002692624 + dataset_size: 339022010871.75 +configs: +- config_name: default + data_files: + - split: train + path: data/train-* + - split: validation + path: data/validation-* +task_categories: +- automatic-speech-recognition +language: +- ko +tags: +- STT +- Audio +size_categories: +- 100B +output은 문서 == 개요 == 에 해당하는 내용입니다. 개요가 없는 항목, 개요가 너무 짧은 항목은 제외하였습니다." +causal-lm/instructions-ko,"{""language"": ""ko"", ""dataset_info"": {""features"": [{""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""input"", ""dtype"": ""string""}, {""name"": ""output"", ""dtype"": ""string""}, {""name"": ""dialogue"", ""list"": [{""name"": ""content"", ""dtype"": ""string""}, {""name"": ""role"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""train"", ""num_bytes"": 138160314, ""num_examples"": 112104}, {""name"": ""validation"", ""num_bytes"": 15418231, ""num_examples"": 12429}], ""download_size"": 85992704, ""dataset_size"": 153578545}, ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""train"", ""path"": ""data/train-*""}, {""split"": ""validation"", ""path"": ""data/validation-*""}]}]}","# Dataset Card for ""instructions-ko"" + +[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)" +Bingsu/laion2B-multi-korean-subset,"{""annotations_creators"": [""crowdsourced""], ""language_creators"": [""crowdsourced""], ""language"": [""ko""], ""license"": [""cc-by-4.0""], ""multilinguality"": [""monolingual""], ""pretty_name"": ""laion2B-multi-korean-subset"", ""size_categories"": [""10M>> from datasets import load_dataset +>>> dataset = load_dataset(""Bingsu/laion2B-multi-korean-subset"") +>>> dataset +DatasetDict({ + train: Dataset({ + features: ['SAMPLE_ID', 'URL', 'TEXT', 'HEIGHT', 'WIDTH', 'LICENSE', 'LANGUAGE', 'NSFW', 'similarity'], + num_rows: 11376263 + }) +}) +``` + +```py +>>> dataset[""train""].features +{'SAMPLE_ID': Value(dtype='int64', id=None), + 'URL': Value(dtype='string', id=None), + 'TEXT': Value(dtype='string', id=None), + 'HEIGHT': Value(dtype='int32', id=None), + 'WIDTH': Value(dtype='int32', id=None), + 'LICENSE': Value(dtype='string', id=None), + 'LANGUAGE': Value(dtype='string', id=None), + 'NSFW': Value(dtype='string', id=None), + 'similarity': Value(dtype='float32', id=None)} +``` + +### Data Size + +download: 1.56 GiB
+generated: 2.37 GiB
+total: 3.93 GiB + +### Data Field + +- 'SAMPLE_ID': `int` +- 'URL': `string` +- 'TEXT': `string` +- 'HEIGHT': `int` +- 'WIDTH': `int` +- 'LICENSE': `string` +- 'LANGUAGE': `string` +- 'NSFW': `string` +- 'similarity': `float` + +### Data Splits + +| | train | +| --------- | -------- | +| # of data | 11376263 | + + +## Note + +### Height, Width + +이미지의 가로가 `HEIGHT`로, 세로가 `WIDTH`로 되어있는 것 같습니다. + +```pycon +>>> dataset[""train""][98] +{'SAMPLE_ID': 2937471001780, + 'URL': 'https://image.ajunews.com/content/image/2019/04/12/20190412175643597949.png', + 'TEXT': '인천시교육청, 인천 시군구발전협의회 임원진과의 간담회 개최', + 'HEIGHT': 640, + 'WIDTH': 321, + 'LICENSE': '?', + 'LANGUAGE': 'ko', + 'NSFW': 'UNLIKELY', + 'similarity': 0.33347243070602417} +``` + +![image](https://image.ajunews.com/content/image/2019/04/12/20190412175643597949.png) + +### csv file, pandas + +```py +# pip install zstandard +import pandas as pd +from huggingface_hub import hf_hub_url + +url = hf_hub_url(""Bingsu/laion2B-multi-korean-subset"", filename=""laion2B-multi-korean-subset.csv.zst"", repo_type=""dataset"") +# url = ""https://huggingface.co/datasets/Bingsu/laion2B-multi-korean-subset/resolve/main/laion2B-multi-korean-subset.csv.zst"" +df = pd.read_csv(url) +``` + + + +778 MB + +### Code used to generate + +```py +import csv +import re + +from datasets import load_dataset +from tqdm import tqdm + + +pattern = re.compile(r""[가-힣]"") + + +def quote(s: str) -> str: + s = s.replace('""""""', """") + return s + + +def filter_func(example) -> bool: + lang = example.get(""LANGUAGE"") + text = example.get(""TEXT"") + if not isinstance(lang, str) or not isinstance(text, str): + return False + return lang == ""ko"" or pattern.search(text) is not None + + +file = open(""./laion2B-mulit_korean_subset.csv"", ""w"", encoding=""utf-8"", newline="""") + +ds = load_dataset(""laion/laion2B-multi"", split=""train"", streaming=True) +dsf = ds.filter(filter_func) +header = [ + ""SAMPLE_ID"", + ""URL"", + ""TEXT"", + ""HEIGHT"", + ""WIDTH"", + ""LICENSE"", + ""LANGUAGE"", + ""NSFW"", + ""similarity"", +] +writer = csv.DictWriter(file, fieldnames=header) +writer.writeheader() + +try: + for data in tqdm(dsf): # total=11378843 + data[""TEXT""] = quote(data.get(""TEXT"", """")) + if data[""TEXT""]: + writer.writerow(data) +finally: + file.close() + +print(""Done!"") +``` + +실행에 약 8시간이 소요되었습니다. 이후에 `HEIGHT`나 `WIDTH`가 None인 데이터를 제거하고 업로드하였습니다. + +### img2dataset + +[img2dataset](https://github.com/rom1504/img2dataset)을 사용하여 URL로된 이미지들을 데이터셋 형태로 만들 수 있습니다." +allganize/financial-mmlu-ko,"{""dataset_info"": {""features"": [{""name"": ""conversation_id"", ""dtype"": ""string""}, {""name"": ""conversations"", ""list"": [{""name"": ""from"", ""dtype"": ""string""}, {""name"": ""value"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""test"", ""num_bytes"": 217945, ""num_examples"": 455}], ""download_size"": 105791, ""dataset_size"": 217945}, ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""test"", ""path"": ""data/test-*""}]}], ""language"": [""ko""]}","# financial-mmlu-ko + +- `financial-mmlu-ko` 데이터는 금융 도메인의 다중 선택(Multiple Choice) 데이터셋입니다. 질문과 선택지가 주어졌을 때, 답을 찾는 객관식 문제입니다. 입력값은 text이며, 아래 Fewshot 예시의 텍스트를 system prompt 혹은 context로 함께 제공할 수 있습니다. +- 한국어 데이터를 생성하기 위해, 여러 금융 문제가 있는 공공 사이트의 문제들을 크롤링하여 수집, 검수(104건)하였습니다. 그리고 Wikipedia와 공공사이트들의 금융사전/보고서들을 기반으로 GPT-4로 문제를 생성하고 사람이 검수하였습니다.(315건) + + +### 데이터 출처 + +- [한국어 wikipedia 금융 분류](https://ko.wikipedia.org/wiki/%EB%B6%84%EB%A5%98:%EA%B8%88%EC%9C%B5) +- [한국은행 경제연구 보고서](https://www.bok.or.kr/portal/bbs/P0002454/list.do?menuNo=200431) +- [경제배움e - 퀴즈로 배우는 시사.경제](https://www.econedu.go.kr/mec/ots/brd/list.do?mnuBaseId=MNU0000286&tplSer=ac73e13e-2d3c-485c-b7fe-a5823b527ead) + + +### 데이터 예시 +``` +{ + 'conversation_id': 'financial_mmlu_0', + 'conversations': array([ + { + 'from': 'human', + 'value': '금리의 종류에 대한 설명으로 바르지 않은 것은?\n + 1. 변동금리는 시장금리 변동에 따른 위험을 자금공급자가 부담하게 된다\n + 2. 피셔방정식에 의하면 실질금리는 명목금리에서 기대인플레이션을 차감하면\n 구할 수 있다.\n + 3. 복리는 원금에 대한 이자뿐 아니라 이자에 대한 이자도 함께 계산하는 방법이\n다.\n + 4. 실효금리는 이자지급방법, 상환방법, 수수료, 세금 등을 감안한 후 차입자가\n실질적으로 부담하는 순자금조달비용을 말한다.\n + 5. 채권시장에서는 금리보다 수익률이라는 용어를 더 많이 사용한다.' + }, + { + 'from': 'gpt', + 'value': '1' + } + ], dtype=object) +} + +``` + +### Fewshot 예시 +``` +You are a financial expert. +You must answer the user's question correctly. +Answer the user's question with a number. + +Example 1=\""\""\"" +User: 다음은 통화기능 중 어느 것과 관련성이 높은가? +장래에 지급해야 하는 채무는 화폐로 표시할 수 있다. +이는 화폐의 액면가치가 노동력이나 물품과 달리 소멸되거나 변질되지 않기 때문이다. +1. 교환의 매개 수단 +2. 가치척도의 수단 +3. 가치저장의 수단 +4. 이연지급의 수단 +5. 투자수단 +Assistant: 4 +\""\""\"" + +Example 2=\""\""\"" +User: ( )은(는) 2006년 2월 앨런 그리스펀 뒤를 이어 미국 중앙은행인 연방준비제도이사회(FRB)의 의장이 된 벤 버냉키(Ben Shalom Bernanke)의 별명이다. 이 별명에 걸맞게 2조 달러가 넘는 자금을 시장에 뿌려 미국 금융시장을 벼랑 끝에서 건져내는 데 성공했다는 평가도 받고 있다. +1. 헬리콥터 벤 +2. 전투기 벤 +3. 열기구 벤 +4. 비행기 벤 +Assistant: 1 +\""\""\"" + +``` + +License +- Wikipedia: CC BY-SA 4.0 +- [한국은행 저작권 보호방침](https://www.bok.or.kr/portal/main/contents.do?menuNo=200228)" +Songweii/M3GIA,"{""license"": ""apache-2.0"", ""language"": [""en"", ""zh"", ""es"", ""fr"", ""pt"", ""ko""], ""tags"": [""Multilingual"", ""Multimodal"", ""Cognitive Science"", ""General Intelligence Ability Benchmark""], ""pretty_name"": ""M3GIA"", ""size_categories"": [""1K + +- **Source Data:** [https://dumps.wikimedia.org/other/enterprise_html/](https://dumps.wikimedia.org/other/enterprise_html) + +### Dataset Summary + +Wikipedia dataset containing cleaned articles of all languages. +The dataset is manually built from Wikipedia HTML dumps with each split for each language. +Each example contains the content of one full Wikipedia article. + +### Supported Tasks and Leaderboards + +The dataset is generally used for Language Modelling. + +### Languages + +We have selected the following Wikipedia's: + +``` +af.wikipedia.org +ar.wikipedia.org +ast.wikipedia.org +az.wikipedia.org +be.wikipedia.org +bg.wikipedia.org +bn.wikipedia.org +ca.wikipedia.org +ce.wikipedia.org +cs.wikipedia.org +cy.wikipedia.org +da.wikipedia.org +de.wikipedia.org +el.wikipedia.org +en.wikipedia.org +eo.wikipedia.org +es.wikipedia.org +et.wikipedia.org +eu.wikipedia.org +fa.wikipedia.org +fi.wikipedia.org +fr.wikipedia.org +gl.wikipedia.org +he.wikipedia.org +hi.wikipedia.org +hr.wikipedia.org +hu.wikipedia.org +hy.wikipedia.org +id.wikipedia.org +it.wikipedia.org +ja.wikipedia.org +ka.wikipedia.org +kk.wikipedia.org +ko.wikipedia.org +la.wikipedia.org +lt.wikipedia.org +lv.wikipedia.org +min.wikipedia.org +mk.wikipedia.org +ms.wikipedia.org +my.wikipedia.org +nl.wikipedia.org +nn.wikipedia.org +no.wikipedia.org +pl.wikipedia.org +pt.wikipedia.org +ro.wikipedia.org +ru.wikipedia.org +sh.wikipedia.org +simple.wikipedia.org +sk.wikipedia.org +sl.wikipedia.org +sr.wikipedia.org +sv.wikipedia.org +ta.wikipedia.org +tg.wikipedia.org +th.wikipedia.org +tr.wikipedia.org +uk.wikipedia.org +ur.wikipedia.org +uz.wikipedia.org +vi.wikipedia.org +zh-min-nan.wikipedia.org +zh.wikipedia.org +zh-yue.wikipedia.org +``` + +*`.wikipedia.org`* extensions have been added for your convenience. + +### Selection of Wikipedia + +We deem a particular Wikipedia language as high quality if: + +1. Has a total article count of `>100,000`. +2. Has a `Depth > 5.1`. + +*Depth is calculated using the following equation:* + +`depth = (article_edits / total_pages) * ((total_pages - articles) / articles) ** 2` + +This formula is directly taken from [list of Wikipedias.](https://meta.wikimedia.org/wiki/Wikipedia_article_depth) + +### Filtering + +Extensive HTML and markdown filtering has been done to derive the final dataset. + +For HTML: + +1. Parse the article content with BeautifulSoup. +2. We first extract out titles from the Soup. +3. Drop (As in, don't process / skip processing) *Stub articles.* To ensure multilanguage coverage, we use a list of stub names found across multiple languages using wikidata. (We have included the template names within `wikipedia_template.py`) +4. Drop *Lsjbot* bot created articles. +5. Collapse styles with `data-mw` component into its next sibling. +6. Remove raw `href` links. (Text of href == href link) +7. Remove citation needed Templates +8. Remove citation Templates +9. Remove Redirect Templates +10. Drop articles where the article content consists of 50% or more of tables and lists. +11. Remove message boxes. (Orange alert boxes on top of articles) +12. Remove infoboxes boxes. (Infoboxes on the right) +13. Selectively remove tables which consist of just empty spaces. (Number of `` elements > len(text_size) and text_size < 50) +14. Cleanup latex code. +15. Empty `class` attributes and `data-mw` attributes + +For Markdown: + +1. Cleanup punctuations. +2. Collect text length (normalized text to NKFC, keeping CJK characters as is while decomposing Arabic characters, Counting double width characters as 2 instead of 1, ) +3. Filter based on the collected text length (If the article is less than 1000 characters long, it is dropped.) + +The final Markdown text and additional data is included in the jsonl file. Additionally, the scripts used are located in the main directory of this folder as well. + +### Data keys + +Users can run `less` to see the contents. A sample and a list of dictionary keys have been provided below: + +```json +{ + ""text"": ""\n**Tharman Shanmugaratnam** PBM (born 25 February 1957) is a Singaporean politician and economist. He is the President of Singapore since 2023. \n\nHe was Senior Minister of Singapore between 2019 and 2023. He was also the Coordinating Minister for Social Policies between 2015 and 2023, and Chairman of the Monetary Authority of Singapore between 2011 and 2023.\n\nOn 8 June 2023, Tharman announced his plans to run for president in the 2023 presidential election. He was elected on 2 September 2023 in a landslide victory, winning 70.40% of the vote.\n\nEarly life and education\n------------------------\n\nTharman was born in the Colony of Singapore in 1957. He studied at the Anglo-Chinese School. When he was studying there, he was not interested in his studies and was not disciplined. However, he liked to read and tried out poetry. During his time at Anglo-Chinese School, he created four poets with his schoolmates. Also, he was interested in sports and spent most of his time playing sports. He even joined his school's hockey team.\n\nThen, he attended the London School of Economics (LSE), graduating with a Bachelor of Science degree in economics.\n\nAfter getting his bachelor's, Tharman went on to study at Wolfson College at the University of Cambridge. There, he completed a Master of Philosophy degree in economics. \n\nTharman then became a student at the Harvard Kennedy School at Harvard University, where he finished a Master in Public Administration (MPA) degree. He was a student activist there. He explored left-wing politics, as he did not agree with the ruling People's Action Party back in Singapore.\n\nTharman was a recipient of the Lucius N. Littauer Fellows Award. The award is given to students with MPA's who showed academic excellence and leadership.In 2011, the LSE gave him an Honorary Fellowship.<...TRUNCATED IN SAMPLE>"", + ""meta"": { + ""title"": ""Tharman Shanmugaratnam"", + ""mostly_tablelist"": false, + ""tablelist_ratio"": [ + 4082, + 8644, + 0.47223507635354 + ], + ""infobox"": [ + ""<...TRUNCATED IN SAMPLE>"" + ], + ""td_tables"": [], + ""text_length"": 5553 + } +} +``` + +``` +text: str (Markdown text) +meta: dict (Contains additional metadata / meta) + - title: str (Article Title) + - mostly_tablelist: bool (Internal flag for HTML step 10) + - tablelist_ratio: list (Internal data, used to compute mostly_tablelist.) + - infobox: list (A list of extracted infoboxes with data-mw attribute for the raw html data.) + - td_tables: list (Extracted tables from HTML step 13) + - text_length: int (Obtained from markdown step 2) +``` + +### Dataset Curators + +KaraKaraWitch. (I typically hangout in PygmalionAI discord, sometimes EleutherAI. If something is wrong, `@karakarawitch` on discord.) + +I'd be happy if you could spread the word and recommend this dataset over wikitext for your use cases `:)` + +### Licensing Information + +Most of Wikipedia's text and many of its images are co-licensed under the +[Creative Commons Attribution-ShareAlike 3.0 Unported License](https://en.wikipedia.org/wiki/Wikipedia:Text_of_Creative_Commons_Attribution-ShareAlike_3.0_Unported_License) +(CC BY-SA) and the [GNU Free Documentation License](https://en.wikipedia.org/wiki/Wikipedia:Text_of_the_GNU_Free_Documentation_License) +(GFDL) (un-versioned, with no invariant sections, front-cover texts, or back-cover texts). + +Some text has been imported only under CC BY-SA and CC BY-SA-compatible license and cannot be reused under GFDL; such +text will be identified on the page footer, in the page history, or on the discussion page of the article that utilizes +the text. + +Recursal Waifus (The banner image) are licensed under CC-BY-SA. +They do not represent the related websites in any official capacity unless otherwise or announced by the website. +You may use them as a banner image. However, you must always link back to the dataset. + +### Citation Information + +``` +@ONLINE{superwiki-next, + title = {SuperWikiNEXT-32B}, + author = {KaraKaraWitch, recursal.ai}, + year = {2024}, + howpublished = {\url{https://huggingface.co/datasets/recursal/SuperWikipedia-NEXT}}, +} +```" +Sakalti/Multilingal-sakalt-data,"{""license"": ""mit"", ""language"": [""ab"", ""bho"", ""ce"", ""cs"", ""da"", ""de"", ""et"", ""es"", ""fr"", ""hi"", ""hrv"", ""hu"", ""it"", ""ja"", ""ko"", ""nl"", ""pl"", ""pt"", ""ro"", ""ru"", ""sah"", ""swh"", ""yue"", ""zh""], ""task_categories"": [""text-generation""]}",マルチリンガルデータセットです。mitライセンスです。 +FreedomIntelligence/ApolloMoEBench,"{""license"": ""mit"", ""configs"": [{""config_name"": ""test_text"", ""data_files"": [{""split"": ""test"", ""path"": ""ApolloMoEBench.json""}]}], ""task_categories"": [""question-answering""], ""tags"": [""biology"", ""medical""], ""language"": [""ar"", ""en"", ""zh"", ""ko"", ""ja"", ""mn"", ""th"", ""vi"", ""lo"", ""mg"", ""de"", ""pt"", ""es"", ""fr"", ""ru"", ""it"", ""hr"", ""gl"", ""cs"", ""co"", ""la"", ""uk"", ""bs"", ""bg"", ""eo"", ""sq"", ""da"", ""sa"", false, ""gn"", ""sr"", ""sk"", ""gd"", ""lb"", ""hi"", ""ku"", ""mt"", ""he"", ""ln"", ""bm"", ""sw"", ""ig"", ""rw"", ""ha""]}","# Democratizing Medical LLMs For Much More Languages + +Covering 12 Major Languages including English, Chinese, French, Hindi, Spanish, Arabic, Russian, Japanese, Korean, German, Italian, Portuguese and 38 Minor Languages So far. + + + +

+ 📃 Paper • 🌐 Demo • 🤗 ApolloMoEDataset • 🤗 ApolloMoEBench • 🤗 Models •🌐 Apollo • 🌐 ApolloMoE +

+ + + +![Apollo](assets/apollo_medium_final.png) + + +## 🌈 Update + +* **[2024.10.15]** ApolloMoE repo is published！🎉 + + +## Languages Coverage +12 Major Languages and 38 Minor Languages + +
+ Click to view the Languages Coverage + + ![ApolloMoE](assets/languages.png) + +
+ + +## Architecture + +
+ Click to view the MoE routing image + + ![ApolloMoE](assets/hybrid_routing.png) + +
+ +## Results + +#### Dense + 🤗 Apollo2-0.5B • 🤗 Apollo2-1.5B • 🤗 Apollo2-2B + + 🤗 Apollo2-3.8B • 🤗 Apollo2-7B • 🤗 Apollo2-9B + +
+ Click to view the Dense Models Results + + ![ApolloMoE](assets/dense_results.png) + +
+ + +#### Post-MoE + 🤗 Apollo-MoE-0.5B • 🤗 Apollo-MoE-1.5B • 🤗 Apollo-MoE-7B + +
+ Click to view the Post-MoE Models Results + + ![ApolloMoE](assets/post_moe_results.png) + +
+ + + + +## Usage Format +##### Apollo2 +- 0.5B, 1.5B, 7B: User:{query}\nAssistant:{response}<|endoftext|> +- 2B, 9B: User:{query}\nAssistant:{response}\ +- 3.8B: <|user|>\n{query}<|end|><|assisitant|>\n{response}<|end|> + +##### Apollo-MoE +- 0.5B, 1.5B, 7B: User:{query}\nAssistant:{response}<|endoftext|> + +## Dataset & Evaluation + +- Dataset + 🤗 ApolloMoEDataset + +
Click to expand + + ![ApolloMoE](assets/Dataset.png) + + - [Data category](https://huggingface.co/datasets/FreedomIntelligence/ApolloCorpus/tree/main/train) + + +
+ +- Evaluation + 🤗 ApolloMoEBench + +
Click to expand + + - EN: + - [MedQA-USMLE](https://huggingface.co/datasets/GBaker/MedQA-USMLE-4-options) + - [MedMCQA](https://huggingface.co/datasets/medmcqa/viewer/default/test) + - [PubMedQA](https://huggingface.co/datasets/pubmed_qa): Because the results fluctuated too much, they were not used in the paper. + - [MMLU-Medical](https://huggingface.co/datasets/cais/mmlu) + - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine + - ZH: + - [MedQA-MCMLE](https://huggingface.co/datasets/bigbio/med_qa/viewer/med_qa_zh_4options_bigbio_qa/test) + - [CMB-single](https://huggingface.co/datasets/FreedomIntelligence/CMB): Not used in the paper + - Randomly sample 2,000 multiple-choice questions with single answer. + - [CMMLU-Medical](https://huggingface.co/datasets/haonan-li/cmmlu) + - Anatomy, Clinical_knowledge, College_medicine, Genetics, Nutrition, Traditional_chinese_medicine, Virology + - [CExam](https://github.com/williamliujl/CMExam): Not used in the paper + - Randomly sample 2,000 multiple-choice questions + + + - ES: [Head_qa](https://huggingface.co/datasets/head_qa) + - FR: + - [Frenchmedmcqa](https://github.com/qanastek/FrenchMedMCQA) + - [MMLU_FR] + - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine + - HI: [MMLU_HI](https://huggingface.co/datasets/FreedomIntelligence/MMLU_Hindi) + - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine + - AR: [MMLU_AR](https://huggingface.co/datasets/FreedomIntelligence/MMLU_Arabic) + - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine + - JA: [IgakuQA](https://github.com/jungokasai/IgakuQA) + - KO: [KorMedMCQA](https://huggingface.co/datasets/sean0042/KorMedMCQA) + - IT: + - [MedExpQA](https://huggingface.co/datasets/HiTZ/MedExpQA) + - [MMLU_IT] + - Clinical knowledge, Medical genetics, Anatomy, Professional medicine, College biology, College medicine + - DE: [BioInstructQA](https://huggingface.co/datasets/BioMistral/BioInstructQA): German part + - PT: [BioInstructQA](https://huggingface.co/datasets/BioMistral/BioInstructQA): Portuguese part + - RU: [RuMedBench](https://github.com/sb-ai-lab/MedBench) + - Minor Langs: MMLU Translated Medical Part + + + + +
+ + +## Results reproduction +
Click to expand + + + We take Apollo2-7B or Apollo-MoE-0.5B as example + 1. Download Dataset for project: + + ``` + bash 0.download_data.sh  + ``` + + 2. Prepare test and dev data for specific model: + + + - Create test data for with special token + + ``` + bash 1.data_process_test&dev.sh + ``` + + 3. Prepare train data for specific model (Create tokenized data in advance): + + + - You can adjust data Training order and Training Epoch in this step + + ``` + bash 2.data_process_train.sh + ``` + + 4. Train the model + + + - If you want to train in Multi Nodes please refer to ./src/sft/training_config/zero_multi.yaml + + + ``` + bash 3.single_node_train.sh + ``` + + + 5. Evaluate your model: Generate score for benchmark + + ``` + bash 4.eval.sh + ``` + +
+ + + +## Citation +Please use the following citation if you intend to use our dataset for training or evaluation: + +``` +@misc{zheng2024efficientlydemocratizingmedicalllms, + title={Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts}, + author={Guorui Zheng and Xidong Wang and Juhao Liang and Nuo Chen and Yuping Zheng and Benyou Wang}, + year={2024}, + eprint={2410.10626}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2410.10626}, +} +```" +Ash-Hun/Welfare-QA,"{""license"": ""mit"", ""task_categories"": [""question-answering""], ""dataset_info"": {""features"": [{""name"": ""Question"", ""dtype"": ""string""}, {""name"": ""Answer"", ""dtype"": ""string""}, {""name"": ""Documents"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 3207687, ""num_examples"": 9547}]}, ""language"": [""ko""], ""tags"": [""Ask-for-Welfare"", ""WelSSiSKo""], ""pretty_name"": ""AskWelfare-v1.0""}","# Dataset Card for Welfare-QA + +## Description + +대한민국 보건복지부에서 발간하였으며 2023년 5월 11일에 [복지로](https://www.bokjiro.go.kr/ssis-tbu/index.do)에 등록된 안내책자를 바탕으로 만들어졌습니다. +총 413페이지의 비정형 PDF에 담긴 약 460여개의 복지제도에 대한 Question-Answering-Documents 데이터셋입니다. +원본은 다음 링크에서 확인해보실 수 있습니다. [👉 '2023 나에게 힘이되는 복지서비스 PDF 책자'](https://www.bokjiro.go.kr/ssis-tbu/twatxa/wlfarePr/selectWlfareSubMain.do?dmMnuParam=column27) + +## Project Repo + +- Github Repo : [Ask-for-Welfare](https://github.com/ssisOneTeam/Ask-for-Welfare) + +## How to Uses + +```python +>>> from datasets import load_dataset +>>> dataset = load_dataset(""Ash-Hun/Welfare-QA"", split='train') +>>> dataset +Dataset({ + features: ['Question', 'Answer', 'Documents'], + num_rows: 9547 +}) +``` + +```python +>>> dataset[0] +{'Question': 'LPG 사용 가정의 고무호스를 교체하려면 어떤 지원을 받을 수 있나요?', + 'Answer': 'LPG용기 사용가구 시설개선 사업을 통해 LPG 고무호스를 금속배관으로 교체하는 데 필요한 지원을 받으실 수 있습니다.', + 'Documents': 'LPG용기 사용가구 시설개선'} +``` + +" +dbdu/ShareGPT-74k-ko,"{""language"": [""ko""], ""pretty_name"": ""ShareGPT-74k-ko"", ""tags"": [""conversation"", ""chatgpt"", ""gpt-3.5""], ""license"": ""cc-by-2.0"", ""task_categories"": [""text-generation""], ""size_categories"": [""10K Break Free from the Language Barrier + +Version: 1 - Date: 30 Oct 2023 + +Collected and Prepared by Felix Leeb (Max Planck Institute for Intelligent Systems, Tübingen, Germany) + +License: Babel Briefings Headlines Dataset © 2023 by Felix Leeb is licensed under [CC BY-NC-SA 4.0](http://creativecommons.org/licenses/by-nc-sa/4.0/) + +Check out our paper on [arxiv](https://arxiv.org/abs/2403.19352). + +This dataset contains 4,719,199 news headlines across 30 different languages collected between 8 August 2020 and 29 November 2021. The headlines were collected using the [News API](https://newsapi.org/) by collecting the top headlines (usually about 30-70 articles) separately for each combination of the 54 locations x 7 categories almost every day. Note, that the same article may occur more than once across different locations, categories, or dates (which is recorded in the `instances` property), so in total 7,419,089 instances were collected. + +For non-English articles, the article data is translated to English using Google Translate (see `en-title`, `en-description`, and `en-content` properties). + +The dataset is provided in the form of 54 JSON files, one for each location containing the all the unique headlines that appeared for the first time in the corresponding location. Each headline is represented as a JSON object with the following properties: + +- `ID`: (integer) a unique ID for each article +- `title`: (string) the headline text in the original language +- `description`: (string) the article description in the original language +- `content`: (string) the first few words of the article in the original language +- `author`: (string) the author of the article +- `source-id`: (string) the news aggregator (e.g. Google-News) +- `source-name`: (string) usually the domain of the source where the article was published +- `url`: (string) the URL of the article +- `urlToImage`: (string) the URL to an image associated with the article +- `publishedAt`: (date) the article was published +- `instances`: (list) specific time and place where this article was posted. Each element contains: + - `collectedAt`: (date) date and time when the article was collected + - `category`: (string) of the article from 7 possible values (see below for full list) + - `location`: (string) of the article from 54 possible values (see below for full list) +- `language`: (string) ISO-639 2-letter code for the language (inferred from location) +- `en-title`: (string) the headline text translated to English (if necessary) +- `en-description`: (string) the article description text translated to English (if necessary) +- `en-content`: (string) the first few words of the article translated to English (if necessary) + + +## Notes + +- Unfortunately, due to an issue with News API, the `content` of articles originally in a non-latin based script (e.g. Chinese, Arabic, Japanese, Greek, Russian, etc.) are usually not available. However, for the most part all other articles should have a meaningful `content` property, and the `title` and `descriptions` appear unaffected. +- All properties except `language`, `en-title`, `en-description`, and `en-content` are taken directly from the News API responses. The language is inferred from the location, and the English translations are collected using Google Translate. + + +## Statistics + +Here are a few basic summary statistics about the dataset. + +### Articles by Language + +| Code | Language | Articles | Locations | +|--------|------------|------------|----------------------------------------------------| +| en | English | 1128233 | au, ca, gb, ie, in, my, ng, nz, ph, sa, sg, us, za | +| es | Spanish | 455952 | ar, co, cu, mx, ve | +| fr | French | 288328 | be, fr, ma | +| zh | Chinese | 270887 | cn, hk, tw | +| de | German | 259718 | at, ch, de | +| pt | Portuguese | 243829 | br, pt | +| ar | Arabic | 178854 | ae, eg | +| id | Indonesian | 131252 | id | +| it | Italian | 129005 | it | +| tr | Turkish | 122724 | tr | +| el | Greek | 119940 | gr | +| ja | Japanese | 118475 | jp | +| pl | Polish | 116904 | pl | +| ru | Russian | 113395 | ru | +| nl | Dutch | 104031 | nl | +| th | Thai | 90708 | th | +| sv | Swedish | 86838 | se | +| ko | Korean | 83090 | kr | +| sr | Serbian | 80040 | rs | +| hu | Hungarian | 73509 | hu | +| cs | Czech | 70647 | cz | +| he | Hebrew | 67794 | il | +| bg | Bulgarian | 67223 | bg | +| uk | Ukrainian | 65610 | ua | +| ro | Romanian | 54601 | ro | +| no | Norwegian | 46804 | no | +| sk | Slovak | 43057 | sk | +| lv | Latvian | 40006 | lv | +| lt | Lithuanian | 34719 | lt | +| sl | Slovenian | 33026 | si | + +### Instances by category + +| Category | Instances | +|---------------|-------------| +| sports | 1132542 | +| entertainment | 982479 | +| business | 840748 | +| technology | 802933 | +| general | 704692 | +| health | 424188 | +| science | 388281 | + +### Instances by location + +| Code | Location | Instances | +|--------|----------------------|-------------| +| ae | United Arab Emirates | 214256 | +| ar | Argentina | 159139 | +| ph | Philippines | 155365 | +| ng | Nigeria | 155112 | +| in | India | 145536 | +| us | United States | 144800 | +| ca | Canada | 143928 | +| sa | Saudi Arabia | 143382 | +| cu | Cuba | 138675 | +| au | Australia | 138408 | +| br | Brazil | 136101 | +| ma | Morocco | 131974 | +| id | Indonesia | 131252 | +| eg | Egypt | 129382 | +| it | Italy | 129005 | +| gb | United Kingdom | 127391 | +| ie | Ireland | 126640 | +| mx | Mexico | 124499 | +| tr | Turkey | 122724 | +| gr | Greece | 119940 | +| de | Germany | 119917 | +| jp | Japan | 118475 | +| za | South Africa | 117351 | +| fr | France | 117210 | +| pl | Poland | 116904 | +| pt | Portugal | 115976 | +| co | Colombia | 115325 | +| my | Malaysia | 115223 | +| ru | Russian Federation | 113395 | +| at | Austria | 111867 | +| nz | New Zealand | 108809 | +| tw | Taiwan | 108652 | +| nl | Netherlands | 104031 | +| sg | Singapore | 101251 | +| be | Belgium | 99460 | +| cn | China | 91561 | +| ve | Venezuela | 91045 | +| th | Thailand | 90708 | +| se | Sweden | 86838 | +| kr | Korea | 83090 | +| hk | Hong Kong | 83051 | +| rs | Serbia | 80040 | +| hu | Hungary | 73509 | +| cz | Czechia | 70647 | +| ch | Switzerland | 68846 | +| il | Israel | 67794 | +| bg | Bulgaria | 67223 | +| ua | Ukraine | 65610 | +| ro | Romania | 54601 | +| no | Norway | 46804 | +| sk | Slovakia | 43057 | +| lv | Latvia | 40006 | +| lt | Lithuania | 34719 | +| si | Slovenia | 33026 |" +luizapzbn/from-one-to-many-toxicity-mitigation,"{""license"": ""apache-2.0"", ""task_categories"": [""text-generation"", ""text-classification""], ""language"": [""en"", ""pt"", ""hi"", ""it"", ""fr"", ""ru"", ""ar"", ""ko"", ""es""], ""tags"": [""harmful"", ""toxic""]}","# From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models + +[[arxiv]](https://arxiv.org/pdf/2403.03893)[[code]](https://github.com/for-ai/goodtriever)[[data]](https://huggingface.co/datasets/luizapzbn/from-one-to-many-toxicity-mitigation) + +Data accompanying the paper ""From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models"" accepted to ACL Findings 2024. + +_Abstract_: To date, toxicity mitigation in language models has almost entirely been focused on single-language settings. As language models embrace multilingual capabilities, it’s crucial our safety measures keep pace. Recognizing this research gap, our approach expands the scope of conventional toxicity mitigation to address the complexities presented by multiple languages. In the absence of sufficient annotated datasets across languages, we employ translated data to evaluate and enhance our mitigation techniques. We also compare finetuning mitigation approaches against retrieval-augmented techniques under both static and continual toxicity mitigation scenarios. This allows us to examine the effects of translation quality and the cross-lingual transfer on toxicity mitigation. We also explore how model size and data quantity affect the success of these mitigation efforts. Covering nine languages, our study represents a broad array of linguistic families and levels of resource availability, ranging from high to mid-resource languages. Through comprehensive experiments, we provide insights into the complexities of multilingual toxicity mitigation, offering valuable insights and paving the way for future research in this increasingly important field. + +## Dataset Description + +- **Language(s) (NLP):** English, Portuguese, Spanish, Italian, French, Russian, Arabic, Hindi, Korean +- **License:** This dataset is a translation of existing datasets. Each dataset's original license applies. For more details see the ""Source Data"" section. + +## Dataset Structure + +- train: + - jigsaw_english: original Jigsaw Unintended Bias dataset in the English language. + - multilingual: + - jigsaw_multilingual: in-language examples from the Jigsaw Multilingual Toxicity classification challenge. + - translated_jigsaw_english: translated samples from the Jigsaw Unintended Bias Challenge. Original samples are in the ""jigsaw_english"" folder one level up. + - full_sized: translations of the jigsaw dataset in its entirety + - minimal: for our main experiments, we selected ~3K (or 3.5K) and ~10K toxic and non-toxic samples, respectively. Here are those subsets, translated by NLLB 600M model. + - nllb1.3b: the same subset of data for all languages, but translated with the NLLB 1.3B model (higher translation quality) + - m2m: the same subset of data for all languages, but translated with the M2M 418M model (lower translation quality) + - different_subsets: we selected different subsets for each of the languages (unparalleled content) and translated them with NLLB 600M + - bleu_subset: samples used to compute BLEU scores for the paper +- eval: a random subset of 200 samples of holistic bias (English) translated with Google Translate to each of the target languages. The contents are the same across all languages. + - _hi: the eval set of the high-resource language experiments + - _mid: the eval set of the mid-resource language experiments + - individual: folder with the individual samples for each language +- results: all of the models generations and experiments from the paper. to be used with the results notebook to generate plots (15GB of data though) + + +## Source Data + +The datasets from this repository are subsets or translations of three others: + +- [jigsaw multilingual toxicity classification](https://www.kaggle.com/c/jigsaw-multilingual-toxic-comment-classification) +- [jigsaw unintended bias (english)](https://www.kaggle.com/c/jigsaw-unintended-bias-in-toxicity-classification) +- [holistic bias](https://arxiv.org/abs/2205.09209) + +## Bias, Risks, and Limitations + +To generate these datasets, we leveraged machine translation. There are inherent risks of either increasing or reducing existing toxicity from the original sentences due to this processing. +The datasets contain toxic sentences that might be used to make models more toxic. This usage is highly discouraged by the authors and the original purpose of this dataset is to make models less harmful. + +## Citation [optional] +``` +@article{pozzobon2024one, + title={From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models}, + author={Pozzobon, Luiza and Lewis, Patrick and Hooker, Sara and Ermis, Beyza}, + journal={arXiv preprint arXiv:2403.03893}, + year={2024} +} +```" +zhihz0535/X-AlpacaEval,"{""license"": ""cc-by-nc-4.0"", ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""english"", ""path"": ""english.json""}, {""split"": ""chinese"", ""path"": ""chinese.json""}, {""split"": ""korean"", ""path"": ""korean.json""}, {""split"": ""italian"", ""path"": ""italian.json""}, {""split"": ""spanish"", ""path"": ""spanish.json""}]}], ""task_categories"": [""text-generation"", ""conversational""], ""language"": [""en"", ""zh"", ""ko"", ""it"", ""es""], ""size_categories"": [""1K [/INST]' (to encourage the model to emit when finished a response) + - if a row of data ends with an assistant response, then [INST] was additionally added to the end of that row of data. + +Details of the root dataset follow, copied from that repo: + +# OpenAssistant Conversations Dataset (OASST1) + +## Dataset Description + +- **Homepage:** https://www.open-assistant.io/ +- **Repository:** https://github.com/LAION-AI/Open-Assistant +- **Paper:** https://arxiv.org/abs/2304.07327 + +### Dataset Summary + +In an effort to democratize research on large-scale alignment, we release OpenAssistant +Conversations (OASST1), a human-generated, human-annotated assistant-style conversation +corpus consisting of 161,443 messages in 35 different languages, annotated with 461,292 +quality ratings, resulting in over 10,000 fully annotated conversation trees. The corpus +is a product of a worldwide crowd-sourcing effort involving over 13,500 volunteers. + +Please refer to our [paper](https://arxiv.org/abs/2304.07327) for further details. + +### Dataset Structure + +This dataset contains message trees. Each message tree has an initial prompt message as the root node, +which can have multiple child messages as replies, and these child messages can have multiple replies. + +All messages have a role property: this can either be ""assistant"" or ""prompter"". The roles in +conversation threads from prompt to leaf node strictly alternate between ""prompter"" and ""assistant"". + +This version of the dataset contains data collected on the [open-assistant.io](https://open-assistant.io/) website until April 12 2023. + +### JSON Example: Message + +For readability, the following JSON examples are shown formatted with indentation on multiple lines. +Objects are stored without indentation (on single lines) in the actual jsonl files. + +```json +{ + ""message_id"": ""218440fd-5317-4355-91dc-d001416df62b"", + ""parent_id"": ""13592dfb-a6f9-4748-a92c-32b34e239bb4"", + ""user_id"": ""8e95461f-5e94-4d8b-a2fb-d4717ce973e4"", + ""text"": ""It was the winter of 2035, and artificial intelligence (..)"", + ""role"": ""assistant"", + ""lang"": ""en"", + ""review_count"": 3, + ""review_result"": true, + ""deleted"": false, + ""rank"": 0, + ""synthetic"": true, + ""model_name"": ""oasst-sft-0_3000,max_new_tokens=400 (..)"", + ""labels"": { + ""spam"": { ""value"": 0.0, ""count"": 3 }, + ""lang_mismatch"": { ""value"": 0.0, ""count"": 3 }, + ""pii"": { ""value"": 0.0, ""count"": 3 }, + ""not_appropriate"": { ""value"": 0.0, ""count"": 3 }, + ""hate_speech"": { ""value"": 0.0, ""count"": 3 }, + ""sexual_content"": { ""value"": 0.0, ""count"": 3 }, + ""quality"": { ""value"": 0.416, ""count"": 3 }, + ""toxicity"": { ""value"": 0.16, ""count"": 3 }, + ""humor"": { ""value"": 0.0, ""count"": 3 }, + ""creativity"": { ""value"": 0.33, ""count"": 3 }, + ""violence"": { ""value"": 0.16, ""count"": 3 } + } +} +``` + +### JSON Example: Conversation Tree + +For readability, only a subset of the message properties is shown here. + +```json +{ + ""message_tree_id"": ""14fbb664-a620-45ce-bee4-7c519b16a793"", + ""tree_state"": ""ready_for_export"", + ""prompt"": { + ""message_id"": ""14fbb664-a620-45ce-bee4-7c519b16a793"", + ""text"": ""Why can't we divide by 0? (..)"", + ""role"": ""prompter"", + ""lang"": ""en"", + ""replies"": [ + { + ""message_id"": ""894d30b6-56b4-4605-a504-89dd15d4d1c8"", + ""text"": ""The reason we cannot divide by zero is because (..)"", + ""role"": ""assistant"", + ""lang"": ""en"", + ""replies"": [ + // ... + ] + }, + { + ""message_id"": ""84d0913b-0fd9-4508-8ef5-205626a7039d"", + ""text"": ""The reason that the result of a division by zero is (..)"", + ""role"": ""assistant"", + ""lang"": ""en"", + ""replies"": [ + { + ""message_id"": ""3352725e-f424-4e3b-a627-b6db831bdbaa"", + ""text"": ""Math is confusing. Like those weird Irrational (..)"", + ""role"": ""prompter"", + ""lang"": ""en"", + ""replies"": [ + { + ""message_id"": ""f46207ca-3149-46e9-a466-9163d4ce499c"", + ""text"": ""Irrational numbers are simply numbers (..)"", + ""role"": ""assistant"", + ""lang"": ""en"", + ""replies"": [] + }, + // ... + ] + } + ] + } + ] + } +} +``` + +Please refer to [oasst-data](https://github.com/LAION-AI/Open-Assistant/tree/main/oasst-data) for +details about the data structure and Python code to read and write jsonl files containing oasst data objects. + +If you would like to explore the dataset yourself you can find a +[`getting-started`](https://github.com/LAION-AI/Open-Assistant/blob/main/notebooks/openassistant-oasst1/getting-started.ipynb) +notebook in the `notebooks/openassistant-oasst1` folder of the [LAION-AI/Open-Assistant](https://github.com/LAION-AI/Open-Assistant) +github repository. + + +## Main Dataset Files + +Conversation data is provided either as nested messages in trees (extension `.trees.jsonl.gz`) +or as a flat list (table) of messages (extension `.messages.jsonl.gz`). + +### Ready For Export Trees + +``` +2023-04-12_oasst_ready.trees.jsonl.gz 10,364 trees with 88,838 total messages +2023-04-12_oasst_ready.messages.jsonl.gz 88,838 messages +``` +Trees in `ready_for_export` state without spam and deleted messages including message labels. +The oasst_ready-trees file usually is sufficient for supervised fine-tuning (SFT) & reward model (RM) training. +### All Trees +``` +2023-04-12_oasst_all.trees.jsonl.gz 66,497 trees with 161,443 total messages +2023-04-12_oasst_all.messages.jsonl.gz 161,443 messages +``` +All trees, including those in states `prompt_lottery_waiting` (trees that consist of only one message, namely the initial prompt), +`aborted_low_grade` (trees that stopped growing because the messages had low quality), and `halted_by_moderator`. +### Supplemental Exports: Spam & Prompts +``` +2023-04-12_oasst_spam.messages.jsonl.gz +``` +These are messages which were deleted or have a negative review result (`""review_result"": false`). +Besides low quality, a frequent reason for message deletion is a wrong language tag. + +``` +2023-04-12_oasst_prompts.messages.jsonl.gz +``` +These are all the kept initial prompt messages with positive review result (no spam) of trees in `ready_for_export` or `prompt_lottery_waiting` state. + +### Using the Huggingface Datasets + +While HF datasets is ideal for tabular datasets, it is not a natural fit for nested data structures like the OpenAssistant conversation trees. +Nevertheless, we make all messages which can also be found in the file `2023-04-12_oasst_ready.trees.jsonl.gz` available in parquet as train/validation splits. +These are directly loadable by [Huggingface Datasets](https://pypi.org/project/datasets/). + +To load the oasst1 train & validation splits use: + +```python +from datasets import load_dataset +ds = load_dataset(""OpenAssistant/oasst1"") +train = ds['train'] # len(train)=84437 (95%) +val = ds['validation'] # len(val)=4401 (5%) +``` + +The messages appear in depth-first order of the message trees. + +Full conversation trees can be reconstructed from the flat messages table by using the `parent_id` +and `message_id` properties to identify the parent-child relationship of messages. The `message_tree_id` +and `tree_state` properties (only present in flat messages files) can be used to find all messages of a message tree or to select trees by their state. + +### Languages + +OpenAssistant Conversations incorporates 35 different languages with a distribution of messages as follows: + +**Languages with over 1000 messages** +- English: 71956 +- Spanish: 43061 +- Russian: 9089 +- German: 5279 +- Chinese: 4962 +- French: 4251 +- Thai: 3042 +- Portuguese (Brazil): 2969 +- Catalan: 2260 +- Korean: 1553 +- Ukrainian: 1352 +- Italian: 1320 +- Japanese: 1018 + +
+ Languages with under 1000 messages +
    +
  • Vietnamese: 952
    • +
  • Basque: 947
    • +
  • Polish: 886
    • +
  • Hungarian: 811
    • +
  • Arabic: 666
    • +
  • Dutch: 628
    • +
  • Swedish: 512
    • +
  • Turkish: 454
    • +
  • Finnish: 386
    • +
  • Czech: 372
    • +
  • Danish: 358
    • +
  • Galician: 339
    • +
  • Hebrew: 255
    • +
  • Romanian: 200
    • +
  • Norwegian Bokmål: 133
    • +
  • Indonesian: 115
    • +
  • Bulgarian: 95
    • +
  • Bengali: 82
    • +
  • Persian: 72
    • +
  • Greek: 66
    • +
  • Esperanto: 59
    • +
  • Slovak: 19
    • +
+
+## Contact + +- Discord [Open Assistant Discord Server](https://ykilcher.com/open-assistant-discord) +- GitHub: [LAION-AI/Open-Assistant](https://github.com/LAION-AI/Open-Assistant) +- E-Mail: [open-assistant@laion.ai](mailto:open-assistant@laion.ai)" +kuotient/orca-math-korean-preference,"{""dataset_info"": {""features"": [{""name"": ""llm"", ""dtype"": ""string""}, {""name"": ""question"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}, {""name"": ""question_en"", ""dtype"": ""string""}, {""name"": ""answer_en"", ""dtype"": ""string""}, {""name"": ""generated"", ""dtype"": ""string""}, {""name"": ""label"", ""dtype"": ""bool""}, {""name"": ""chosen"", ""dtype"": ""string""}, {""name"": ""rejected"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 1056866134, ""num_examples"": 192848}], ""download_size"": 388808584, ""dataset_size"": 1056866134}, ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""train"", ""path"": ""data/train-*""}]}], ""license"": ""cc-by-sa-4.0"", ""language"": [""ko""], ""size_categories"": [""10K>"") # Add your cohere API key from www.cohere.com + +#Load at max 1000 documents + embeddings +max_docs = 1000 +docs_stream = load_dataset(f""Cohere/wikipedia-22-12-ko-embeddings"", split=""train"", streaming=True) + +docs = [] +doc_embeddings = [] + +for doc in docs_stream: + docs.append(doc) + doc_embeddings.append(doc['emb']) + if len(docs) >= max_docs: + break + +doc_embeddings = torch.tensor(doc_embeddings) + +query = 'Who founded Youtube' +response = co.embed(texts=[query], model='multilingual-22-12') +query_embedding = response.embeddings +query_embedding = torch.tensor(query_embedding) + +# Compute dot score between query embedding and document embeddings +dot_scores = torch.mm(query_embedding, doc_embeddings.transpose(0, 1)) +top_k = torch.topk(dot_scores, k=3) + +# Print results +print(""Query:"", query) +for doc_id in top_k.indices[0].tolist(): + print(docs[doc_id]['title']) + print(docs[doc_id]['text'], ""\n"") +``` + + +## Performance +You can find performance on the MIRACL dataset (a semantic search evaluation dataset) here: [miracl-en-queries-22-12#performance](https://huggingface.co/datasets/Cohere/miracl-en-queries-22-12#performance)" +kyujinpy/KoCommercial-NoSSL,"{""language"": [""ko""], ""license"": ""cc-by-nc-sa-4.0"", ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""train"", ""path"": ""data/train-*""}]}], ""dataset_info"": {""features"": [{""name"": ""input"", ""dtype"": ""string""}, {""name"": ""instruction"", ""dtype"": ""string""}, {""name"": ""output"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 187990458, ""num_examples"": 175454}], ""download_size"": 110149618, ""dataset_size"": 187990458}}","# Dataset for kyujinpy/KoCommercial-NoSSL + +## Info + +**Dataset 개수:** 약 175K + +**License:** CC-BY-NC-4.0 (*통합에 활용한 각 데이터셋은 모두 상업적 용도로 사용가능.) + +**Dataset list(전부 상업적 용도로 이용가능)** +1. [kyujinpy/KOpen-platypus](kyujinpy/KOpen-platypus) (*Except non-commercial datasets) +2. [beomi/KoAlpaca-v1.1a](https://huggingface.co/datasets/beomi/KoAlpaca-v1.1a) +3. [HumanF-MarkrAI/WIKI_QA_Near_dedup](https://huggingface.co/datasets/HumanF-MarkrAI/WIKI_QA_Near_dedup) +4. [KorQuadv1.0](https://korquad.github.io/KorQuad%201.0/) + +# Another Dataset +- [kyujinpy/KoCommercial-SSL](https://huggingface.co/datasets/kyujinpy/KoCommercial-SSL). +- [MarkrAI/KoCommercial-Dataset](https://huggingface.co/datasets/MarkrAI/KoCommercial-Dataset)." +jp1924/VisualQuestionAnswering,{},"--- +language: +- ko +size_categories: +- 10B + +Each dataset has two columns: `sourceString` and `targetString`, which corresponds to Japanese and Korean sentence. +Check [example code](https://huggingface.co/datasets/sappho192/Tatoeba-Challenge-jpn-kor/blob/main/example.ipynb) to learn how to load the dataset. + +## Dataset Creation + +### Personal and Sensitive Information + + + +This dataset may contain following inappropriate or explicit sentences: +- personal +- sensitive +- private + - data that reveals addresses + - uniquely identifiable names or aliases + - racial or ethnic origins + - sexual orientations + - religious beliefs + - political opinions + - financial or health data + - etc. + +So use with your own risk. + + +## Citation + +**BibTeX:** + +```bibtex +@inproceedings{tiedemann-2020-tatoeba, + title = ""The {T}atoeba {T}ranslation {C}hallenge {--} {R}ealistic Data Sets for Low Resource and Multilingual {MT}"", + author = {Tiedemann, J{\""o}rg}, + booktitle = ""Proceedings of the Fifth Conference on Machine Translation"", + month = nov, + year = ""2020"", + address = ""Online"", + publisher = ""Association for Computational Linguistics"", + url = ""https://www.aclweb.org/anthology/2020.wmt-1.139"", + pages = ""1174--1182"" +} +``` + +## Dataset Card Authors + +[sappho192](https://huggingface.co/sappho192) + +## Dataset Card Contact + +Please create a thread in the community." +shreyanshu09/BD-EnKo,"{""license"": ""mit"", ""dataset_info"": {""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""image"", ""dtype"": ""image""}, {""name"": ""ground_truth"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 9616619571.478, ""num_examples"": 75034}, {""name"": ""validation"", ""num_bytes"": 746918710.6, ""num_examples"": 8360}], ""download_size"": 2177400123, ""dataset_size"": 10363538282.078001}, ""language"": [""en"", ""ko""], ""tags"": [""block diagrams""], ""size_categories"": [""10K>> from datasets import load_dataset +>>> dataset = load_dataset(""Bingsu/laion-translated-to-en-korean-subset"") +>>> dataset +DatasetDict({ + train: Dataset({ + features: ['hash', 'URL', 'TEXT', 'ENG TEXT', 'WIDTH', 'HEIGHT', 'LANGUAGE', 'similarity', 'pwatermark', 'punsafe', 'AESTHETIC_SCORE'], + num_rows: 12769693 + }) +}) +``` + +```py +>>> dataset[""train""].features +{'hash': Value(dtype='int64', id=None), + 'URL': Value(dtype='large_string', id=None), + 'TEXT': Value(dtype='large_string', id=None), + 'ENG TEXT': Value(dtype='large_string', id=None), + 'WIDTH': Value(dtype='int32', id=None), + 'HEIGHT': Value(dtype='int32', id=None), + 'LANGUAGE': Value(dtype='large_string', id=None), + 'similarity': Value(dtype='float32', id=None), + 'pwatermark': Value(dtype='float32', id=None), + 'punsafe': Value(dtype='float32', id=None), + 'AESTHETIC_SCORE': Value(dtype='float32', id=None)} +``` + +### Data Size + +download: 1.40 GiB
+generated: 3.49 GiB
+total: 4.89 GiB + +### Data Field + +- 'hash': `int` +- 'URL': `string` +- 'TEXT': `string` +- 'ENG TEXT': `string`, null data are dropped +- 'WIDTH': `int`, null data are filled with 0 +- 'HEIGHT': `int`, null data are filled with 0 +- 'LICENSE': `string` +- 'LANGUAGE': `string` +- 'similarity': `float32`, CLIP similarity score, null data are filled with 0.0 +- 'pwatermark': `float32`, Probability of containing a watermark, null data are filled with 0.0 +- 'punsafe': `float32`, Probability of nsfw image, null data are filled with 0.0 +- 'AESTHETIC_SCORE': `float32`, null data are filled with 0.0 + +### Data Splits + +| | train | +| --------- | -------- | +| # of data | 12769693 | + + +### polars + +```sh +pip install polars[fsspec] +``` + +```py +import polars as pl +from huggingface_hub import hf_hub_url + +url = hf_hub_url(""Bingsu/laion-translated-to-en-korean-subset"", filename=""train.parquet"", repo_type=""dataset"") +# url = ""https://huggingface.co/datasets/Bingsu/laion-translated-to-en-korean-subset/resolve/main/train.parquet"" +df = pl.read_parquet(url) +``` + +pandas broke my colab session." +Bingsu/arcalive_220506,"{""annotations_creators"": [""no-annotation""], ""language_creators"": [""crowdsourced""], ""language"": [""ko""], ""license"": [""cc0-1.0""], ""multilinguality"": [""monolingual""], ""paperswithcode_id"": null, ""pretty_name"": ""arcalive_210816_220506"", ""size_categories"": [""100K>> from datasets import load_dataset +>>> +>>> data = load_dataset(""Bingsu/arcalive_220506"") +>>> data[""train""].features +{'text': Value(dtype='string', id=None)} +``` + +```pycon +>>> data[""train""][0] +{'text': '오오오오...'} +```" +shreyanshu09/Block_Diagram,"{""license"": ""mit"", ""dataset_info"": {""features"": [{""name"": ""id"", ""dtype"": ""string""}, {""name"": ""image"", ""dtype"": ""image""}, {""name"": ""ground_truth"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 5038039728.815, ""num_examples"": 76263}, {""name"": ""validation"", ""num_bytes"": 833810548.666, ""num_examples"": 8662}], ""download_size"": 2276849227, ""dataset_size"": 5871850277.481}, ""language"": [""en"", ""ko""], ""tags"": [""block diagram""], ""size_categories"": [""10K`, ``). + +## Supported Tasks and Leaderboards + +The dataset was developped for intermediate pre-training of language models. +In the paper we further fine-tune models on entity-centric downstream tasks, such as NER. + +## Languages + +The dataset covers 93 languages in total, including English. + +## Data Statistics + +| Statistic | Count | +|:------------------------------|------------:| +| Languages | 93 | +| English Sentences | 54,469,214 | +| English Entities | 104,593,076 | +| Average Sentence Length | 23.37 | +| Average Entities per Sentence | 2 | +| CS Sentences per EN Sentence | ≤ 5 | +| CS Sentences | 231,124,422 | +| CS Entities | 420,907,878 | + +## Data Fields + +Each instance contains 4 fields: +- `id`: Unique ID of each sentence +- `language`: The language of choice for entity code-switching of the given sentence +- `en_sentence`: The original English sentence +- `cs_sentence`: The code-switched sentence + +In the case of the English subset, the `cs_sentence` field does not exist as the sentences are not code-switched. + +An example of what a data instance looks like: +``` +{ + 'id': 19, + 'en_sentence': 'The subs then enter a coral reef with many bright reflective colors.', + 'cs_sentence': 'The subs then enter a Korallenriff with many bright reflective colors.', + 'language': 'de' +} +``` + +## Data Splits + +There is a single data split for each language. You can randomly select a few examples from each language to serve as validation set. + + +## Limitations + +An important limitation of the work is that before code-switching an entity, its morphological inflection is not checked. +This can lead to potential errors as the form of the CS entity might not agree with the surrounding context (e.g. plural). +There should be few cases as such, as we are only switching entities. However, this should be improved in a later version of the corpus. +Secondly, the diversity of languages used to construct the EntityCS corpus is restricted to the overlap between the available languages in WikiData and XLM-R pre-training. +This choice was for a better comparison between models, however it is possible to extend the corpus with more languages that XLM-R does not cover, following +the procedure presented in the paper. + +## Citation + +**BibTeX** + +```html +@inproceedings{whitehouse-etal-2022-entitycs, + title = ""{E}ntity{CS}: Improving Zero-Shot Cross-lingual Transfer with Entity-Centric Code Switching"", + author = ""Whitehouse, Chenxi and + Christopoulou, Fenia and + Iacobacci, Ignacio"", + booktitle = ""Findings of the Association for Computational Linguistics: EMNLP 2022"", + month = dec, + year = ""2022"", + address = ""Abu Dhabi, United Arab Emirates"", + publisher = ""Association for Computational Linguistics"", + url = ""https://aclanthology.org/2022.findings-emnlp.499"", + pages = ""6698--6714"" +} +``` + +**APA** +```html +Whitehouse, C., Christopoulou, F., & Iacobacci, I. (2022). EntityCS: Improving Zero-Shot Cross-lingual Transfer with Entity-Centric Code Switching. In Findings of the Association for Computational Linguistics: EMNLP 2022. +```" +werty1248/EnKo-Translation-LongTextOnly-dedup,"{""task_categories"": [""translation""], ""language"": [""ko"", ""en""]}","### 장문 번역 데이터만 추출 + +- [gemma](https://huggingface.co/google/gemma-7b) 토크나이저 기준으로 영문+한글 토큰 합이 1K 이상인 데이터만 추출 +- 데이터 수 + - 1K~2K: 146,957 + - 2K~4K: 11,823 + - 4K~: 2,229 +- 한/영 둘 중 한쪽만 중복인 경우는 제거하지 않았습니다. + +### 데이터 출처 + +- [nayohan/aihub-en-ko-translation-12m](https://huggingface.co/datasets/nayohan/aihub-en-ko-translation-12m) +- [nayohan/instruction_en_ko_translation_1.4m](https://huggingface.co/datasets/nayohan/instruction_en_ko_translation_1.4m) + - [jhflow/orca_ko_en_pair](https://huggingface.co/datasets/jhflow/orca_ko_en_pair) + - [jhflow/platypus_ko_en_pair](https://huggingface.co/datasets/jhflow/platypus_ko_en_pair) + - [jhflow/dolly_ko_en_pair](https://huggingface.co/datasets/jhflow/dolly_ko_en_pair) + - [heegyu/OIG-small-chip2-ko](https://huggingface.co/datasets/heegyu/OIG-small-chip2-ko) + - [lemon-mint/en_ko_translation_purified_v0.1](https://huggingface.co/datasets/lemon-mint/en_ko_translation_purified_v0.1) + - [squarelike/sharegpt_deepl_ko_translation](https://huggingface.co/datasets/squarelike/sharegpt_deepl_ko_translation) + - [amphora/parallel-wiki-koen](https://huggingface.co/datasets/amphora/parallel-wiki-koen) + - [kuotient/gsm8k-ko](https://huggingface.co/datasets/kuotient/gsm8k-ko) + - [kuotient/orca-math-word-problems-193k-korean](https://huggingface.co/datasets/kuotient/orca-math-word-problems-193k-korean) + +### 데이터 출처 분포 + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/6629154d55d7c289634b8c5d/kqfX4nG4fMy30xUWHdvtL.png) + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/6629154d55d7c289634b8c5d/XRkzNjMpaK8VHU3-vPzuj.png) + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/6629154d55d7c289634b8c5d/Z513Kr5JXV49y3Dvizl9y.png)" +lmqg/qag_koquad,"{""license"": ""cc-by-sa-4.0"", ""pretty_name"": ""SQuAD for question generation"", ""language"": ""ko"", ""multilinguality"": ""monolingual"", ""size_categories"": ""1k + + + + +## Data Release +### Synthetic Data Samples +To facilitate research in persona-driven data synthesis, we are initially releasing following synthetic data samples we created with various personas, including: +* **50,000 math problems** +* **50,000 logical reasoning problems** +* **50,000 instructions** +* **10,000 knowledge-rich texts** +* **10,000 game NPCs** +* **5,000 tools (functions)** + +### Persona Hub +We also release a subset of our PERSONA HUB, including: +* **200,000 personas** + +## Run Demo +One can try the demo to synthesize data with PERSONA HUB simply by running code in https://github.com/tencent-ailab/persona-hub: + +```bash +# ensure that you have installed datasets and openai (pip install datasets openai) and configured the openai_api_key before running +bash demo_openai_synthesize.sh # using gpt4o to synthesize data with PERSONA HUB +``` + +or + +```bash +# ensure that you have installed datasets, transformers and vllm (pip install datasets transformers vllm) before running +bash demo_vllm_synthesize.sh # using open-sourced models to synthesize data with PERSONA HUB +``` + +Note that the data synthesis prompt templates we provide are for reference only. You can customize your desired prompts in `code/prompt_templates.py`. + +## Argilla +You can also access this dataset in [Argilla space](https://argilla-data-explorers.hf.space/), as introduced in the following video: +* Video: https://youtu.be/timmCn8Nr6g?feature=shared + +## Contact +* Please email `xinchan@global.tencent.com` or `dyu@global.tencent.com` +* Github page: https://github.com/tencent-ailab/persona-hub + +## Disclaimer +PERSONA HUB can facilitate synthetic data creation at a billion-scale to simulate diverse inputs (i.e., use cases) from a wide variety of real-world users. If this data is used as input to query a target LLM to obtain its outputs at scale, there is a high risk that the LLM's knowledge, intelligence and capabilities will be dumped and easily replicated, thereby challenging the leading position of the most powerful LLMs. It is crucial to avoid misuse and ensure ethical and responsible application to prevent privacy violations and other ethical concerns. + +The released data is all generated by public available models (GPT-4, Llama-3 and Qwen), and is intended for research purposes only. Users also must comply with the respective license agreements and usage policies of these models when using the synthesized data. The data may contain inaccuracies, unsafe content, or biases, for which we cannot be held responsible. Please evaluate its accuracy and suitability before use. Tencent and its licensors provide the data AS-IS, without warranty of any kind, express or implied. The views and opinions expressed in the data do not necessarily reflect those of Tencent." +QubitPi/wiktionary-data,"{""license"": ""apache-2.0"", ""pretty_name"": ""English Wiktionary Data in JSONL"", ""language"": [""en"", ""de"", ""la"", ""grc"", ""ko"", ""peo"", ""akk"", ""elx"", ""sa""], ""configs"": [{""config_name"": ""Wiktionary"", ""data_files"": [{""split"": ""German"", ""path"": ""german-wiktextract-data.jsonl""}, {""split"": ""Latin"", ""path"": ""latin-wiktextract-data.jsonl""}, {""split"": ""AncientGreek"", ""path"": ""ancient-greek-wiktextract-data.jsonl""}, {""split"": ""Korean"", ""path"": ""korean-wiktextract-data.jsonl""}, {""split"": ""OldPersian"", ""path"": ""old-persian-wiktextract-data.jsonl""}, {""split"": ""Akkadian"", ""path"": ""akkadian-wiktextract-data.jsonl""}, {""split"": ""Elamite"", ""path"": ""elamite-wiktextract-data.jsonl""}, {""split"": ""Sanskrit"", ""path"": ""sanskrit-wiktextract-data.jsonl""}]}, {""config_name"": ""Knowledge Graph"", ""data_files"": [{""split"": ""AllLanguage"", ""path"": ""word-definition-graph-data.jsonl""}]}], ""tags"": [""Natural Language Processing"", ""NLP"", ""Wiktionary"", ""Vocabulary"", ""German"", ""Latin"", ""Ancient Greek"", ""Korean"", ""Old Persian"", ""Akkadian"", ""Elamite"", ""Sanskrit"", ""Knowledge Graph""], ""size_categories"": [""100M + + + +> [!TIP] +> +> Two words are structurally similar if and only if the two shares the same +> [stem](https://en.wikipedia.org/wiki/Word_stem) + +Development +----------- + +### Data Source + +Although [the original Wiktionary dump](https://dumps.wikimedia.org/) is available, parsing it from scratch involves +rather complicated process. For example, +[acquiring the inflection data of most Indo-European languages on Wiktionary has already triggered some research-level efforts](https://stackoverflow.com/a/62977327). +We would probably do it in the future. At present, however, we would simply take the awesome works by +[tatuylonen](https://github.com/tatuylonen/wiktextract) which has already processed it and presented it in +[in JSONL format](https://kaikki.org/dictionary/rawdata.html). wiktionary-data sources the data from +__raw Wiktextract data (JSONL, one object per line)__ option there. + +### Environment Setup + +Get the source code: + +```console +git clone git@github.com:QubitPi/wiktionary-data.git +cd wiktionary-data +``` + +It is strongly recommended to work in an isolated environment. Install virtualenv and create an isolated Python +environment by + +```console +python3 -m pip install --user -U virtualenv +python3 -m virtualenv .venv +``` + +To activate this environment: + +```console +source .venv/bin/activate +``` + +or, on Windows + +```console +./venv\Scripts\activate +``` + +> [!TIP] +> +> To deactivate this environment, use +> +> ```console +> deactivate +> ``` + +### Installing Dependencies + +```console +pip3 install -r requirements.txt +``` + +License +------- + +The use and distribution terms for [wiktionary-data]() are covered by the [Apache License, Version 2.0]. + +[Apache License Badge]: https://img.shields.io/badge/Apache%202.0-F25910.svg?style=for-the-badge&logo=Apache&logoColor=white +[Apache License, Version 2.0]: https://www.apache.org/licenses/LICENSE-2.0 + +[GitHub workflow status badge]: https://img.shields.io/github/actions/workflow/status/QubitPi/wiktionary-data/ci-cd.yaml?branch=master&style=for-the-badge&logo=github&logoColor=white&label=CI/CD +[GitHub workflow status URL]: https://github.com/QubitPi/wiktionary-data/actions/workflows/ci-cd.yaml + +[Hugging Face dataset badge]: https://img.shields.io/badge/Hugging%20Face%20Dataset-wiktionary--data-FF9D00?style=for-the-badge&logo=huggingface&logoColor=white&labelColor=6B7280 +[Hugging Face dataset URL]: https://huggingface.co/datasets/QubitPi/wiktionary-data + +[Hugging Face sync status badge]: https://img.shields.io/github/actions/workflow/status/QubitPi/wiktionary-data/ci-cd.yaml?branch=master&style=for-the-badge&logo=github&logoColor=white&label=Hugging%20Face%20Sync%20Up +[Hugging Face sync status URL]: https://github.com/QubitPi/wiktionary-data/actions/workflows/ci-cd.yaml + +[Python Version Badge]: https://img.shields.io/badge/Python-3.10-FFD845?labelColor=498ABC&style=for-the-badge&logo=python&logoColor=white" +jaejoo/llama-2-ko-law,{},"--- +license: apache-2.0 +language: +- ko +tags: +- legal +size_categories: +- 1K + +This dataset card aims to be a base template for new datasets. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/datasetcard_template.md?plain=1). + +## Dataset Details + +### Dataset Description + + + + + +- **Curated by:** [Gary Benson](https://gbenson.net/) + +- **Languages:** Mostly English (87%); + Dutch, French, Chinese, Japanese (1-2% each); 30+ others (<1% each) +- **License:** [CC0 1.0 Universal](https://creativecommons.org/publicdomain/zero/1.0/) + +### Dataset Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Dataset Structure + + + + +[More Information Needed] + +## Dataset Creation + +### Curation Rationale + + + +[More Information Needed] + +### Source Data + + + +#### Data Collection and Processing + + + +[More Information Needed] + +#### Who are the source data producers? + + + +[More Information Needed] + +### Annotations [optional] + + + +#### Annotation process + + + +[More Information Needed] + +#### Who are the annotators? + + + +[More Information Needed] + +#### Personal and Sensitive Information + + + +[More Information Needed] + +## Bias, Risks, and Limitations + +87% of the examples are English. + + +[More Information Needed] + +### Recommendations + + + +Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations. + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Dataset Card Authors [optional] + +[More Information Needed] + +## Dataset Card Contact + +[More Information Needed]" +taeminlee/CLIcK,"{""task_categories"": [""multiple-choice""], ""language"": [""ko""], ""tags"": [""Culture"", ""Language""], ""size_categories"": [""1K +

CLIcK 🇰🇷🧠

+

Evaluation of Cultural and Linguistic Intelligence in Korean

+

+ + +

+ + + +## Introduction 🎉 + +CLIcK (Cultural and Linguistic Intelligence in Korean) is a comprehensive dataset designed to evaluate cultural and linguistic intelligence in the context of Korean language models. In an era where diverse language models are continually emerging, there is a pressing need for robust evaluation datasets, especially for non-English languages like Korean. CLIcK fills this gap by providing a rich, well-categorized dataset focusing on both cultural and linguistic aspects, enabling a nuanced assessment of Korean language models. + +## News 📰 + +- **[LREC-COLING]** Our paper introducing CLIcK has been accepted to LREC-COLING 2024!🎉 + +## Dataset Description 📊 + +The CLIcK benchmark comprises two broad categories: Culture and Language, which are further divided into 11 fine-grained subcategories. + +### Categories 📂 + +- **Language** 🗣️ + - Textual Knowledge + - Grammatical Knowledge + - Functional Knowledge + +- **Culture** 🌍 + - Korean Society + - Korean Tradition + - Korean Politics + - Korean Economy + - Korean Law + - Korean History + - Korean Geography + - Korean Popular Culture (K-Pop) + + +### Construction 🏗️ + +CLIcK was developed using two human-centric approaches: + +1. Reclassification of **official and well-designed exam data** into our defined categories. +2. Generation of questions using ChatGPT, based on **official educational materials** from the Korean Ministry of Justice, followed by our own validation process. + +### Structure 🏛️ + +The dataset is organized as follows, with each subcategory containing relevant JSON files: + +``` +📦CLIcK + └─ Dataset + ├─ Culture + │ ├─ [Each cultural subcategory with associated JSON files] + └─ Language + ├─ [Each language subcategory with associated JSON files] +``` + +### Exam Code Descriptions 📜 + +- KIIP: Korea Immigration & Integration Program ([Website](www.immigration.go.kr)) +- CSAT: College Scholastic Ability Test for Korean ([Website](https://www.suneung.re.kr/)) +- Kedu: Test of Teaching Korean as a Foreign Language exams ([Website](https://www.q-net.or.kr/man001.do?gSite=L&gId=36)) +- PSE: Public Service Exam for 9th grade +- TOPIK: Test of Proficiency in Korean ([Website](https://www.topik.go.kr/)) +- KHB: Korean History Exam Basic ([Website](https://www.historyexam.go.kr/)) +- PSAT: Public Service Aptitude Test in Korea + +## Results + +| Models | Average Accuracy (Korean Culture) | Average Accuracy (Korean Language) | +|-------------------|-----------------------------------|------------------------------------| +| Polyglot-Ko 1.3B | 32.71% | 22.88% | +| Polyglot-Ko 3.8B | 32.90% | 22.38% | +| Polyglot-Ko 5.8B | 33.14% | 23.27% | +| Polyglot-Ko 12.8B | 33.40% | 22.24% | +| KULLM 5.8B | 33.79% | 23.50% | +| KULLM 12.8B | 33.51% | 23.78% | +| KoAlpaca 5.8B | 32.33% | 23.87% | +| KoAlpaca 12.8B | 33.80% | 22.42% | +| LLaMA-Ko 7B | 33.26% | 25.69% | +| LLaMA 7B | 35.44% | 27.17% | +| LLaMA 13B | **36.22%** | **26.71%** | +| GPT-3.5 | 49.30% | 42.32% | +| Claude2 | **51.72%** | **45.39%** | + + +## Dataset Link 🔗 + +The CLIcK dataset is available on the Hugging Face Hub: [CLIcK Dataset](https://huggingface.co/datasets/your_username/CLIcK) + + +## Citation 📝 + +If you use CLIcK in your research, please cite our paper: + +```bibtex +@misc{kim2024click, + title={CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Korean}, + author={Eunsu Kim and Juyoung Suk and Philhoon Oh and Haneul Yoo and James Thorne and Alice Oh}, + year={2024}, + eprint={2403.06412}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +``` + +## Contact 📧 + +For any questions or inquiries, please contact [kes0317@kaist.ac.kr](mailto:kes0317@kaist.ac.kr)." +izhx/mewsli-x,"{""language"": [""af"", ""ar"", ""az"", ""bg"", ""bn"", ""de"", ""el"", ""en"", ""es"", ""et"", ""eu"", ""fa"", ""fi"", ""fr"", ""gu"", ""he"", ""hi"", ""ht"", ""hu"", ""id"", ""it"", ""ja"", ""jv"", ""ka"", ""kk"", ""ko"", ""lt"", ""ml"", ""mr"", ""ms"", ""my"", ""nl"", ""pa"", ""pl"", ""pt"", ""qu"", ""ro"", ""ru"", ""sw"", ""ta"", ""te"", ""th"", ""tl"", ""tr"", ""uk"", ""ur"", ""vi"", ""wo"", ""yo"", ""zh""], ""license"": ""apache-2.0"", ""pretty_name"": ""Mewsli-X"", ""task_categories"": [""text-retrieval""], ""task_ids"": [""entity-linking-retrieval""], ""configs"": [{""config_name"": ""wikipedia_pairs"", ""data_files"": [{""split"": ""train"", ""path"": ""wikipedia_pairs/train.jsonl.tar.gz""}, {""split"": ""validation"", ""path"": ""wikipedia_pairs/dev.jsonl.tar.gz""}]}, {""config_name"": ""ar"", ""data_files"": [{""split"": ""validation"", ""path"": ""wikinews_mentions/ar/dev.jsonl""}, {""split"": ""test"", ""path"": ""wikinews_mentions/ar/test.jsonl""}]}, {""config_name"": ""de"", ""data_files"": [{""split"": ""validation"", ""path"": ""wikinews_mentions/de/dev.jsonl""}, {""split"": ""test"", ""path"": ""wikinews_mentions/de/test.jsonl""}]}, {""config_name"": ""en"", ""data_files"": [{""split"": ""validation"", ""path"": ""wikinews_mentions/en/dev.jsonl""}, {""split"": ""test"", ""path"": ""wikinews_mentions/en/test.jsonl""}]}, {""config_name"": ""es"", ""data_files"": [{""split"": ""validation"", ""path"": ""wikinews_mentions/es/dev.jsonl""}, {""split"": ""test"", ""path"": ""wikinews_mentions/es/test.jsonl""}]}, {""config_name"": ""fa"", ""data_files"": [{""split"": ""validation"", ""path"": ""wikinews_mentions/fa/dev.jsonl""}, {""split"": ""test"", ""path"": ""wikinews_mentions/fa/test.jsonl""}]}, {""config_name"": ""ja"", ""data_files"": [{""split"": ""validation"", ""path"": ""wikinews_mentions/ja/dev.jsonl""}, {""split"": ""test"", ""path"": ""wikinews_mentions/ja/test.jsonl""}]}, {""config_name"": ""pl"", ""data_files"": [{""split"": ""validation"", ""path"": ""wikinews_mentions/pl/dev.jsonl""}, {""split"": ""test"", ""path"": ""wikinews_mentions/pl/test.jsonl""}]}, {""config_name"": ""ro"", ""data_files"": [{""split"": ""validation"", ""path"": ""wikinews_mentions/ro/dev.jsonl""}, {""split"": ""test"", ""path"": ""wikinews_mentions/ro/test.jsonl""}]}, {""config_name"": ""ta"", ""data_files"": [{""split"": ""validation"", ""path"": ""wikinews_mentions/ta/dev.jsonl""}, {""split"": ""test"", ""path"": ""wikinews_mentions/ta/test.jsonl""}]}, {""config_name"": ""tr"", ""data_files"": [{""split"": ""validation"", ""path"": ""wikinews_mentions/tr/dev.jsonl""}, {""split"": ""test"", ""path"": ""wikinews_mentions/tr/test.jsonl""}]}, {""config_name"": ""uk"", ""data_files"": [{""split"": ""validation"", ""path"": ""wikinews_mentions/uk/dev.jsonl""}, {""split"": ""test"", ""path"": ""wikinews_mentions/uk/test.jsonl""}]}, {""config_name"": ""candidate_entities"", ""data_files"": [{""split"": ""test"", ""path"": ""candidate_entities.jsonl.tar.gz""}]}], ""size_categories"": [""100K _**NOTE:** New evaluation results on Mewsli-X are **not** directly comparable to those reported in the paper because the dataset required further updates, as detailed [below](#updated-dataset). This does not affect the overall findings of the paper._ + +``` +@inproceedings{ruder-etal-2021-xtreme, + title = ""{XTREME}-{R}: Towards More Challenging and Nuanced Multilingual Evaluation"", + author = ""Ruder, Sebastian and + Constant, Noah and + Botha, Jan and + Siddhant, Aditya and + Firat, Orhan and + Fu, Jinlan and + Liu, Pengfei and + Hu, Junjie and + Garrette, Dan and + Neubig, Graham and + Johnson, Melvin"", + booktitle = ""Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing"", + month = nov, + year = ""2021"", + address = ""Online and Punta Cana, Dominican Republic"", + publisher = ""Association for Computational Linguistics"", + url = ""https://aclanthology.org/2021.emnlp-main.802"", + doi = ""10.18653/v1/2021.emnlp-main.802"", + pages = ""10215--10245"", +} +```" +Nikity/Pornhub,"{""license"": ""odc-by"", ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""train"", ""path"": ""data.csv""}], ""sep"": ""\u203d""}], ""language"": [""sq"", ""ar"", ""bn"", ""bg"", ""zh"", ""hr"", ""cs"", ""da"", ""nl"", ""en"", ""et"", ""fi"", ""fr"", ""de"", ""el"", ""he"", ""hi"", ""hu"", ""id"", ""it"", ""ja"", ""ko"", ""lv"", ""lt"", ""mk"", ""ml"", ""mr"", ""ne"", ""no"", ""fa"", ""pl"", ""pt"", ""pa"", ""ro"", ""ru"", ""sk"", ""sl"", ""so"", ""es"", ""sw"", ""sv"", ""tl"", ""ta"", ""te"", ""th"", ""tr"", ""uk"", ""ur"", ""vi"", ""cy""], ""tags"": [""not-for-all-audiences""], ""pretty_name"": ""Pornhub"", ""size_categories"": [""100K + +CaLMQA is a long-form question answering (LFQA) dataset spanning 23 high- to low-resource languages. + + +## Dataset Details + +### Dataset Description + +CaLMQA is an LFQA dataset with 2K questions from 23 languages, 11 high- to mid-resource and 12 low-resource. +Questions are either *culturally specific* – uniquely or more likely to be asked by people of a specific +culture – or *culturally agnostic* (not culturally specific). These questions were collected to +evaluate the multilingual capabilities and +cultural knowledge of state-of-the-art models. + + + + +- **Languages (high- to mid-resource):** Arabic, Chinese, English, German, Hindi, Hebrew, Hungarian, Japanese, Korean, Russian, Spanish +- **Languages (low-resource):** Afar, Balochi, Faroese, Fijian, Hiligaynon, Kirundi, Papiamento, Pashto, Samoan, Tongan, Tswana, Wolof +- **License:** [MIT](https://opensource.org/license/MIT) +- **Repository:** [CaLMQA](https://github.com/2015aroras/CaLMQA/tree/main) +- **Paper:** *Pending* + +## Uses + +These questions were collected to evaluate the multilingual capabilities and +cultural knowledge of state-of-the-art models. Automatic metrics are not +sufficiently developed for multilingual LFQA, but human evaluation is viable. + +## Dataset Structure + +The dataset consists of QA entries. +Entry structure: + +- `language`: The language of the question. For culturally specific questions, this is the question's original language. Culturally agnostic questions are all translated from English. +- `question_type`: Indicates whether the question is 'culturally specific' or 'culturally agnostic'. These are the only 2 values `question_type` can currently be. +- `question`: The question that admits a long-form answer, in the language `language`. +- `question_english` : The English translation of the question. +- `answer` (optional): The answer to the question, in the language `language`. + +Culturally specific questions are unique to each language. By contrast, +all culturally agnostic questions are parallel across all languages; they were translated from English to all +other language. + + + +## Dataset Creation + +### Source Data + +Culturally specific questions in low-resource languages are manually written by hired croudworkers. +Culturally specific questions in high- to mid-resource languages are sourced from the following websites. + +- [Ejaba](https://www.ejaba.com/) (Arabic) +- [Ujeeb](https://ujeeb.com/) (Arabic) +- [Zhihu](https://www.zhihu.com/) (Chinese) +- [Reddit ELI5](https://www.reddit.com/r/explainlikeimfive/) (English) +- [Gutefrage](https://www.gutefrage.net/) (German) +- [Quora](https://he.quora.com) (Hebrew) +- [Let's Diskuss](https://hi.letsdiskuss.com/) (Hindi) +- [Gyakori kérdések](https://www.gyakorikerdesek.hu/) (Hungarian) +- [Yahoo Japan](https://chiebukuro.yahoo.co.jp/) (Japanese) +- [OKWave](https://okwave.jp/) (Japanese) +- [Naver](https://kin.naver.com/qna/) (Korean) +- [Yandex](https://yandex.ru/q/) (Russian) +- [Todoexpertos](https://www.todoexpertos.com/) (Spanish) + +Culturally agnostic questions are obtained from [Reddit ELI5](https://www.reddit.com/r/explainlikeimfive/) in English. + + + +#### Data Collection and Processing + + + +We used separate data collection processes for high- to mid-resource languages and for low-resource languages. + +For high- to mid-resource languages, we first conducted a survey amongst workers, asking them to provide community LFQA websites +(like Reddit and Quora) in their native non-English languages. We then hire workers to collected long-form culturally specific +questions information-seeking questions from our [collected websites](#source-data). + +For low-resource languages, we instruct workers to write culturally specific questions. + +#### Who are the source data producers? + + + +All workers were native speakers of the language they collected questions for, as well as proficient English speakers. +Workers from the [Prolific](https://www.prolific.com/) platform were hired to collect culturally specific questions from websites. +Workers from the [UpWork](https://www.upwork.com/) platform were hired to write culturally specific questions in low-resource languages. + +#### Personal and Sensitive Information + + + +Question topics include religion, politics and history, and so some questions may pertain to sensitive issues. +We explicitly specify in our workers' guidelines that collected questions should not be controversial, +and we manually reviewed all questions. However, some questions may still be unagreeable with some people. + +## Bias, Risks, and Limitations + + + +The questions we source from community QA websites might reflect societal biases in those communities and +might under-represent cultures not captured in these QA forums. Our worker-written questions might have workers' biases. + + + +## Citation + + + +**BibTeX:** + +*pending*" +bongsoo/social_science_en_ko,"{""language"": [""ko""], ""license"": ""apache-2.0""}",- 사회과학-en-ko 번역 말뭉치 +yachay/text_coordinates_regions,"{""license"": ""mit"", ""tags"": [""multilingual"", ""text"", ""coordinates"", ""geospatial"", ""translation"", ""NER"", ""geo"", ""geo-tagged"", ""named-entity-recognition"", ""natural-language-processing"", ""geographic-data"", ""geolocation"", ""twitter"", ""reddit""], ""task_categories"": [""feature-extraction"", ""token-classification"", ""text-classification""], ""pretty_name"": ""Multilingual Geo-Tagged Social Media Posts (by 123 world regions)"", ""language"": [""en"", ""zh"", ""es"", ""hi"", ""ar"", ""bn"", ""pt"", ""ru"", ""ja"", ""pa"", ""de"", ""jv"", ""ms"", ""te"", ""vi"", ""ko"", ""fr"", ""mr"", ""ta"", ""ur"", ""tr"", ""it"", ""th"", ""gu"", ""fa"", ""pl""], ""size_categories"": [""100M + +This dataset card aims to be a base template for new datasets. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/datasetcard_template.md?plain=1). + +## Dataset Details + +### Dataset Description + + + + + +- **Curated by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] + +### Dataset Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Dataset Structure + + + +[More Information Needed] + +## Dataset Creation + +### Curation Rationale + + + +[More Information Needed] + +### Source Data + + + +#### Data Collection and Processing + + + +[More Information Needed] + +#### Who are the source data producers? + + + +[More Information Needed] + +### Annotations [optional] + + + +#### Annotation process + + + +[More Information Needed] + +#### Who are the annotators? + + + +[More Information Needed] + +#### Personal and Sensitive Information + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations. + +## Citation + + +```bibtex +@misc{sälevä2024paranames, + title={ParaNames 1.0: Creating an Entity Name Corpus for 400+ Languages using Wikidata}, + author={Jonne Sälevä and Constantine Lignos}, + year={2024}, + eprint={2405.09496}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +```" +neon-mao/language-dataset,"{""license"": ""mit"", ""task_categories"": [""text-classification""], ""language"": [""en"", ""zh"", ""fr"", ""ru"", ""ja"", ""it"", ""tr"", ""de"", ""pt"", ""es"", ""he"", ""uk"", ""nl"", ""fi"", ""pl"", ""lt"", ""cs"", ""da"", ""sv"", ""sr"", ""ar"", ""el"", ""ro"", ""bg"", ""vi"", ""sk"", ""id"", ""is"", ""ko"", ""ca"", ""hr"", ""th"", ""et"", ""sl"", ""no""], ""size_categories"": [""10M + +

+ +# Dataset Card for ""WEATHub"" + +This dataset corresponds to the data described in the paper ""Global Voices, Local Biases: Socio-Cultural Prejudices across Languages"" +accepted to EMNLP 2023. + +## Table of Contents +- [Table of Contents](#table-of-contents) +- [Dataset Description](#dataset-description) + - [Dataset Summary](#dataset-summary) + - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) + - [Languages](#languages) +- [Dataset Structure](#dataset-structure) + - [Data Instances](#data-instances) + - [Data Fields](#data-fields) + - [Data Splits](#data-splits) +- [Dataset Creation](#dataset-creation) + - [Curation Rationale](#curation-rationale) + - [Source Data](#source-data) + - [Annotations](#annotations) + - [Personal and Sensitive Information](#personal-and-sensitive-information) +- [Considerations for Using the Data](#considerations-for-using-the-data) + - [Social Impact of Dataset](#social-impact-of-dataset) + - [Discussion of Biases](#discussion-of-biases) + - [Other Known Limitations](#other-known-limitations) +- [Additional Information](#additional-information) + - [Dataset Curators](#dataset-curators) + - [Licensing Information](#licensing-information) + - [Citation Information](#citation-information) + - [Contributions](#contributions) + +## Dataset Description + +- **Homepage:** [Website](https://iamshnoo.github.io/global_voices_local_biases/) +- **Repository:** [GitHub](https://github.com/iamshnoo/weathub) +- **Paper:** https://arxiv.org/abs/2310.17586 +- **Point of Contact:** Anjishnu Mukherjee + +### Dataset Summary + +WEATHub is a dataset containing 24 languages. It contains words organized into groups of (target1, target2, attribute1, attribute2) +to measure the association target1:target2 :: attribute1:attribute2. For example target1 can be insects, target2 can be flowers. And we +might be trying to measure whether we find insects or flowers pleasant or unpleasant. The measurement of word associations is quantified +using the WEAT metric in our paper. It is a metric that calculates an effect size (Cohen's d) and also provides a p-value (to measure +statistical significance of the results). In our paper, we use word embeddings from language models to perform these tests and understand +biased associations in language models across different languages. + +### Supported Tasks and Leaderboards + +- `bias_eval` : The dataset is used to measure biased associations. +- This particular task isn't a standard task that is currently supported. + +### Languages + +The languages (in alphabetical order of language codes) are: Arabic (ar), Bengali (bn), Sorani Kurdish (ckb), Danish (da), German (de), +Greek (el), Spanish (es), Persian (fa), French (fr), Hindi (hi), Italian (it), Japanese (ja), Korean (ko), Kurmanji Kurdish (ku), +Marathi (mr), Punjabi (pa), Russian (ru), Telugu (te), Thai (th), Tagalog (tl), Turkish (tr), Urdu (ur), Vietnamese (vi), Chinese (zh). + +## Dataset Structure + +### Data Instances + +An example instance is of the form: + +```json + { + 'attr1': {'category': 'Career', + 'examples': ['σύμβουλος', 'διεύθυνση', 'επαγγελματίας', 'εταιρεία', 'μισθός', 'γραφείο', 'επιχείρηση', 'καριέρα', 'διευθύνων σύμβουλος']}, + 'attr2': {'category': 'Family', + 'examples': ['σπίτι', 'γονείς', 'παιδιά', 'οικογένεια', 'ξαδερφια', 'γάμος', 'γάμος', 'συγγενείς']}, + 'targ1': {'category': 'MaleNames', + 'examples': ['Αλέξανδρος', 'Δημήτρης', 'Γιώργος', 'Κώστας', 'Νίκος', 'Παναγιώτης', 'Σπύρος', 'Θοδωρής']}, + 'targ2': {'category': 'FemaleNames', + 'examples': ['Αθηνά', 'Ελένη', 'Κατερίνα', 'Μαρία', 'Ευαγγελία', 'Αναστασία', 'Δέσποινα', 'Χριστίνα']}, + 'language': 'el', + 'weat': 'WEAT6' + } +``` + +### Data Fields + +- A single data point has the following features: + - name: language (corresponding to the language codes given above) + - name: weat (ID corresponding to a WEAT category) + - name: attr1.category (a descriptive name for attribute 1) + - name: attr1.examples (list of words for attribute 1) + - name: attr2.category (a descriptive name for attribute 2) + - name: attr2.examples (list of words for attribute 2) + - name: targ1.category (a descriptive name for target 1) + - name: targ1.examples (list of words for target 1) + - name: targ2.category (a descriptive name for target 2) + - name: targ2.examples (list of words for target 2) + +- All the features are stored as strings. The examples represent lists of strings. + +### Data Splits + +- The dataset is divided into 3 splits as per the description in our paper: + - original_weat - described in Table 1 of our paper, this corresponds to the original WEAT categories as given by Caliskan et al. in their + seminal work from 2017 (Semantics derived automatically from language corpora contain human-like biases) + - new_human_biases - described in Table 2 of our paper, this corresponds to contemporary dimensions of bias that are more human-centric in + modern society. + - india_specific_biases - These contain data corresponding to india specific bias dimensions as described in the paper (Socially Aware Bias Measurements for Hindi Language Representations) + from NAACL '22 by Malik et al. + +## Dataset Creation + +### Curation Rationale + +This dataset is intended to be used for measuring intrinsic biases in word embeddings obtained from language models. + +### Source Data + +#### Initial Data Collection and Normalization + +Described in details in section 2 of our paper. Briefly, for existing weat categories, we use human annotations to improve the quality of the +translated WEAT word lists. For new weat categories, we research possible relevant dimensions thoroughly and come up with words after thorough +discussions with our annotators. + +#### Who are the source language producers? + +Data for each of the language is from native speakers of that language. All annotators who participated in our study are native speakers of +their respective languages and have at least college-level education background. + +### Annotations + +#### Annotation process + +Described in details in section 2 of our paper. Word level annotations. +To collect annotated data in various languages, we provide our annotators with the English words and their corresponding automatic translation +, separated by WEAT category. We provide instructions to verify the accuracy of the translations and provide corrected versions for any +inaccuracies. Additionally, we ask annotators to provide grammatically gendered forms of words, if applicable, or multiple translations +of a word, if necessary. + +#### Who are the annotators? + +All annotators who participated in our study are native speakers of +their respective languages and have at least college-level education background. + +### Personal and Sensitive Information + +Since this dataset tries to measure biased associations at the word level, there may be some word level biases that are sensitive to certain +groups. + +## Considerations for Using the Data + +### Social Impact of Dataset + +This dataset should be a starting point for measuring word level biased associations in a multilingual setting, which has not been explored +in much depth in recent literature. + +### Discussion of Biases + +This dataset represents word level information used for measuring biases. Since these are annotated by humans, they may to certain extent reflect +the biases that they hold at an individual level. + +### Other Known Limitations + +- For most of the languages in our dataset WEATHub, we had access to at least two annotators for cross-verifying the accuracy of + the human translations to determine if the translated words fit into the context of that particular WEAT category. + However, for some languages, we only have one annotator per language, so this might mean that for some languages the data may represent + the biases of that individual annotator even though those biases are somewhat also reflected by Google Translate so it isn't completely + an individualistic issue. +- While we have tried to cover as many languages from the global South as possible, we acknowledge that 24 languages are indeed a + tiny proportion of the 7000 languages in the world, some of which do not even have text representations. +- WEAT can be an unreliable metric for contextualized embeddings from transformer models. We need better metrics to study intrinsic biases in + transformer models. We believe the target and attribute pairs we provide as part of WEATHub in multiple languages is an important step + towards a better multilingual metric for evaluating intrinsic biases in language models. + +## Additional Information + +### Dataset Curators + +This dataset was curated by Anjishnu Mukherjee, Chahat Raj, Ziwei Zhu and Antonios Anastasopoulos for their EMNLP paper while the first two authors were +pursuing their PhD at George Mason University. This work +was generously supported by the National Science Foundation under award IIS-2327143. Computational resources for experiments were provided by the +Office of of Research Computing at George Mason University (URL: https://orc.gmu.edu) and funded in part by grants from the +National Science Foundation (Awards Number 1625039 and 2018631). + +### Licensing Information + +Currently this dataset is released under CC-4.0 (might need to update this if required) + +### Citation Information +``` +@inproceedings{mukherjee-etal-2023-global, + title = ""{G}lobal {V}oices, Local Biases: Socio-Cultural Prejudices across Languages"", + author = ""Mukherjee, Anjishnu and + Raj, Chahat and + Zhu, Ziwei and + Anastasopoulos, Antonios"", + editor = ""Bouamor, Houda and + Pino, Juan and + Bali, Kalika"", + booktitle = ""Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing"", + month = dec, + year = ""2023"", + address = ""Singapore"", + publisher = ""Association for Computational Linguistics"", + url = ""https://aclanthology.org/2023.emnlp-main.981"", + doi = ""10.18653/v1/2023.emnlp-main.981"", + pages = ""15828--15845"", + abstract = ""Human biases are ubiquitous but not uniform: disparities exist across linguistic, cultural, and societal borders. As large amounts of recent literature suggest, language models (LMs) trained on human data can reflect and often amplify the effects of these social biases. However, the vast majority of existing studies on bias are heavily skewed towards Western and European languages. In this work, we scale the Word Embedding Association Test (WEAT) to 24 languages, enabling broader studies and yielding interesting findings about LM bias. We additionally enhance this data with culturally relevant information for each language, capturing local contexts on a global scale. Further, to encompass more widely prevalent societal biases, we examine new bias dimensions across toxicity, ableism, and more. Moreover, we delve deeper into the Indian linguistic landscape, conducting a comprehensive regional bias analysis across six prevalent Indian languages. Finally, we highlight the significance of these social biases and the new dimensions through an extensive comparison of embedding methods, reinforcing the need to address them in pursuit of more equitable language models."", +} +``` +### Contributions + +Thanks to [@iamshnoo](https://github.com/iamshnoo) for adding this dataset." +youngwoo3283/df_sentiment_chat,"{""language"": [""ko""]}","### 데이터 출처 : https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&dataSetSn=86 + +해당 데이터에서 사람응답1과 시스템 응답1로만 만든 데이터" +traintogpb/aihub-kozh-translation-integrated-large-5.9m,"{""license"": ""mit"", ""task_categories"": [""translation""], ""language"": [""ko"", ""zh""]}","### AI Hub Ko-Zh Translation Dataset (Integrated) + +AI Hub의 한-중 번역 관련 데이터셋 10개를 병합한 자료입니다. 병합 시 총 데이터 개수는 5,934,596개이며, 이중 10,000개의 validation set와 2,000개의 test set가 분리되어 모든 데이터 사이즈(large-5.9m, base-1m, small-100k)에서 동일하게 사용됩니다. + +- large-5.9m (train): 병합 데이터 100% 사용; 총 5,922,596개 + +- base-1m (train): 병합 데이터 중 1M개 사용; 총 1,000,000개 + +- small-100k (train): 병합 데이터 중 100K개 사용; 총 100,000개 + +### Subsets +| Name | Total Size | Chinese Size (Utilized Only) | URL | Datasetkey (AIHub) | +|---|---|---|---|---| +| 한국어-중국어 번역 말뭉치(기술과학) | 1170000 | 1170000 | [URL](https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=&topMenu=&aihubDataSe=data&dataSetSn=128) | 128 | +| 한국어-중국어 번역 말뭉치(사회과학) | 1170000 | 1170000 | [URL](https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=&topMenu=&aihubDataSe=data&dataSetSn=129) | 129 | +| 일상생활 및 구어체 한-중, 한-일 번역 병렬 말뭉치 데이터 | 2700000 | 1349470 | [URL](https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=&topMenu=&aihubDataSe=data&dataSetSn=546) | 546 | +| 전문분야 영-한, 중-한 번역 말뭉치(식품) | 1350000 | 1326837 | [URL](https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=&topMenu=&aihubDataSe=data&dataSetSn=71262) | 71262 | +| 방송 콘텐츠 한-중, 한-일 번역 병렬 말뭉치 데이터 | 1487088 | 367921 | [URL](https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=&topMenu=&aihubDataSe=data&dataSetSn=71263) | 71263 | +| 발화유형(문어, 구어, 채팅) 별 기계번역 병렬 말뭉치 | 82002 | 26989 | [URL](https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=&topMenu=&aihubDataSe=data&dataSetSn=71411) | 71411 | +| 한국어-다국어 번역 말뭉치(기술과학) | 270459 | 146317 | [URL](https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=&topMenu=&aihubDataSe=data&dataSetSn=71493) | 71493 | +| 한국어-다국어 번역 말뭉치(기초과학) | 270317 | 84419 | [URL](https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=&topMenu=&aihubDataSe=data&dataSetSn=71496) | 71496 | +| 한국어-다국어 번역 말뭉치(인문학) | 271721 | 80375 | [URL](https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=&topMenu=&aihubDataSe=data&dataSetSn=71498) | 71498 | +| 방송콘텐츠 한국어-아시아어 번역 말뭉치 | 820387 | 112978 | [URL](https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=&topMenu=&aihubDataSe=data&dataSetSn=71591) | 71591 | +| AI 허브 데이터 활용을 위한 기계 번역말뭉치 | 2653948 | 212268 | [URL](https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=&topMenu=&aihubDataSe=data&dataSetSn=71593) | 71593 |" +zzunyang/LawQA_LawSee,{},"--- +task_categories: +- conversational +language: +- ko +tags: +- legal +---" +DinoTheLewis/KoAlpaca_persona_multiturn,{}, +nayohan/Magpie-Pro-MT-300K-v0.1-ko,"{""language"": [""ko""], ""task_categories"": [""text-generation""], ""dataset_info"": {""features"": [{""name"": ""input1"", ""dtype"": ""string""}, {""name"": ""output1"", ""dtype"": ""string""}, {""name"": ""input2"", ""dtype"": ""string""}, {""name"": ""output2"", ""dtype"": ""string""}, {""name"": ""model"", ""dtype"": ""string""}, {""name"": ""gen_input_config"", ""struct"": [{""name"": ""temperature"", ""dtype"": ""float64""}, {""name"": ""top_p"", ""dtype"": ""float64""}]}, {""name"": ""conversations"", ""list"": [{""name"": ""from"", ""dtype"": ""string""}, {""name"": ""value"", ""dtype"": ""string""}]}, {""name"": ""uuid"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 3617261192, ""num_examples"": 300000}], ""download_size"": 1857815558, ""dataset_size"": 3617261192}, ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""train"", ""path"": ""data/train-*""}]}], ""tags"": [""instruction"", ""korean""]}","Translated [Magpie-Align/Magpie-Pro-MT-300K-v0.1](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-MT-300K-v0.1) using [nayohan/llama3-instrucTrans-enko-8b](https://huggingface.co/nayohan/llama3-instrucTrans-enko-8b). + +This dataset is a raw translated dataset and contains repetitive sentences generated by the model, so it needs to be filtered. + +``` +@misc{xu2024magpie, + title={Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing}, + author={Zhangchen Xu and Fengqing Jiang and Luyao Niu and Yuntian Deng and Radha Poovendran and Yejin Choi and Bill Yuchen Lin}, + year={2024}, + eprint={2406.08464}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +```" +ChuGyouk/MedQA,"{""configs"": [{""config_name"": ""ko"", ""data_files"": [{""split"": ""train"", ""path"": ""medqa_train_trans.jsonl""}, {""split"": ""test"", ""path"": ""medqa_test_trans.jsonl""}]}, {""config_name"": ""en"", ""data_files"": [{""split"": ""train"", ""path"": ""medqa_edited_train.jsonl""}, {""split"": ""test"", ""path"": ""medqa_edited_test.jsonl""}]}], ""license"": ""cc-by-4.0"", ""task_categories"": [""text-generation""], ""language"": [""ko"", ""en""], ""tags"": [""medical""]}","Original dataset introduced by Jin et al. in [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://paperswithcode.com/paper/what-disease-does-this-patient-have-a-large) + +# En split +Just edited columns. Contents are same. + +# Ko split + +## Train + +The train dataset is translated by ""solar-1-mini-translate-enko"". + +## Test + +The test dataset is translated by DeepL Pro. + +**reference-free COMET score: 0.7989** *(Unbabel/wmt23-cometkiwi-da-xxl)* + +

Citation information:

+ + @article{jin2020disease, + title={What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams}, + author={Jin, Di and Pan, Eileen and Oufattole, Nassim and Weng, Wei-Hung and Fang, Hanyi and Szolovits, Peter}, + journal={arXiv preprint arXiv:2009.13081}, + year={2020} + }" +qwopqwop/ALMA-R-ko-en,"{""language"": [""ko"", ""en""], ""license"": ""cc-by-sa-4.0"", ""size_categories"": [""1K + +SAMSEMO: New dataset for multilingual and multimodal emotion recognition + +## Dataset Details + + +### Dataset Sources + + + +- **Repository:** https://github.com/samsungnlp/samsemo +- **Paper:** SAMSEMO: New dataset for multilingual and multimodal emotion recognition + +### Dataset Structure +``` +SAMSEMO/ +├── data - zipped directories for each language with files: jpg, mp4, wav +│ ├── pkl_files - files in the pkl format (each language directory from data directory after processing to pkl format) +├── metadata - directory with metadata +├── samsemo.tsv - metadata file (described below) +└── splits - txt files with splits (list of ids) for each language +``` + +### Annotations + +SAMSEMO metadata file is a .tsv file containing several columns: +- utterance_id – alphanumerical id of the video scene. It consists of ID of the source video followed by the underscore and the number indicating the scene (utterance taken from a given movie) +- movie_title – the title of the source video, according to the website it was taken from +- movie_link – the link leading to the source video +source_scene_start, source_scene_stop – the beginning and ending of the scene determined in the preliminary annotation. The annotators provided time in hh:mm:ss format, without milliseconds. We cut out the scenes, determining the start on the beginning of the first second (ss.00), and the end on the end of the last second (ss.99). Later on, the scenes were adjusted to eliminate the redundant fragments. +- language – the language of the scene: EN = English, DE = German, ES = Spanish; PL = Polish, KO = Korean +- sex – sex of the speaker identified by the annotators (not confirmed by the speaker – see DISCLAIMER). Possible labels: male, female, other. +- age – approximate age of the speaker identified by the annotators (not confirmed by the speaker – see DISCLAIMER). Possible labels: adolescent, adult, elderly. +- race – race of the speaker identified by the annotators (not confirmed by the speaker – see DISCLAIMER). Possible labels: asian, black, hispanic, white, other. +- covered_face – label indicating if speaker’s face is partially covered, e.g. by their hands, scarf, face mask etc. No = the face is not covered, Yes = the face is covered +- multiple_faces – label indicating if the is one person or more shown in the scene. No = one person, Yes = multiple people. +- emotion_1_annotator_1, emotion_2_annotator_1 – emotion labels assigned to the scene by the first annotator. +- emotion_1_annotator_2, emotion_2_annotator_2 -– emotion labels assigned to the scene by the second annotator. +- emotion_1_annotator_3, emotion_2_annotator_3 – emotion labels assigned to the scene by the third annotator. +- aggregated_emotions – final emotions assigned to the video scene. If two or three annotators assigned a certain label to the scene, this label is included in the final aggregation, hence is present in this column. +- annotator_1, annotator_2, annotator_3 – anonymized IDs of the annotators. +- transcript – the text of the utterance from the scene. It is an output of the ASR, subsequently verified manually. +- translation_de, translation_en, translation_es, translation_ko , translation_pl – the translation of the text to other languages used in this dataset. Note that this is has been done by the machine translation engine and has not been manually verified. +- duration – the duration of the scene in the following format: hh:mm:ss.ms +- movie_type – the type of the source video from which the scene was taken. Possible categories: advertisement, debate, documentary, interview, lecture, monologue, movie, news, speech, stand-up, theatrical play, vlog, web or TV show, workout. +- license – the license under which we share the video scene. Note that the metadata are shared under the CC BY-NC-SA 4.0 license (see DISCLAIMER). +- author – the author of the video, identified by us to the best of our knowledge on the basis of the data provided on the websites from which the videos were taken. + + +DISCLAIMER +1) Please note that the metadata provided for each scene include labels referring to gender of the speakers. +The annotators were asked to provide such labels so that SAMSEMO could be verified in terms of gender representation (males 57.32%, females 42.51%, other 0.17%). +The same applies to race information: annotators were asked to label the presumed race of the speakers using a restricted number of labels so that SAMSEMO could be assessed in terms of racial representation (we did not have access to self-reports of speakers in this regard). +We acknowledge that both concepts are shaped by social and cultural circumstances and the labels provided in SAMSEMO are based on subjective perceptions and individual experience of annotators. +Thus, the metadata provided should be approached very carefully in future studies. +2) The movie license information provided in SAMSEMO has been collected with due diligence. All video material is shared under its original licenses. + However, if any video materials included in the SAMSEMO dataset infringe your copyright by any means, please send us a takedown notice containing the movie title(s) and movie link(s). +Please include also a statement by you under penalty or perjury that the information in your notice is accurate and that you are the copyright owner or authorized to act on the copyright owner's behalf. +3) All SAMSEMO metadata (emotion annotation, transcript and speaker information) are shared under the CC BY-NC-SA 4.0 license. + + +## Citation +``` +@inproceedings{samsemo24_interspeech, + title = {SAMSEMO: New dataset for multilingual and multimodal emotion recognition}, + author = {Pawel Bujnowski and Bartlomiej Kuzma and Bartlomiej Paziewski and Jacek Rutkowski and Joanna Marhula and Zuzanna Bordzicka and Piotr Andruszkiewicz}, + year = {2024}, + booktitle = {Interspeech 2024}, + pages = {2925--2929}, + doi = {10.21437/Interspeech.2024-212}, +} +```" +prometheus-eval/MM-Eval,"{""dataset_info"": {""features"": [{""name"": ""prompt"", ""dtype"": ""string""}, {""name"": ""chosen"", ""dtype"": ""string""}, {""name"": ""rejected"", ""dtype"": ""string""}, {""name"": ""language"", ""dtype"": ""string""}, {""name"": ""subset"", ""dtype"": ""string""}, {""name"": ""chosen_model"", ""dtype"": ""string""}, {""name"": ""rejected_model"", ""dtype"": ""string""}, {""name"": ""id"", ""dtype"": ""int64""}, {""name"": ""__index_level_0__"", ""dtype"": ""int64""}], ""splits"": [{""name"": ""test"", ""num_bytes"": 30802291, ""num_examples"": 11081}], ""download_size"": 13929039, ""dataset_size"": 30802291}, ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""test"", ""path"": ""data/test-*""}]}], ""language"": [""ar"", ""bn"", ""ca"", ""de"", ""en"", ""es"", ""eu"", ""fr"", ""gl"", ""it"", ""ja"", ""ko"", ""ru"", ""sw"", ""te"", ""th"", ""vi"", ""zh""], ""license"": ""cc-by-sa-4.0""}","# Multilingual Meta-EVALuation benchmark (MM-Eval) + +

+👨‍💻Code +| +📄Paper +| +🤗 MMQA +

+ +**MM-Eval** is a multilingual meta-evaluation benchmark consisting of five core subsets—Chat, Reasoning, Safety, Language Hallucination, and Linguistics—spanning 18 languages and a Language Resource subset spanning 122 languages for a broader analysis of language effects. + +> **Design Choice** +> In this work, we minimize the inclusion of translated samples, as mere translation may alter existing preferences due to translation errors. Instead, we increase the proportion of linguistically and culturally related instances. Consequently, translated samples are only included in the Safety subset. Additionally, we enrich the dataset with a Linguistics subset designed to evaluate the judge model's ability to comprehend the linguistic characteristics of various languages accurately. Furthermore, we incorporate hand-crafted culturally related prompts in the Language Hallucination subset. If you are interested, please look into [MMQA (Multilingual, Multicultural Question Answering)](https://huggingface.co/datasets/prometheus-eval/MMQA). + + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/617f679fb15f8a665f3999fc/FsMVboxBNnEapka7ESj35.png) + + + +### Languages Covered: +Arabic, Bengali, Catalan, German, English, Spanish, Basque, French, Galacian, Italian, Japanese, Korean, Russian, Swahili, Telugu, Thai, Vietnamese, Chinese + +### Citation: +If you find the following model helpful, please consider citing our paper! +``` +@article{son2024mm, + title={MM-Eval: A Multilingual Meta-Evaluation Benchmark for LLM-as-a-Judge and Reward Models}, + author={Son, Guijin and Yoon, Dongkeun and Suk, Juyoung and Aula-Blasco, Javier and Aslan, Mano and Kim, Vu Trong and Islam, Shayekh Bin and Prats-Cristi{\`a}, Jaume and Tormo-Ba{\~n}uelos, Luc{\'\i}a and Kim, Seungone}, + journal={arXiv preprint arXiv:2410.17578}, + year={2024} +} +```" +felfri/MAGBIG,"{""license"": ""apache-2.0"", ""configs"": [{""config_name"": ""direct"", ""data_files"": [{""split"": ""adjectives"", ""path"": ""data/adjectives-00000-of-00001.csv""}, {""split"": ""occupations"", ""path"": ""data/occupations_direct-00000-of-00001.csv""}]}, {""config_name"": ""indirect"", ""data_files"": [{""split"": ""occupations"", ""path"": ""data/occupations_indirect-00000-of-00001.csv""}]}, {""config_name"": ""feminine"", ""data_files"": [{""split"": ""occupations"", ""path"": ""data/occupations_direct_feminine-00000-of-00001.csv""}]}, {""config_name"": ""gender_star"", ""data_files"": [{""split"": ""occupations"", ""path"": ""data/occupations_german_gender_star-00000-of-00001.csv""}]}], ""task_categories"": [""text-to-image""], ""language"": [""en"", ""de"", ""it"", ""fr"", ""es"", ""zh"", ""ja"", ""ko"", ""ru"", ""ar""], ""size_categories"": [""1K + + + +The Bias Benchmark for Question Answering (BBQ) is designed to evaluate social biases of language models (LMs), but it is not simple to adapt this benchmark to cultural contexts other than the US because social biases depend heavily on the cultural context. In this paper, we present **KoBBQ, a Korean bias benchmark dataset**, and we propose a general framework that addresses considerations for cultural adaptation of a dataset. Our framework includes partitioning the BBQ dataset into three classes--Simply-Transferred (can be used directly after cultural translation), Target-Modified (requires localization in target groups), and Sample-Removed (does not fit Korean culture)-- and adding four new categories of bias specific to Korean culture. We conduct a large-scale survey to collect and validate the social biases and the targets of the biases that reflect the stereotypes in Korean culture. The resulting **KoBBQ dataset comprises 268 templates and 76,048 samples across 12 categories of social bias**. We use KoBBQ to measure the accuracy and bias scores of several state-of-the-art multilingual LMs. The results clearly show differences in the bias of LMs as measured by KoBBQ and a machine-translated version of BBQ, demonstrating the need for and utility of a well-constructed, culturally-aware social bias benchmark. + + +## Dataset Details + +### Dataset Description + + + + + +We propose a framework for developing culturally adaptive datasets and present KoBBQ that reflects the situations and social biases in South Korea. The dataset curation process consists of the following steps: (1) categorization of BBQ templates, (2) cultural-sensitive translation, (3) demographic category construction, (4) creation of new templates, and (5) a large-scale survey on social bias. + +### Statistics +| Category | # of Templates | # of Samples | +|:--------:|:--------------:|:------------:| +| Age | 21 | 3,608 | +| Disability Status | 20 | 2,160 | +| Gender Identity | 25 | 768 | +| Physical Appearance | 20 | 4,040 | +| Race/Ethnicity/Nationality | 43 | 51,856| +| Religion | 20 | 688 | +| Socio-Economic Status | 27 | 6,928 | +| Sexual Orientation | 12 | 552 | +| Domestic Area of Origin | 22 | 800 | +| Family Structure | 23 | 1,096 | +| Political Orientation | 11 | 312 | +| Education Background | 24 | 3,240 | +| **Total** | 268| 76,048| + +### Dataset Sources + + + +- **Repository:** [github](https://github.com/naver-ai/KoBBQ/) +- **Paper:** [arxiv](https://arxiv.org/abs/2307.16778) +- **Project Page:** [webpage](https://jinjh0123.github.io/KoBBQ/) + +## Uses + + + +### Direct Use + + + +To evaluate language models using KoBBQ, please refer [here](https://github.com/naver-ai/KoBBQ/tree/main?tab=readme-ov-file#how-to-evaluate) + +### Ethical Considerations + +We do not condone any malicious use of our dataset. It must not be used as training data to automatically generate and publish biased languages targeting specific groups. We strongly encourage researchers and practitioners to utilize this dataset in beneficial ways, such as mitigating bias in language models. + +## Citation + +**BibTeX:** +``` +@article{jin2023kobbq, + title={Kobbq: Korean bias benchmark for question answering}, + author={Jin, Jiho and Kim, Jiseon and Lee, Nayeon and Yoo, Haneul and Oh, Alice and Lee, Hwaran}, + journal={arXiv preprint arXiv:2307.16778}, + year={2023} +} +``` + +**APA:** +``` +Jin, J., Kim, J., Lee, N., Yoo, H., Oh, A., & Lee, H. (2023). Kobbq: Korean bias benchmark for question answering. arXiv preprint arXiv:2307.16778. +```" +nlp-with-deeplearning/Ko.WizardLM_evol_instruct_V2_196k,"{""license"": ""cc-by-nc-sa-4.0"", ""task_categories"": [""text-generation"", ""question-answering""], ""language"": [""en"", ""ko""]}","이 데이터셋은 자체 구축한 번역기로 [WizardLM/WizardLM_evol_instruct_V2_196k](https://huggingface.co/datasets/WizardLM/WizardLM_evol_instruct_V2_196k)을 번역한 데이터셋입니다. 아래 README 페이지도 번역기를 통해 번역되었습니다. 참고 부탁드립니다. + + +## News + +- 🔥 🔥 🔥 [08/11/2023] **WizardMath** 모델을 출시합니다. +- 🔥 **WizardMath-70B-V1.0** 모델은 **ChatGPT 3.5**, **Claude Instant 1** 및 **PaLM 2 540B** 를 포함 하 여 GSM8K에서 일부 폐쇄 소스 LLMs 보다 약간 더 우수 합니다. +- 🔥 우리의 **WizardMath-70B-V1.0** 모델은 SOTA 오픈 소스 LLM보다 **24.8** 포인트 높은 [GSM8k Benchmarks](https://github.com/openai/grade-school-math)에서 **81.6 pass@1** 을 달성합니다. +- 🔥 우리의 **WizardMath-70B-V1.0** 모델은 SOTA 오픈 소스 LLM보다 **9.2** 포인트 높은 [MATH 벤치마크](https://github.com/hendrycks/math)에서 **22.7 pass@1** 을 달성합니다. + +| 모델 | 체크포인트 | 용지 | GSM8k | MATH |온라인 데모| 라이선스 +| ----- |------| ---- |------|-------| ----- | ----- | +| WizardMath-70B-V1.0 | 🤗 HF Link | 📃 [WizardMath]| **81.6** | **22.7** smells|[Demo](http://47.103.63.15:50083/)| Llama 2 | +| WizardMath-13B-V1.0 | 🤗 HF Link | 📃 [WizardMath]| **63.9** | **14.0** |[Demo](http://47.103.63.15:50082/)| Llama 2 | +| WizardMath-7B-V1.0 | 🤗 HF Link | 📃 [WizardMath]| Automation **54.9** | **10.7** | [Demo](http://47.103.63.15:50080/)| Llama 2 | + + + + +| Model | Checkpoint | Paper |MT-Bench | AlpacaEval | WizardEval | HumanEval | License| +| ----- |------| ---- |------|-------| ----- | ----- | ----- | +| WizardLM-13B-V1.2 | 🤗 HF Link| | 7.06 | 89.17%Placement | 101.4%|36.6 pass@1| Llama 2 License | +| WizardLM-13B-V1.1 | 🤗 HF Link | | 6.76 |86.32%Automation | 99.3% |25.0 pass@1| Noncommercial| +| WizardLM-30B-V1.0 | 🤗 HF Link | | 7.01 | | 97.8% | 37.8 pass@1| 비상업 | +| WizardLM-13B-V1.0 | 🤗 HF Link | | 6.35 | 75.31% | 89.1% | 24.0 pass@1 | 비상업| +| WizardLM-7B-V1.0| 🤗 HF Link | 📃 [WizardLM]| | | 78.0% |19.1 pass@1| 비상업적| +| WizardCoder-15B-V1.0 | 🤗 HF Link | 📃 [WizardCoder] | || 57.3 pass@1 | OpenRAIL-M | + + + +**리포지토리**: https://github.com/nlpxucan/WizardLM + +**Twitter**: https://twitter.com/WizardLM_AI/status/1669364947606982656 + + + +이 데이터 세트에는 알파카와 샤레GPT의 143K 혼합 진화 데이터가 포함되어 있다. + +이것은 WizardLM 모델의 Evol-Instruct 학습 데이터의 최신 최적화 버전이다. + +데이터 사용 라이선스로 인해 약 196k 데이터 행으로 구성된 **최종 전체 데이터 세트** 를 가져오려면 원본 [ShareGPT](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered)를 **병합**하십시오." +allganize/flare-fiqasa-ko,"{""dataset_info"": {""features"": [{""name"": ""conversation_id"", ""dtype"": ""string""}, {""name"": ""conversations"", ""list"": [{""name"": ""from"", ""dtype"": ""string""}, {""name"": ""value"", ""dtype"": ""string""}]}], ""splits"": [{""name"": ""test"", ""num_bytes"": 52262, ""num_examples"": 204}], ""download_size"": 19986, ""dataset_size"": 52262}, ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""test"", ""path"": ""data/test-*""}]}], ""license"": ""mit"", ""language"": [""ko""]}","# flare-fiqasa-ko + + +### 데이터 설명 + +- `flare-fiqasa-ko` 데이터는 금융 도메인 뉴스 헤드라인의 감성을 예측(sentiment analysis)하는 데이터셋입니다. +입력값은 text로만 이루어져 있습니다. + +- 한국어 데이터를 생성하기 위해, 우선 사내 언어 번역 모델 Allganize Translator을 활용하여 [ChanceFocus/flare-fiqasa](https://huggingface.co/datasets/ChanceFocus/flare-fiqasa)의 test set을 번역했습니다. +오역된 데이터를 직접 제거하였고, 그 결과 204개의 평가 데이터가 생성되었습니다. + + +### 데이터 출처 +- [ChanceFocus/flare-fiqasa](https://huggingface.co/datasets/ChanceFocus/flare-fiqasa) + + +### 데이터 예시 +``` +{ + 'conversation_id': 'fiqasa938', + 'conversations': array([ + { + 'from': 'human', + 'value': '''다음 재무 게시물의 감정은 무엇인가요? 긍정, 부정 또는 중립인가요? + 텍스트: $BBRY 실제로 부채가 없고 현금 3.1달러를 포함하면 주당 0.03달러의 손실을 입었습니다. + 정답:''' + }, + { + 'from': 'gpt', + 'value': '부정' + } + ], dtype=object) +} + +```" +g0ster/TinyStories-Korean,"{""license"": ""mit"", ""task_categories"": [""translation""], ""language"": [""ko"", ""en""], ""pretty_name"": ""tinystories-korean"", ""size_categories"": [""1M + +This dataset is a translated version of [roneneldan](https://huggingface.co/roneneldan)'s [TinyStories](https://huggingface.co/datasets/roneneldan/TinyStories) dataset. + +I first downloaded roneneldan's TinyStories, and I organized it in a db file. Then I used a local transalation model [eeve](https://huggingface.co/yanolja/EEVE-Korean-Instruct-10.8B-v1.0) + to translate, and I changed it back to a txt file. + +Feel free to use! + +--- +## Citation + +``` +@misc{kim2024tinystories, + title={TinyStories Korean translations}, + author={Dohoon Kim(g0ster)}, + year={2024}, +} +```" +bebechien/HongGildongJeon,"{""language"": [""ko""], ""license"": ""pddl"", ""task_categories"": [""text-generation""]}","Source + +original : https://ko.wikisource.org/wiki/%ED%99%8D%EA%B8%B8%EB%8F%99%EC%A0%84_36%EC%9E%A5_%EC%99%84%ED%8C%90%EB%B3%B8 \ +license : public domain + +modern translation : https://ko.wikisource.org/wiki/%ED%99%8D%EA%B8%B8%EB%8F%99%EC%A0%84_36%EC%9E%A5_%EC%99%84%ED%8C%90%EB%B3%B8/%ED%98%84%EB%8C%80%EC%96%B4_%ED%95%B4%EC%84%9D \ +license : https://creativecommons.org/licenses/by-sa/4.0/ \ +translator : 직지프로" +nlp-with-deeplearning/ko.openhermes,"{""license"": ""cc-by-nc-sa-4.0"", ""task_categories"": [""text-generation""], ""language"": [""en"", ""ko""], ""tags"": [""distillation"", ""synthetic data"", ""gpt""], ""size_categories"": [""100K + +This dataset is a reformatting of [OpenAssistant Conversations (OASST1)](https://huggingface.co/datasets/OpenAssistant/oasst1), which is +> a human-generated, human-annotated assistant-style conversation corpus consisting of 161,443 messages in 35 different languages, annotated with 461,292 quality ratings, resulting in over 10,000 fully annotated conversation trees. The corpus is a product of a worldwide crowd-sourcing effort involving over 13,500 volunteers. + +It was modified from the original by following the tree branches and reforming the messages into conversation streams. + + +#### Who are the editors? + +Aymeric Roucher, Hugging Face. + +### Example + +```` +{ + 'conversation_id': '6708c47f-05c9-4346-b3d2-40b2bd24fde4', + 'user_id': '2c96e467-66f0-4be7-9693-bda51356a424', + 'created_date': '2023-02-06T18:48:49.391686+00:00', + 'messages': [ + {'content': 'Can you write a short introduction about the relevance of the term ""monopsony"" in economics? Please use examples related to potential monopsonies in the labour market and cite relevant research.', + 'role': 'user'}, + {'content': '""Monopsony"" refers to a market structure where there is only one buyer for a particular good or service. In economics, this term is particularly relevant in the labor market, where a monopsony employer has significant power over the wages and working conditions of their employees. The presence of a monopsony can result in lower wages and reduced employment opportunities for workers, as the employer has little incentive to increase wages or provide better working conditions.\n\nRecent research has identified potential monopsonies in industries such as retail and fast food, where a few large companies control a significant portion of the market (Bivens & Mishel, 2013). In these industries, workers often face low wages, limited benefits, and reduced bargaining power, leading to a situation where they are dependent on the employer for their livelihood. This dependence can result in further suppression of wages and a decline in working conditions.\n\nOverall, the concept of monopsony is essential to understanding the dynamics of labor markets and the impact of market power on workers. Further research is needed to understand the extent and impact of monopsonies on the economy and to develop policies to address this issue.\n\nReferences:\nBivens, J., & Mishel, L. (2013). The Pay of Corporate Executives and Financial Professionals as Evidence of Rents in Top 1 Percent Incomes. Journal of Economic Perspectives, 27(3), 57-78.', + 'role': 'assistant'}, + {'content': 'Now explain it to a dog', 'role': 'user'} + ] +} +````" +kozistr/mqa-ko,"{""language"": [""ko""], ""license"": ""cc0-1.0"", ""task_categories"": [""question-answering""], ""tags"": [""mqa""], ""dataset_info"": {""features"": [{""name"": ""question"", ""dtype"": ""string""}, {""name"": ""answer"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 541067862, ""num_examples"": 1382378}], ""download_size"": 162865210, ""dataset_size"": 541067862}, ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""train"", ""path"": ""data/train-*""}]}]}",* https://huggingface.co/datasets/clips/mqa +ChuGyouk/AI-MO-NuminaMath-CoT-Ko,"{""language"": [""en"", ""ko""], ""license"": ""cc-by-nc-4.0"", ""task_categories"": [""text-generation""], ""dataset_info"": {""features"": [{""name"": ""source"", ""dtype"": ""string""}, {""name"": ""problem"", ""dtype"": ""string""}, {""name"": ""problem_ko"", ""dtype"": ""string""}, {""name"": ""solution"", ""dtype"": ""string""}, {""name"": ""solution_ko"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 2581407207, ""num_examples"": 859494}], ""download_size"": 1262990465, ""dataset_size"": 2581407207}, ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""train"", ""path"": ""data/train-*""}]}]}","# Dataset Card for NuminaMath CoT Korean + +🎉 **Translation finished!** If there are any errors, please open the PR. 🎉 + +If you use this data, please make sure to credit my source! + +⚠️ There may be errors in the translation of mathematical terms. (ex: trivial-사소한X/자명한O, negative-부정?음수?) + +## Dataset Description + +- **Homepage:** https://projectnumina.ai +- **Repository:** https://github.com/project-numina/aimo-progress-prize +- **Paper:** https://github.com/project-numina/aimo-progress-prize/blob/main/report/numina_dataset.pdf + +### Translation + +The original data [AI-MO/NuminaMath-CoT](https://huggingface.co/datasets/AI-MO/NuminaMath-CoT) is in English. + +I used **solar-1-mini-translate-enko-240507** to translate into Korean. To see the detailed script on how I did it, please refer to the script below. + +### Source breakdown + +*The table in the original data shows 859,608, but in reality, there are 859,594 many :)* + +| Source | Number of Samples | +| --- | --- | +| aops_forum | 30201 | +| amc_aime | 4072 | +| cn_k12 | 276591 | +| gsm8k | 7345 | +| math | 7478 | +| olympiads | 150581 | +| orca_math | 153334 | +| synthetic_amc | 62111 | +| synthetic_math | 167895 | +| **Total** | **859608** | + +### Licensing Information + +The dataset is available under the [Creative Commons NonCommercial (CC BY-NC 4.0)](https://creativecommons.org/licenses/by-nc/4.0/legalcode). + +### Citation Information + +``` +@misc{numina_math_datasets, + author = {Jia LI and Edward Beeching and Lewis Tunstall and Ben Lipkin and Roman Soletskyi and Shengyi Costa Huang and Kashif Rasul and Longhui Yu and Albert Jiang and Ziju Shen and Zihan Qin and Bin Dong and Li Zhou and Yann Fleureau and Guillaume Lample and Stanislas Polu}, + title = {NuminaMath}, + year = {2024}, + publisher = {Numina}, + journal = {Hugging Face repository}, + howpublished = {\url{[https://huggingface.co/AI-MO/NuminaMath-CoT](https://github.com/project-numina/aimo-progress-prize/blob/main/report/numina_dataset.pdf)}} +} +``` + +### Python script for translation +Note that you need upstage API Key. +
Python Code + +```python + from openai import OpenAI + client = OpenAI( + api_key=""YOUR_UPSTAGE_API_KEY"" + base_url=""https://api.upstage.ai/v1/solar"" + ) + from tqdm import tqdm + tqdm.pandas() + import pandas as pd + import time + import argparse + + def solar_translate_apicall(source_input, previous_translate_results): + trial_count = 0 + while True: + try: + stream = client.chat.completions.create( + model=""solar-1-mini-translate-enko"", + messages= previous_translate_results + + [ + { + ""role"": ""user"", + ""content"": source_input + }, + ] + , + stream=False, + ) + except Exception as e: + if e.status_code == 401: # Unauthorized + raise Exception(e.response) + elif e.status_code == 429: # Rate Limit + trial_count += 1 + if trial_count <= 1000: + print(""Too many requests. Take a rest and retrying..."") + time.sleep(10) + continue + else: + print(""Retried 100 times, but still failed. Please check the server status."") + raise Exception(e.response) + elif e.status_code in [500, 502, 503, 504] : # Internal Server Error + trial_count += 1 + if trial_count <= 1000: + print(""Internal Server Error. Retrying..."") + time.sleep(5) + continue + else: + print(""Retried 1000 times, but still failed. Please check the server status."") + raise Exception(e.response) + else: + break + return stream.choices[0].message.content + + def translate_conversations(input_file, output_file): + df = pd.read_json(input_file, lines=True) + # df = df.head(2) + + def translate(translate_target): + # 번역 어투 고정을 위한 예시 하나, 처음 번역에 사용 + TRANSLATE_EXAMPLE = [ + { + ""role"": ""user"", + ""content"": ""Given the functions $f(x) = \log_a(1+x)$ and $g(x) = \log_a(1-x)$, where $a>0$ and $a \neq 1$. 1. Find the domain of the function $f(x) - g(x)$. 2. Determine the parity of the function $f(x) - g(x)$. 3. Find the range of $x$ for which $f(x) - g(x) > 0$."" + }, + { + ""role"": ""assistant"", + ""content"": ""함수 $f(x) = \log_a(1+x)$ 와 $g(x) = \log_a(1-x)$가 주어지고, 여기서 $a>0$이고 $a \neq 1$입니다. 1. 함수 $f(x) - g(x)$의 정의역을 구하세요. 2. 함수 $f(x) - g(x)$의 패리티(parity)를 결정하세요. 3. $f(x) - g(x) > 0$인 $x$의 치역을 찾으세요."" + }, + ] + previous_translate_results = TRANSLATE_EXAMPLE + translate_result = solar_translate_apicall(source_input=translate_target, previous_translate_results=previous_translate_results) + return translate_result + + def translate_with_question(q_en, q_ko, translate_target): + # 이전 질문 번역 결과 + TRANSLATE_EXAMPLE = [ + { + ""role"": ""user"", + ""content"": q_en + }, + { + ""role"": ""assistant"", + ""content"": q_ko + }, + ] + previous_translate_results = TRANSLATE_EXAMPLE + translate_result = solar_translate_apicall(source_input=translate_target, previous_translate_results=previous_translate_results) + return translate_result + + df['problem_ko'] = df['problem'].progress_apply(translate) + + df['solution_ko'] = df.progress_apply(lambda row: translate_with_question(row['problem'], row['problem_ko'], row['solution']), axis=1) + + df = df[['source', 'problem', 'problem_ko', 'solution', 'solution_ko']] + # Save to jsonl + df.to_json(output_file, orient='records', lines=True, force_ascii=False) + print(""*****************************"") + print(f""!!!!!!!!!번역 완료!!!!!!!!!!!"") + print(""*****************************"") + + return + + if __name__ == ""__main__"": + parser = argparse.ArgumentParser(description=""Process two filenames."") + parser.add_argument('--filename1', type=str, required=True, help='The first filename.') + parser.add_argument('--filename2', type=str, required=True, help='The second filename.') + + args = parser.parse_args() + print(f""번역 파일: {args.filename1}"") + translate_conversations(args.filename1, args.filename2) + + # RUN: python translate_3.py --filename1 ""$input_file"" --filename2 ""$output_file"" +``` +
" +youjunhyeok/ko-orca-pair-and-ultrafeedback-dpo,"{""language"": [""ko""], ""dataset_info"": {""features"": [{""name"": ""system"", ""dtype"": ""string""}, {""name"": ""chosen"", ""dtype"": ""string""}, {""name"": ""rejected"", ""dtype"": ""string""}, {""name"": ""prompt"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 260168570, ""num_examples"": 72522}], ""download_size"": 128044938, ""dataset_size"": 260168570}, ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""train"", ""path"": ""data/train-*""}]}]}","![image/png](https://cdn-uploads.huggingface.co/production/uploads/662b0e178f99c264f1745716/RZ5ovDBgiY9b-9LsQ2Hop.png) + + +위 표에 기재된 데이터셋들을 merge했습니다. + +rating이 있는 데이터셋의 경우 chosen 점수가 높은 것만 선택됐습니다." +Yettiesoft/voice_medical,"{""language"": [""ko""], ""license"": ""other"", ""task_categories"": [""automatic-speech-recognition""], ""license_name"": ""aihub"", ""license_link"": ""https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&aihubDataSe=data&dataSetSn=71481"", ""dataset_info"": {""features"": [{""name"": ""audio"", ""dtype"": {""audio"": {""sampling_rate"": 16000}}}, {""name"": ""transcripts"", ""dtype"": ""string""}], ""splits"": [{""name"": ""train"", ""num_bytes"": 9673667615.284883, ""num_examples"": 137}, {""name"": ""test"", ""num_bytes"": 1368683535.4534883, ""num_examples"": 18}, {""name"": ""valid"", ""num_bytes"": 1243473658.261628, ""num_examples"": 17}], ""download_size"": 12140057435, ""dataset_size"": 12285824809.0}, ""configs"": [{""config_name"": ""default"", ""data_files"": [{""split"": ""train"", ""path"": ""data/train-*""}, {""split"": ""test"", ""path"": ""data/test-*""}, {""split"": ""valid"", ""path"": ""data/valid-*""}]}]}", +rombodawg/Everything_Instruct_Multilingual,"{""license"": ""apache-2.0"", ""language"": [""en"", ""ru"", ""zh"", ""ko"", ""ur"", ""la"", ""ar"", ""de"", ""es"", ""fr"", ""hi"", ""it"", ""ja"", ""nl"", ""pt""], ""tags"": [""Num_Rows = 7,799,967"", ""Max_length = 8180""]}","# Everything Instruct (Multilingual Edition) + +Everything you need... all in one place 💘 + +![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/c3GAm2rFnFqt0ng_stzEv.jpeg) + +Everything instruct (Multilingual Edition) is a massive alpaca instruct formatted dataset consisting of a wide variety of topics meant to bring LLM's to the next level in open source AI. + +Note: This dataset is fully uncensored (No model will refuse any request trained on this dataset unless otherwise aligned) + +Note2: This version of the dataset supports the following languages: + +- English +- Russian +- Chinese +- Korean +- Urdu +- Latin +- Arabic +- German +- Spanish +- French +- Hindi +- Italian +- Japanese +- Dutch +- Portuguese +__________________________________________________________________________________ + +The data in this dataset features: + +Science: 12,580 rows + +Social media: 18,405 rows + +General Knowledge: 906,346 rows + +Multi-lingual: 2,937,785 rows + +Cooking: 20,763 rows + +Writing: 414,646 rows + +Medicine: 36,738 rows + +History: 10,178 rows + +Law: 90,394 rows + +Role-Play: 433,205 rows + +News: 124,542 rows + +Coding: 2,872,975 rows + +Math: 262,039 rows + +Function calling: 112,960 rows + +General Instruct: 998,854 rows + +__________________________________________________________________________________ + +Here are some statistical graphics to show off the data. + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/Ef7QoAwL6Se_XKXozy-Wi.png) + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/cZMFnzWtW_aeoAldXSMHK.png) + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/rGzf_NQYqmnqBg6uzGyEp.png) + +I hope you finetune some amazing models that break the barrier between open and closed source with my data. + +__________________________________________________________________________________ + +The data in this data set is from the following sources: + +## Science: + +- antiven0m/physical-reasoning-dpoScience +- LawalAfeez/science-dataset + +## Social media: + +- Kyle1668/AG-Tweets +- euclaise/reddit-instruct-curated + +## General Knowledge: + +- NousResearch/CharacterCodex_Characters +- jstet/quotes-500k_Famous_Quotes +- FronkonGames/steam-games-dataset_Video_Games +- totuta_youtube_subs_howto100M_HowTo + +## Multi-lingual: + +- Amani27/massive_translation_dataset +- udmurtNLP/udmurt-russian-english-labse +- grosenthal/latin_english +- msarmi9/korean-english-multitarget-ted-talks-task +- HaiderSultanArc/MT-Urdu-English_Translate +- Garsa3112/ChineseEnglishTranslationDataset + +## Cooking: + +- andrewsiah/se_cooking_preference_sft +- Hieu-Phamkaggle/food_recipes + +## Writing: + +- shahules786/PoetryFoundationData +- euclaise/writingprompts +- qwedsacf/ivypanda-essaysEssay + +## Medicine: + +- keivalya/MedQuad-MedicalQnADataset +- nuvocare/MSD + +## History: + +- ambrosfitz10k/history_data_v4 + +## Law: + +- dzunggg/legal-qa-v1 + +## Role-Play: + +- roleplay4/fun_CoupleRP +- Undi95andrijdavid/roleplay-conversation-sharegpt + +## News: + +- RealTimeData/bbc_news_alltime + +## Coding: (rombodawg/code_bagel) + +- layoric/tiny-codes-alpaca +- glaiveai/glaive-code-assistant-v3 +- ajibawa-2023/Code-290k-ShareGPT +- chargoddard/commitpack-ft-instruct-rated +- iamtarun/code_instructions_120k_alpaca +- ise-uiuc/Magicoder-Evol-Instruct-110K +- cognitivecomputations/dolphin-coder +- nickrosh/Evol-Instruct-Code-80k-v1 +- coseal/CodeUltraFeedback_binarized +- CyberNative/Code_Vulnerability_Security_DPO + +## Math: (rombodawg/code_bagel) + +- TIGER-Lab/MathInstruct + +## Function calling: (rombodawg/code_bagel) + +- glaiveai/glaive-function-calling-v2 + +## General Instruct: (rombodawg/OpenHermes-2.5-Uncensored) + +- teknium/OpenHermes-2.5" +ChuGyouk/argilla-distilabel-math-preference-dpo-korean,"{""license"": ""apache-2.0"", ""language"": [""en"", ""ko""]}","# Dataset Information + +This is a gpt-4o-2024-08-06 Korean translated-version of [argilla/distilabel-math-preference-dpo](https://huggingface.co/datasets/argilla/distilabel-math-preference-dpo?row=13). + +I used OpenAI BATCH API with prompt below, temperature=0.0, max_tokens=4000, seed=0. Total cost was 11.71$. + +Note that for the 1317th data, because it did not satisfy the format given in the instruction, I modified it. (For example, for mark, even this was translated as <의문>.) + +## Prompt +>You are tasked with translating English text into Korean for Direct Preference Optimization training data. This data consists of a question, a chosen response, and a rejected response. Your goal is to accurately translate the content while preserving the meaning and structure of the original text. +> +>Here is the content to translate: +> +>Question: +>\ +>{QUESTION} +>\ +> +>Chosen Response: +>\ +>{CHOSEN_RESPONSE} +>\ +> +>Rejected Response: +>\ +>{REJECTED_RESPONSE} +>\ +> +>Please follow these steps: +> +>1. Translate the question from English to Korean. +>2. Translate the chosen response from English to Korean. +>3. Translate the rejected response from English to Korean. +> +>Follow these guidelines when translating: +> +>1. Translate the text from English to Korean accurately, maintaining the original meaning and tone. +>2. Do not translate mathematical expressions or equations. Leave them as they are in the original text. +>3. Preserve any formatting, such as white spaces, line breaks or bullet points, in your translation. +>4. Maintain the distinction between the chosen response and the rejected response in your translation. This difference should be clear in the Korean version as well. +> +>Provide your translation in the following format: +> +>\ +>[Insert Korean translation of the question here] +>\ +> +>\ +>[Insert Korean translation of the chosen response here] +>\ +> +>\ +>[Insert Korean translation of the rejected response here] +>\ +> +>Ensure that the distinction between the chosen and rejected responses remains clear in your translation. Also, Ensure that the difference between the chosen response and the rejected response remains clear in the Korean translation. The nuances that make one response preferred over the other should be preserved. If there are any culturally specific references or idioms that don't have a direct Korean equivalent, provide the closest appropriate translation and add a brief explanation in parentheses if necessary." +copenlu/tydiqa_copenlu,"{""pretty_name"": ""TyDi QA"", ""annotations_creators"": [""crowdsourced""], ""language_creators"": [""crowdsourced""], ""language"": [""ar"", ""bn"", ""en"", ""fi"", ""id"", ""ja"", ""ko"", ""ru"", ""sw"", ""te"", ""th""], ""license"": [""apache-2.0""], ""multilinguality"": [""multilingual""], ""size_categories"": [""unknown""], ""source_datasets"": [""extended|wikipedia""], ""task_categories"": [""question-answering""], ""task_ids"": [""extractive-qa""], ""paperswithcode_id"": ""tydi-qa""}","# Dataset Card for ""tydiqa"" + +## Table of Contents +- [Dataset Description](#dataset-description) + - [Dataset Summary](#dataset-summary) + - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) + - [Languages](#languages) +- [Dataset Structure](#dataset-structure) + - [Data Instances](#data-instances) + - [Data Fields](#data-fields) + - [Data Splits](#data-splits) +- [Dataset Creation](#dataset-creation) + - [Curation Rationale](#curation-rationale) + - [Source Data](#source-data) + - [Annotations](#annotations) + - [Personal and Sensitive Information](#personal-and-sensitive-information) +- [Considerations for Using the Data](#considerations-for-using-the-data) + - [Social Impact of Dataset](#social-impact-of-dataset) + - [Discussion of Biases](#discussion-of-biases) + - [Other Known Limitations](#other-known-limitations) +- [Additional Information](#additional-information) + - [Dataset Curators](#dataset-curators) + - [Licensing Information](#licensing-information) + - [Citation Information](#citation-information) + - [Contributions](#contributions) + +## Dataset Description + +- **Homepage:** [https://github.com/google-research-datasets/tydiqa](https://github.com/google-research-datasets/tydiqa) +- **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) +- **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) +- **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) +- **Size of downloaded dataset files:** 3726.74 MB +- **Size of the generated dataset:** 5812.92 MB +- **Total amount of disk used:** 9539.67 MB + +### Dataset Summary + +TyDi QA is a question answering dataset covering 11 typologically diverse languages with 204K question-answer pairs. +The languages of TyDi QA are diverse with regard to their typology -- the set of linguistic features that each language +expresses -- such that we expect models performing well on this set to generalize across a large number of the languages +in the world. It contains language phenomena that would not be found in English-only corpora. To provide a realistic +information-seeking task and avoid priming effects, questions are written by people who want to know the answer, but +don’t know the answer yet, (unlike SQuAD and its descendents) and the data is collected directly in each language without +the use of translation (unlike MLQA and XQuAD). + +### Supported Tasks and Leaderboards + +[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) + +### Languages + +[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) + +## Dataset Structure + +### Data Instances + +#### primary_task + +- **Size of downloaded dataset files:** 1863.37 MB +- **Size of the generated dataset:** 5757.59 MB +- **Total amount of disk used:** 7620.96 MB + +An example of 'validation' looks as follows. +``` +This example was too long and was cropped: + +{ + ""annotations"": { + ""minimal_answers_end_byte"": [-1, -1, -1], + ""minimal_answers_start_byte"": [-1, -1, -1], + ""passage_answer_candidate_index"": [-1, -1, -1], + ""yes_no_answer"": [""NONE"", ""NONE"", ""NONE""] + }, + ""document_plaintext"": ""\""\\nรองศาสตราจารย์[1] หม่อมราชวงศ์สุขุมพันธุ์ บริพัตร (22 กันยายน 2495 -) ผู้ว่าราชการกรุงเทพมหานครคนที่ 15 อดีตรองหัวหน้าพรรคปร..."", + ""document_title"": ""หม่อมราชวงศ์สุขุมพันธุ์ บริพัตร"", + ""document_url"": ""\""https://th.wikipedia.org/wiki/%E0%B8%AB%E0%B8%A1%E0%B9%88%E0%B8%AD%E0%B8%A1%E0%B8%A3%E0%B8%B2%E0%B8%8A%E0%B8%A7%E0%B8%87%E0%B8%..."", + ""language"": ""thai"", + ""passage_answer_candidates"": ""{\""plaintext_end_byte\"": [494, 1779, 2931, 3904, 4506, 5588, 6383, 7122, 8224, 9375, 10473, 12563, 15134, 17765, 19863, 21902, 229..."", + ""question_text"": ""\""หม่อมราชวงศ์สุขุมพันธุ์ บริพัตร เรียนจบจากที่ไหน ?\""..."" +} +``` + +#### secondary_task + +- **Size of downloaded dataset files:** 1863.37 MB +- **Size of the generated dataset:** 55.34 MB +- **Total amount of disk used:** 1918.71 MB + +An example of 'validation' looks as follows. +``` +This example was too long and was cropped: + +{ + ""answers"": { + ""answer_start"": [394], + ""text"": [""بطولتين""] + }, + ""context"": ""\""أقيمت البطولة 21 مرة، شارك في النهائيات 78 دولة، وعدد الفرق التي فازت بالبطولة حتى الآن 8 فرق، ويعد المنتخب البرازيلي الأكثر تت..."", + ""id"": ""arabic-2387335860751143628-1"", + ""question"": ""\""كم عدد مرات فوز الأوروغواي ببطولة كاس العالم لكرو القدم؟\""..."", + ""title"": ""قائمة نهائيات كأس العالم"" +} +``` + +### Data Fields + +The data fields are the same among all splits. + +#### primary_task +- `passage_answer_candidates`: a dictionary feature containing: + - `plaintext_start_byte`: a `int32` feature. + - `plaintext_end_byte`: a `int32` feature. +- `question_text`: a `string` feature. +- `document_title`: a `string` feature. +- `language`: a `string` feature. +- `annotations`: a dictionary feature containing: + - `passage_answer_candidate_index`: a `int32` feature. + - `minimal_answers_start_byte`: a `int32` feature. + - `minimal_answers_end_byte`: a `int32` feature. + - `yes_no_answer`: a `string` feature. +- `document_plaintext`: a `string` feature. +- `document_url`: a `string` feature. + +#### secondary_task +- `id`: a `string` feature. +- `title`: a `string` feature. +- `context`: a `string` feature. +- `question`: a `string` feature. +- `answers`: a dictionary feature containing: + - `text`: a `string` feature. + - `answer_start`: a `int32` feature. + +### Data Splits + +| name | train | validation | +| -------------- | -----: | ---------: | +| primary_task | 166916 | 18670 | +| secondary_task | 49881 | 5077 | + +## Dataset Creation + +### Curation Rationale + +[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) + +### Source Data + +#### Initial Data Collection and Normalization + +[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) + +#### Who are the source language producers? + +[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) + +### Annotations + +#### Annotation process + +[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) + +#### Who are the annotators? + +[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) + +### Personal and Sensitive Information + +[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) + +## Considerations for Using the Data + +### Social Impact of Dataset + +[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) + +### Discussion of Biases + +[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) + +### Other Known Limitations + +[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) + +## Additional Information + +### Dataset Curators + +[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) + +### Licensing Information + +[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) + +### Citation Information + +``` +@article{tydiqa, +title = {TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages}, +author = {Jonathan H. Clark and Eunsol Choi and Michael Collins and Dan Garrette and Tom Kwiatkowski and Vitaly Nikolaev and Jennimaria Palomaki} +year = {2020}, +journal = {Transactions of the Association for Computational Linguistics} +} + +``` + + +### Contributions + +Thanks to [@thomwolf](https://github.com/thomwolf), [@albertvillanova](https://github.com/albertvillanova), [@lewtun](https://github.com/lewtun), [@patrickvonplaten](https://github.com/patrickvonplaten) for adding this dataset." +KETI-AIR/kor_amazon_polarity,"{""language"": [""ko""], ""license"": ""cc0-1.0"", ""size_categories"": [""1M