library_name: transformers
language:
- br
- cy
- de
- en
- es
- fr
- ga
- gd
- gv
- kw
- pt
tags:
- translation
- opus-mt-tc-bible
license: apache-2.0
model-index:
- name: opus-mt-tc-bible-big-cel-deu_eng_fra_por_spa
results:
- task:
name: Translation cym-deu
type: translation
args: cym-deu
dataset:
name: flores200-devtest
type: flores200-devtest
args: cym-deu
metrics:
- name: BLEU
type: bleu
value: 22.6
- name: chr-F
type: chrf
value: 0.52745
- task:
name: Translation cym-eng
type: translation
args: cym-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: cym-eng
metrics:
- name: BLEU
type: bleu
value: 55.5
- name: chr-F
type: chrf
value: 0.75234
- task:
name: Translation cym-fra
type: translation
args: cym-fra
dataset:
name: flores200-devtest
type: flores200-devtest
args: cym-fra
metrics:
- name: BLEU
type: bleu
value: 31.4
- name: chr-F
type: chrf
value: 0.58339
- task:
name: Translation cym-por
type: translation
args: cym-por
dataset:
name: flores200-devtest
type: flores200-devtest
args: cym-por
metrics:
- name: BLEU
type: bleu
value: 18.3
- name: chr-F
type: chrf
value: 0.47566
- task:
name: Translation cym-spa
type: translation
args: cym-spa
dataset:
name: flores200-devtest
type: flores200-devtest
args: cym-spa
metrics:
- name: BLEU
type: bleu
value: 19.9
- name: chr-F
type: chrf
value: 0.48834
- task:
name: Translation gla-deu
type: translation
args: gla-deu
dataset:
name: flores200-devtest
type: flores200-devtest
args: gla-deu
metrics:
- name: BLEU
type: bleu
value: 13
- name: chr-F
type: chrf
value: 0.41962
- task:
name: Translation gla-eng
type: translation
args: gla-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: gla-eng
metrics:
- name: BLEU
type: bleu
value: 26.4
- name: chr-F
type: chrf
value: 0.53374
- task:
name: Translation gla-fra
type: translation
args: gla-fra
dataset:
name: flores200-devtest
type: flores200-devtest
args: gla-fra
metrics:
- name: BLEU
type: bleu
value: 16.6
- name: chr-F
type: chrf
value: 0.44916
- task:
name: Translation gla-por
type: translation
args: gla-por
dataset:
name: flores200-devtest
type: flores200-devtest
args: gla-por
metrics:
- name: BLEU
type: bleu
value: 12.1
- name: chr-F
type: chrf
value: 0.3979
- task:
name: Translation gla-spa
type: translation
args: gla-spa
dataset:
name: flores200-devtest
type: flores200-devtest
args: gla-spa
metrics:
- name: BLEU
type: bleu
value: 12.9
- name: chr-F
type: chrf
value: 0.40375
- task:
name: Translation gle-deu
type: translation
args: gle-deu
dataset:
name: flores200-devtest
type: flores200-devtest
args: gle-deu
metrics:
- name: BLEU
type: bleu
value: 19.2
- name: chr-F
type: chrf
value: 0.49962
- task:
name: Translation gle-eng
type: translation
args: gle-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: gle-eng
metrics:
- name: BLEU
type: bleu
value: 38.9
- name: chr-F
type: chrf
value: 0.64866
- task:
name: Translation gle-fra
type: translation
args: gle-fra
dataset:
name: flores200-devtest
type: flores200-devtest
args: gle-fra
metrics:
- name: BLEU
type: bleu
value: 26.7
- name: chr-F
type: chrf
value: 0.54564
- task:
name: Translation gle-por
type: translation
args: gle-por
dataset:
name: flores200-devtest
type: flores200-devtest
args: gle-por
metrics:
- name: BLEU
type: bleu
value: 14.9
- name: chr-F
type: chrf
value: 0.44768
- task:
name: Translation gle-spa
type: translation
args: gle-spa
dataset:
name: flores200-devtest
type: flores200-devtest
args: gle-spa
metrics:
- name: BLEU
type: bleu
value: 18.7
- name: chr-F
type: chrf
value: 0.47347
- task:
name: Translation cym-deu
type: translation
args: cym-deu
dataset:
name: flores101-devtest
type: flores_101
args: cym deu devtest
metrics:
- name: BLEU
type: bleu
value: 22.4
- name: chr-F
type: chrf
value: 0.52672
- task:
name: Translation cym-fra
type: translation
args: cym-fra
dataset:
name: flores101-devtest
type: flores_101
args: cym fra devtest
metrics:
- name: BLEU
type: bleu
value: 31.3
- name: chr-F
type: chrf
value: 0.58299
- task:
name: Translation cym-por
type: translation
args: cym-por
dataset:
name: flores101-devtest
type: flores_101
args: cym por devtest
metrics:
- name: BLEU
type: bleu
value: 18.4
- name: chr-F
type: chrf
value: 0.47733
- task:
name: Translation gle-eng
type: translation
args: gle-eng
dataset:
name: flores101-devtest
type: flores_101
args: gle eng devtest
metrics:
- name: BLEU
type: bleu
value: 38.6
- name: chr-F
type: chrf
value: 0.64773
- task:
name: Translation gle-fra
type: translation
args: gle-fra
dataset:
name: flores101-devtest
type: flores_101
args: gle fra devtest
metrics:
- name: BLEU
type: bleu
value: 26.5
- name: chr-F
type: chrf
value: 0.54559
- task:
name: Translation cym-deu
type: translation
args: cym-deu
dataset:
name: ntrex128
type: ntrex128
args: cym-deu
metrics:
- name: BLEU
type: bleu
value: 16.3
- name: chr-F
type: chrf
value: 0.46627
- task:
name: Translation cym-eng
type: translation
args: cym-eng
dataset:
name: ntrex128
type: ntrex128
args: cym-eng
metrics:
- name: BLEU
type: bleu
value: 40
- name: chr-F
type: chrf
value: 0.65343
- task:
name: Translation cym-fra
type: translation
args: cym-fra
dataset:
name: ntrex128
type: ntrex128
args: cym-fra
metrics:
- name: BLEU
type: bleu
value: 23.8
- name: chr-F
type: chrf
value: 0.51183
- task:
name: Translation cym-por
type: translation
args: cym-por
dataset:
name: ntrex128
type: ntrex128
args: cym-por
metrics:
- name: BLEU
type: bleu
value: 14.4
- name: chr-F
type: chrf
value: 0.42857
- task:
name: Translation cym-spa
type: translation
args: cym-spa
dataset:
name: ntrex128
type: ntrex128
args: cym-spa
metrics:
- name: BLEU
type: bleu
value: 25
- name: chr-F
type: chrf
value: 0.51542
- task:
name: Translation gle-deu
type: translation
args: gle-deu
dataset:
name: ntrex128
type: ntrex128
args: gle-deu
metrics:
- name: BLEU
type: bleu
value: 15.5
- name: chr-F
type: chrf
value: 0.46495
- task:
name: Translation gle-eng
type: translation
args: gle-eng
dataset:
name: ntrex128
type: ntrex128
args: gle-eng
metrics:
- name: BLEU
type: bleu
value: 33.5
- name: chr-F
type: chrf
value: 0.60913
- task:
name: Translation gle-fra
type: translation
args: gle-fra
dataset:
name: ntrex128
type: ntrex128
args: gle-fra
metrics:
- name: BLEU
type: bleu
value: 20.7
- name: chr-F
type: chrf
value: 0.49513
- task:
name: Translation gle-por
type: translation
args: gle-por
dataset:
name: ntrex128
type: ntrex128
args: gle-por
metrics:
- name: BLEU
type: bleu
value: 13.2
- name: chr-F
type: chrf
value: 0.41767
- task:
name: Translation gle-spa
type: translation
args: gle-spa
dataset:
name: ntrex128
type: ntrex128
args: gle-spa
metrics:
- name: BLEU
type: bleu
value: 23.6
- name: chr-F
type: chrf
value: 0.50755
- task:
name: Translation bre-eng
type: translation
args: bre-eng
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: bre-eng
metrics:
- name: BLEU
type: bleu
value: 35
- name: chr-F
type: chrf
value: 0.53473
- task:
name: Translation bre-fra
type: translation
args: bre-fra
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: bre-fra
metrics:
- name: BLEU
type: bleu
value: 28.3
- name: chr-F
type: chrf
value: 0.49013
- task:
name: Translation cym-eng
type: translation
args: cym-eng
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: cym-eng
metrics:
- name: BLEU
type: bleu
value: 52.4
- name: chr-F
type: chrf
value: 0.68892
- task:
name: Translation gla-eng
type: translation
args: gla-eng
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: gla-eng
metrics:
- name: BLEU
type: bleu
value: 23.2
- name: chr-F
type: chrf
value: 0.39607
- task:
name: Translation gla-spa
type: translation
args: gla-spa
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: gla-spa
metrics:
- name: BLEU
type: bleu
value: 26.1
- name: chr-F
type: chrf
value: 0.51208
- task:
name: Translation gle-eng
type: translation
args: gle-eng
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: gle-eng
metrics:
- name: BLEU
type: bleu
value: 50.7
- name: chr-F
type: chrf
value: 0.64268
- task:
name: Translation multi-multi
type: translation
args: multi-multi
dataset:
name: tatoeba-test-v2020-07-28-v2023-09-26
type: tatoeba_mt
args: multi-multi
metrics:
- name: BLEU
type: bleu
value: 24.9
- name: chr-F
type: chrf
value: 0.4267
opus-mt-tc-bible-big-cel-deu_eng_fra_por_spa
Table of Contents
- Model Details
- Uses
- Risks, Limitations and Biases
- How to Get Started With the Model
- Training
- Evaluation
- Citation Information
- Acknowledgements
Model Details
Neural machine translation model for translating from Celtic languages (cel) to unknown (deu+eng+fra+por+spa).
This model is part of the OPUS-MT project, an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of Marian NMT, an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from OPUS and training pipelines use the procedures of OPUS-MT-train. Model Description:
- Developed by: Language Technology Research Group at the University of Helsinki
- Model Type: Translation (transformer-big)
- Release: 2024-05-30
- License: Apache-2.0
- Language(s):
- Source Language(s): bre cor cym gla gle glv
- Target Language(s): deu eng fra por spa
- Valid Target Language Labels: >>deu<< >>eng<< >>fra<< >>por<< >>spa<< >>xxx<<
- Original Model: opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip
- Resources for more information:
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of >>id<<
(id = valid target language ID), e.g. >>deu<<
Uses
This model can be used for translation and text-to-text generation.
Risks, Limitations and Biases
CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.
Significant research has explored bias and fairness issues with language models (see, e.g., Sheng et al. (2021) and Bender et al. (2021)).
How to Get Started With the Model
A short example code:
from transformers import MarianMTModel, MarianTokenizer
src_text = [
">>deu<< Replace this with text in an accepted source language.",
">>spa<< This is the second sentence."
]
model_name = "pytorch-models/opus-mt-tc-bible-big-cel-deu_eng_fra_por_spa"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
You can also use OPUS-MT models with the transformers pipelines, for example:
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-bible-big-cel-deu_eng_fra_por_spa")
print(pipe(">>deu<< Replace this with text in an accepted source language."))
Training
- Data: opusTCv20230926max50+bt+jhubc (source)
- Pre-processing: SentencePiece (spm32k,spm32k)
- Model Type: transformer-big
- Original MarianNMT Model: opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip
- Training Scripts: GitHub Repo
Evaluation
- Model scores at the OPUS-MT dashboard
- test set translations: opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.test.txt
- test set scores: opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.eval.txt
- benchmark results: benchmark_results.txt
- benchmark output: benchmark_translations.zip
langpair | testset | chr-F | BLEU | #sent | #words |
---|---|---|---|---|---|
bre-eng | tatoeba-test-v2021-08-07 | 0.53473 | 35.0 | 383 | 2065 |
bre-fra | tatoeba-test-v2021-08-07 | 0.49013 | 28.3 | 2494 | 13324 |
cym-eng | tatoeba-test-v2021-08-07 | 0.68892 | 52.4 | 818 | 5563 |
gla-eng | tatoeba-test-v2021-08-07 | 0.39607 | 23.2 | 955 | 6611 |
gla-spa | tatoeba-test-v2021-08-07 | 0.51208 | 26.1 | 289 | 1608 |
gle-eng | tatoeba-test-v2021-08-07 | 0.64268 | 50.7 | 1913 | 11190 |
cym-deu | flores101-devtest | 0.52672 | 22.4 | 1012 | 25094 |
cym-fra | flores101-devtest | 0.58299 | 31.3 | 1012 | 28343 |
cym-por | flores101-devtest | 0.47733 | 18.4 | 1012 | 26519 |
gle-eng | flores101-devtest | 0.64773 | 38.6 | 1012 | 24721 |
gle-fra | flores101-devtest | 0.54559 | 26.5 | 1012 | 28343 |
cym-deu | flores200-devtest | 0.52745 | 22.6 | 1012 | 25094 |
cym-eng | flores200-devtest | 0.75234 | 55.5 | 1012 | 24721 |
cym-fra | flores200-devtest | 0.58339 | 31.4 | 1012 | 28343 |
cym-por | flores200-devtest | 0.47566 | 18.3 | 1012 | 26519 |
cym-spa | flores200-devtest | 0.48834 | 19.9 | 1012 | 29199 |
gla-deu | flores200-devtest | 0.41962 | 13.0 | 1012 | 25094 |
gla-eng | flores200-devtest | 0.53374 | 26.4 | 1012 | 24721 |
gla-fra | flores200-devtest | 0.44916 | 16.6 | 1012 | 28343 |
gla-spa | flores200-devtest | 0.40375 | 12.9 | 1012 | 29199 |
gle-deu | flores200-devtest | 0.49962 | 19.2 | 1012 | 25094 |
gle-eng | flores200-devtest | 0.64866 | 38.9 | 1012 | 24721 |
gle-fra | flores200-devtest | 0.54564 | 26.7 | 1012 | 28343 |
gle-por | flores200-devtest | 0.44768 | 14.9 | 1012 | 26519 |
gle-spa | flores200-devtest | 0.47347 | 18.7 | 1012 | 29199 |
cym-deu | ntrex128 | 0.46627 | 16.3 | 1997 | 48761 |
cym-eng | ntrex128 | 0.65343 | 40.0 | 1997 | 47673 |
cym-fra | ntrex128 | 0.51183 | 23.8 | 1997 | 53481 |
cym-por | ntrex128 | 0.42857 | 14.4 | 1997 | 51631 |
cym-spa | ntrex128 | 0.51542 | 25.0 | 1997 | 54107 |
gle-deu | ntrex128 | 0.46495 | 15.5 | 1997 | 48761 |
gle-eng | ntrex128 | 0.60913 | 33.5 | 1997 | 47673 |
gle-fra | ntrex128 | 0.49513 | 20.7 | 1997 | 53481 |
gle-por | ntrex128 | 0.41767 | 13.2 | 1997 | 51631 |
gle-spa | ntrex128 | 0.50755 | 23.6 | 1997 | 54107 |
Citation Information
- Publications: Democratizing neural machine translation with OPUS-MT and OPUS-MT – Building open translation services for the World and The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT (Please, cite if you use this model.)
@article{tiedemann2023democratizing,
title={Democratizing neural machine translation with {OPUS-MT}},
author={Tiedemann, J{\"o}rg and Aulamo, Mikko and Bakshandaeva, Daria and Boggia, Michele and Gr{\"o}nroos, Stig-Arne and Nieminen, Tommi and Raganato, Alessandro and Scherrer, Yves and Vazquez, Raul and Virpioja, Sami},
journal={Language Resources and Evaluation},
number={58},
pages={713--755},
year={2023},
publisher={Springer Nature},
issn={1574-0218},
doi={10.1007/s10579-023-09704-w}
}
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic 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://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
Acknowledgements
The work is supported by the HPLT project, funded by the European Union’s Horizon Europe research and innovation programme under grant agreement No 101070350. We are also grateful for the generous computational resources and IT infrastructure provided by CSC -- IT Center for Science, Finland, and the EuroHPC supercomputer LUMI.
Model conversion info
- transformers version: 4.45.1
- OPUS-MT git hash: a0ea3b3
- port time: Mon Oct 7 23:09:42 EEST 2024
- port machine: LM0-400-22516.local