opus-unigram2 / tokenizer_config.json
speedcell4's picture
Upload tokenizer
2a451c4 verified
{
"added_tokens_decoder": {
"1": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64001": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64002": {
"content": "<af>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64003": {
"content": "<am>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64004": {
"content": "<ar>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64005": {
"content": "<as>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64006": {
"content": "<az>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64007": {
"content": "<be>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64008": {
"content": "<bg>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64009": {
"content": "<bn>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64010": {
"content": "<br>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64011": {
"content": "<bs>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64012": {
"content": "<ca>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64013": {
"content": "<cs>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64014": {
"content": "<cy>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64015": {
"content": "<da>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64016": {
"content": "<de>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64017": {
"content": "<el>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64018": {
"content": "<en>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64019": {
"content": "<eo>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64020": {
"content": "<es>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64021": {
"content": "<et>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64022": {
"content": "<eu>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64023": {
"content": "<fa>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64024": {
"content": "<fi>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64025": {
"content": "<fr>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64026": {
"content": "<fy>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64027": {
"content": "<ga>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64028": {
"content": "<gd>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64029": {
"content": "<gl>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64030": {
"content": "<gu>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64031": {
"content": "<ha>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64032": {
"content": "<he>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64033": {
"content": "<hi>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64034": {
"content": "<hr>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64035": {
"content": "<hu>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64036": {
"content": "<id>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64037": {
"content": "<ig>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64038": {
"content": "<is>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64039": {
"content": "<it>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64040": {
"content": "<ja>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64041": {
"content": "<ka>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64042": {
"content": "<kk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64043": {
"content": "<km>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64044": {
"content": "<kn>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64045": {
"content": "<ko>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64046": {
"content": "<ku>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64047": {
"content": "<ky>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64048": {
"content": "<li>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64049": {
"content": "<lt>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64050": {
"content": "<lv>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64051": {
"content": "<mg>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64052": {
"content": "<mk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64053": {
"content": "<ml>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64054": {
"content": "<mr>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64055": {
"content": "<ms>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64056": {
"content": "<mt>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64057": {
"content": "<my>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64058": {
"content": "<nb>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64059": {
"content": "<ne>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64060": {
"content": "<nl>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64061": {
"content": "<nn>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64062": {
"content": "<no>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64063": {
"content": "<oc>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64064": {
"content": "<or>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64065": {
"content": "<pa>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64066": {
"content": "<pl>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64067": {
"content": "<ps>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64068": {
"content": "<pt>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64069": {
"content": "<ro>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64070": {
"content": "<ru>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64071": {
"content": "<rw>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64072": {
"content": "<se>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64073": {
"content": "<sh>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64074": {
"content": "<si>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64075": {
"content": "<sk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64076": {
"content": "<sl>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64077": {
"content": "<sq>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64078": {
"content": "<sr>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64079": {
"content": "<sv>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64080": {
"content": "<ta>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64081": {
"content": "<te>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64082": {
"content": "<tg>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64083": {
"content": "<th>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64084": {
"content": "<tk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64085": {
"content": "<tr>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64086": {
"content": "<tt>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64087": {
"content": "<ug>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64088": {
"content": "<uk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64089": {
"content": "<ur>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64090": {
"content": "<uz>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64091": {
"content": "<vi>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64092": {
"content": "<wa>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64093": {
"content": "<xh>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64094": {
"content": "<yi>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64095": {
"content": "<zh>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64096": {
"content": "<zu>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<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>",
"<id>",
"<ig>",
"<is>",
"<it>",
"<ja>",
"<ka>",
"<kk>",
"<km>",
"<kn>",
"<ko>",
"<ku>",
"<ky>",
"<li>",
"<lt>",
"<lv>",
"<mg>",
"<mk>",
"<ml>",
"<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>",
"<zh>",
"<zu>"
],
"bos_token": "<eos>",
"clean_up_tokenization_spaces": true,
"cls_token": null,
"eos_token": "<eos>",
"legacy_behaviour": false,
"mask_token": null,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"sep_token": null,
"sp_model_kwargs": {},
"src_lang": "<en>",
"tgt_lang": null,
"tokenizer_class": "NllbTokenizer",
"unk_token": "<unk>"
}