opus-mt-itc-itc

itc-itc

• source group: Italic languages

• target group: Italic languages

• OPUS readme: itc-itc

• model: transformer

• source language(s): arg ast bjn cat cos egl fra frm_Latn gcf_Latn glg hat ind ita lad lad_Latn lat_Grek lat_Latn lij lld_Latn lmo mwl oci pap pcd pms por roh ron scn spa srd vec wln zsm_Latn

• target language(s): arg ast bjn cat cos egl fra frm_Latn gcf_Latn glg hat ind ita lad lad_Latn lat_Grek lat_Latn lij lld_Latn lmo mwl oci pap pcd pms por roh ron scn spa srd vec wln zsm_Latn

• model: transformer

• pre-processing: normalization + SentencePiece (spm32k,spm32k)

• a sentence initial language token is required in the form of >>id<< (id = valid target language ID)

• download original weights: opus-2020-07-07.zip

• test set translations: opus-2020-07-07.test.txt

• test set scores: opus-2020-07-07.eval.txt

Benchmarks

System Info:

• hf_name: itc-itc

• source_languages: itc

• target_languages: itc

• opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/itc-itc/README.md

• original_repo: Tatoeba-Challenge

• tags: ['translation']

• languages: ['it', 'ca', 'rm', 'es', 'ro', 'gl', 'sc', 'co', 'wa', 'pt', 'oc', 'an', 'id', 'fr', 'ht', 'itc']

• src_constituents: {'ita', 'cat', 'roh', 'spa', 'pap', 'bjn', 'lmo', 'mwl', 'lij', 'lat_Latn', 'lad_Latn', 'pcd', 'lat_Grek', 'ext', 'ron', 'ast', 'glg', 'pms', 'zsm_Latn', 'srd', 'gcf_Latn', 'lld_Latn', 'min', 'tmw_Latn', 'cos', 'wln', 'zlm_Latn', 'por', 'egl', 'oci', 'vec', 'arg', 'ind', 'fra', 'hat', 'lad', 'max_Latn', 'frm_Latn', 'scn', 'mfe'}

• tgt_constituents: {'ita', 'cat', 'roh', 'spa', 'pap', 'bjn', 'lmo', 'mwl', 'lij', 'lat_Latn', 'lad_Latn', 'pcd', 'lat_Grek', 'ext', 'ron', 'ast', 'glg', 'pms', 'zsm_Latn', 'srd', 'gcf_Latn', 'lld_Latn', 'min', 'tmw_Latn', 'cos', 'wln', 'zlm_Latn', 'por', 'egl', 'oci', 'vec', 'arg', 'ind', 'fra', 'hat', 'lad', 'max_Latn', 'frm_Latn', 'scn', 'mfe'}

• src_multilingual: True

• tgt_multilingual: True

• prepro: normalization + SentencePiece (spm32k,spm32k)

• url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/itc-itc/opus-2020-07-07.zip

• url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/itc-itc/opus-2020-07-07.test.txt

• src_alpha3: itc

• tgt_alpha3: itc

• short_pair: itc-itc

• chrF2_score: 0.599

• bleu: 40.8

• brevity_penalty: 0.968

• ref_len: 77448.0

• src_name: Italic languages

• tgt_name: Italic languages

• train_date: 2020-07-07

• src_alpha2: itc

• tgt_alpha2: itc

• prefer_old: False

• long_pair: itc-itc

• helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535

• transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b

• port_machine: brutasse

• port_time: 2020-08-21-14:41