Team Ai
Modelpublic

Helsinki-NLP/opus-mt-cpp-en

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes96downloads
Model Card

cpp-eng

  • —source group: Creoles and pidgins, Portuguese-based
  • —target group: English
  • —OPUS readme: cpp-eng

Benchmarks

testsetBLEUchr-F
Tatoeba-test.msa-eng.msa.eng39.60.580
Tatoeba-test.multi.eng39.70.580
Tatoeba-test.pap-eng.pap.eng49.10.579

System Info:

  • —hf_name: cpp-eng
  • —source_languages: cpp
  • —target_languages: eng
  • —opusreadmeurl: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/cpp-eng/README.md
  • —original_repo: Tatoeba-Challenge
  • —tags: ['translation']
  • —languages: ['id', 'cpp', 'en']
  • —srcconstituents: {'zsmLatn', 'ind', 'pap', 'min', 'tmwLatn', 'maxLatn', 'zlm_Latn'}
  • —tgt_constituents: {'eng'}
  • —src_multilingual: True
  • —tgt_multilingual: False
  • —prepro: normalization + SentencePiece (spm32k,spm32k)
  • —url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/cpp-eng/opus2m-2020-07-31.zip
  • —urltestset: https://object.pouta.csc.fi/Tatoeba-MT-models/cpp-eng/opus2m-2020-07-31.test.txt
  • —src_alpha3: cpp
  • —tgt_alpha3: eng
  • —short_pair: cpp-en
  • —chrF2_score: 0.58
  • —bleu: 39.7
  • —brevity_penalty: 0.972
  • —ref_len: 37399.0
  • —src_name: Creoles and pidgins, Portuguese-based
  • —tgt_name: English
  • —train_date: 2020-07-31
  • —src_alpha2: cpp
  • —tgt_alpha2: en
  • —prefer_old: False
  • —long_pair: cpp-eng
  • —helsinkigitsha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
  • —transformersgitsha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
  • —port_machine: brutasse
  • —port_time: 2020-08-21-14:41