opus-mt-en-cpf

eng-cpf

  • source group: English

  • target group: Creoles and pidgins, French‑based

  • OPUS readme: eng-cpf

  • model: transformer

  • source language(s): eng

  • target language(s): gcf_Latn hat mfe

  • 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-2020-07-26.zip

  • test set translations: opus-2020-07-26.test.txt

  • test set scores: opus-2020-07-26.eval.txt

Benchmarks

testset BLEU chr-F
Tatoeba-test.eng-gcf.eng.gcf 6.2 0.262
Tatoeba-test.eng-hat.eng.hat 25.7 0.451
Tatoeba-test.eng-mfe.eng.mfe 80.1 0.900
Tatoeba-test.eng.multi 15.9 0.354

System Info:

Downloads last month
21
Hosted inference API
Translation