Skip to content

Latest commit

 

History

History
24 lines (20 loc) · 1.08 KB

README.md

File metadata and controls

24 lines (20 loc) · 1.08 KB

opus-2020-07-26.zip

  • dataset: opus
  • model: transformer
  • source language(s): eng
  • target language(s): hoc hoc_Latn kha khm khm_Latn mnw vie vie_Hani
  • 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: 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-hoc.eng.hoc 0.1 0.033
Tatoeba-test.eng-kha.eng.kha 0.4 0.043
Tatoeba-test.eng-khm.eng.khm 0.2 0.242
Tatoeba-test.eng-mnw.eng.mnw 0.8 0.003
Tatoeba-test.eng.multi 16.1 0.311
Tatoeba-test.eng-vie.eng.vie 33.2 0.508