jpn-msa

  • source group: Japanese

  • target group: Malay (macrolanguage)

  • OPUS readme: jpn-msa

  • model: transformer-align

  • source language(s): jpn jpn_Hani jpn_Hira jpn_Kana

  • target language(s): ind zlm_Latn zsm_Latn

  • model: transformer-align

  • 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-2020-06-17.zip

  • test set translations: opus-2020-06-17.test.txt

  • test set scores: opus-2020-06-17.eval.txt

Benchmarks

testset BLEU chr-F
Tatoeba-test.jpn.msa 21.5 0.469

System Info:

Downloads last month
2
Hosted inference API
Translation