- dataset: opus
- model: transformer
- source language(s): cmn cmn_Hans cmn_Hant nan wuu yue_Hans yue_Hant
- target language(s): hin
- model: transformer
- pre-processing: normalization + SentencePiece (spm32k,spm4k)
- download: opus-2020-09-10.zip
- test set translations: opus-2020-09-10.test.txt
- test set scores: opus-2020-09-10.eval.txt
testset | BLEU | chr-F |
---|---|---|
Tatoeba-test.zho.hin | 2.0 | 0.141 |