- dataset: opus
- model: transformer-align
- source language(s): jpn
- target language(s): mar
- model: transformer-align
- pre-processing: normalization + SentencePiece (spm32k,spm4k)
- download: opus-2021-02-11.zip
- test set translations: opus-2021-02-11.test.txt
- test set scores: opus-2021-02-11.eval.txt
| testset | BLEU | chr-F |
|---|---|---|
| Tatoeba-test.jpn.mar | 0.3 | 0.088 |
| Tatoeba-test.jpn-mar.jpn.mar | 0.3 | 0.087 |