- dataset: opus
- model: transformer-align
- source language(s): jpn
- target language(s): swe
- model: transformer-align
- pre-processing: normalization + SentencePiece (spm32k,spm32k)
- download: opus-2021-02-19.zip
- test set translations: opus-2021-02-19.test.txt
- test set scores: opus-2021-02-19.eval.txt
testset | BLEU | chr-F | #sent | #words | BP |
---|---|---|---|---|---|
Tatoeba-test.jpn-swe | 22.6 | 0.416 | 898 | 7034 | 0.841 |