- dataset: opus
- model: transformer-align
- source language(s): deu
- target language(s): rus
- model: transformer-align
- pre-processing: normalization + SentencePiece (spm32k,spm32k)
- download: opus-2021-05-15.zip
- test set translations: opus-2021-05-15.test.txt
- test set scores: opus-2021-05-15.eval.txt
| testset | BLEU | chr-F | #sent | #words | BP |
|---|---|---|---|---|---|
| newstest2012.deu-rus | 18.2 | 0.458 | 3003 | 64830 | 0.979 |
| newstest2013.deu-rus | 21.3 | 0.486 | 3000 | 58560 | 0.959 |
| Tatoeba-test.deu-rus | 45.0 | 0.654 | 10000 | 67433 | 0.966 |