- dataset: opus
- model: transformer
- source language(s): rus
- target language(s): ces
- model: transformer
- 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 |
|---|---|---|---|---|---|
| newstest2012.rus-ces | 15.4 | 0.427 | 3003 | 65456 | 0.917 |
| newstest2013.rus-ces | 20.9 | 0.476 | 3000 | 57250 | 0.946 |
| Tatoeba-test.rus-ces | 51.8 | 0.683 | 2500 | 14266 | 0.987 |