- dataset: opus
- model: transformer-align
- source language(s): ell
- 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 |
|---|---|---|---|---|---|
| Tatoeba-test.ell-rus | 54.7 | 0.722 | 2500 | 14600 | 0.992 |