- dataset: opus
- model: transformer-align
- source language(s): bel bel_Latn
- target language(s): pol
- model: transformer-align
- pre-processing: normalization + SentencePiece (spm1k,spm1k)
- download: opus-2020-09-10.zip
- test set translations: opus-2020-09-10.test.txt
- test set scores: opus-2020-09-10.eval.txt
| testset | BLEU | chr-F |
|---|---|---|
| Tatoeba-test.bel.pol | 0.8 | 0.081 |