- dataset: opus+bt
- model: transformer-align
- source language(s): fin
- target language(s): tur
- model: transformer-align
- pre-processing: normalization + SentencePiece (spm32k,spm32k)
- download: opus+bt-2021-03-21.zip
- test set translations: opus+bt-2021-03-21.test.txt
- test set scores: opus+bt-2021-03-21.eval.txt
| testset | BLEU | chr-F | #sent | #words | BP |
|---|---|---|---|---|---|
| Tatoeba-test.fin-tur | 31.2 | 0.613 | 1796 | 10072 | 0.950 |