- dataset: opus+bt
- model: transformer-align
- source language(s): eng
- target language(s): kin
- model: transformer-align
- pre-processing: normalization + SentencePiece (spm32k,spm32k)
- download: opus+bt-2021-04-10.zip
- test set translations: opus+bt-2021-04-10.test.txt
- test set scores: opus+bt-2021-04-10.eval.txt
| testset | BLEU | chr-F | #sent | #words | BP |
|---|---|---|---|---|---|
| Tatoeba-test.eng-kin | 11.7 | 0.502 | 17 | 80 | 1.000 |
| tico19-test.eng-kin | 7.0 | 0.330 | 2100 | 55149 | 1.000 |