- dataset: opus
- model: transformer
- source language(s): kin
- target language(s): eng
- 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 |
|---|---|---|---|---|---|
| Tatoeba-test.kin-eng | 29.5 | 0.465 | 17 | 113 | 1.000 |
| tico19-test.kin-eng | 8.4 | 0.310 | 2100 | 56347 | 0.990 |