- dataset: opus1m+bt
- model: transformer-align
- source language(s): aln sqi
- target language(s): eng
- model: transformer-align
- pre-processing: normalization + SentencePiece (spm12k,spm12k)
- download: opus1m+bt-2021-05-01.zip
- test set translations: opus1m+bt-2021-05-01.test.txt
- test set scores: opus1m+bt-2021-05-01.eval.txt
| testset | BLEU | chr-F | #sent | #words | BP |
|---|---|---|---|---|---|
| Tatoeba-test.aln-eng | 14.6 | 0.396 | 27 | 137 | 1.000 |
| Tatoeba-test.sqi-eng | 53.6 | 0.697 | 1065 | 7760 | 0.950 |
| Tatoeba-test.sqi-eng | 53.8 | 0.698 | 1065 | 7762 | 0.950 |