- dataset: opus
- model: transformer
- source language(s): pob por
- target language(s): eng
- model: transformer
- pre-processing: normalization + SentencePiece (spm32k,spm32k)
- download: opus-2021-02-23.zip
- test set translations: opus-2021-02-23.test.txt
- test set scores: opus-2021-02-23.eval.txt
| testset | BLEU | chr-F | #sent | #words | BP |
|---|---|---|---|---|---|
| Tatoeba-test.por-eng | 62.7 | 0.761 | 10000 | 75240 | 0.974 |
| tico19-test.pob-eng | 49.1 | 0.741 | 2100 | 56339 | 1.000 |
| tico19-test.por-eng | 49.1 | 0.741 | 2100 | 56339 | 1.000 |
- dataset: opus+bt
- model: transformer-align
- source language(s): pob por
- target language(s): eng
- model: transformer-align
- pre-processing: normalization + SentencePiece (spm32k,spm32k)
- download: opus+bt-2021-04-30.zip
- test set translations: opus+bt-2021-04-30.test.txt
- test set scores: opus+bt-2021-04-30.eval.txt
| testset | BLEU | chr-F | #sent | #words | BP |
|---|---|---|---|---|---|
| Tatoeba-test.por-eng | 62.6 | 0.761 | 10000 | 75240 | 0.973 |
| tico19-test.pob-eng | 49.6 | 0.742 | 2100 | 56339 | 1.000 |
| tico19-test.por-eng | 49.6 | 0.742 | 2100 | 56339 | 1.000 |