- dataset: opus
- model: transformer-align
- source language(s): pob por
- target language(s): deu
- model: transformer-align
- pre-processing: normalization + SentencePiece (spm32k,spm32k)
- download: opus-2021-05-16.zip
- test set translations: opus-2021-05-16.test.txt
- test set scores: opus-2021-05-16.eval.txt
| testset | BLEU | chr-F | #sent | #words | BP |
|---|---|---|---|---|---|
| Tatoeba-test.por-deu | 48.5 | 0.675 | 10000 | 81246 | 0.997 |
- dataset: opusTCv20210807
- model: transformer-big
- source language(s): pob por
- target language(s): deu
- raw source language(s): pob por
- raw target language(s): deu
- model: transformer-big
- pre-processing: normalization + SentencePiece (spm32k,spm32k)
- download: opusTCv20210807_transformer-big_2022-07-22.zip
- test set translations: opusTCv20210807_transformer-big_2022-07-22.test.txt
- test set scores: opusTCv20210807_transformer-big_2022-07-22.eval.txt
| testset | BLEU | chr-F | #sent | #words | BP |
|---|---|---|---|---|---|
| Tatoeba-test-v2021-08-07.multi-deu | 51.6 | 0.69663 | 10000 | 81246 | 0.996 |