- dataset: opusTCv20210807
- model: transformer-big
- source language(s): deu
- target language(s): ita
- raw source language(s): deu
- raw target language(s): ita
- 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 |
|---|---|---|---|---|---|
| newssyscomb2009.deu-ita | 27.2 | 0.56821 | 502 | 11551 | 1.000 |
| newstest2009.deu-ita | 25.4 | 0.55065 | 2525 | 63474 | 0.997 |
| Tatoeba-test-v2021-08-07.deu-ita | 49.7 | 0.69847 | 10000 | 74739 | 0.973 |