- dataset: opus4m+btTCv20210807
- model: transformer
- source language(s): dan swe
- target language(s): fin
- raw source language(s): dan swe
- raw target language(s): fin
- model: transformer
- pre-processing: normalization + SentencePiece (spm32k,spm32k)
- download: opus4m+btTCv20210807-2022-01-19.zip
- test set translations: opus4m+btTCv20210807-2022-01-19.test.txt
- test set scores: opus4m+btTCv20210807-2022-01-19.eval.txt
| testset | BLEU | chr-F | #sent | #words | BP |
|---|---|---|---|---|---|
| Tatoeba-test-v2021-08-07.dan-fin | 37.8 | 0.624 | 2665 | 14297 | 0.940 |
| Tatoeba-test-v2021-08-07.isl-fin | 9.5 | 0.075 | 2 | 8 | 1.000 |
| Tatoeba-test-v2021-08-07.multi-fin | 38.0 | 0.623 | 2665 | 14305 | 0.936 |
| Tatoeba-test-v2021-08-07.nor-fin | 22.0 | 0.460 | 2488 | 13054 | 0.933 |
| Tatoeba-test-v2021-08-07.swe-fin | 43.2 | 0.664 | 2841 | 15615 | 0.960 |