- dataset: opus
- model: transformer-align
- source language(s): apc ara arq arz
- target language(s): epo
- model: transformer-align
- pre-processing: normalization + SentencePiece (spm4k,spm4k)
- 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.apc-epo | 0.0 | 0.113 | 2 | 9 | 0.449 |
| Tatoeba-test.ara-epo | 18.9 | 0.376 | 723 | 4506 | 0.948 |
| Tatoeba-test.arq-epo | 6.7 | 0.191 | 4 | 22 | 0.953 |
| Tatoeba-test.arz-epo | 13.4 | 0.230 | 2 | 10 | 0.651 |