- dataset: opusTCv20210807
- model: transformer-align
- source language(s): deu
- target language(s): tur
- raw source language(s): deu
- raw target language(s): tur
- model: transformer-align
- pre-processing: normalization + SentencePiece (spm32k,spm32k)
- download: opusTCv20210807-2021-10-22.zip
- test set translations: opusTCv20210807-2021-10-22.test.txt
- test set scores: opusTCv20210807-2021-10-22.eval.txt
testset | BLEU | chr-F | #sent | #words | BP |
---|---|---|---|---|---|
Tatoeba-test-v2021-08-07.deu-tur | 35.6 | 0.644 | 5000 | 29200 | 0.948 |