mirror of
https://github.com/Helsinki-NLP/OPUS-MT-train.git
synced 2024-09-11 20:27:19 +03:00
.. | ||
README.md |
opus+bt-2020-04-17.zip
- dataset: opus+bt
- model: transformer
- pre-processing: normalization + SentencePiece
- a sentence initial language token is required in the form of
>>id<<
(id = valid target language ID) - download: opus+bt-2020-04-17.zip
- test set translations: opus+bt-2020-04-17.test.txt
- test set scores: opus+bt-2020-04-17.eval.txt
Benchmarks
testset | BLEU | chr-F |
---|---|---|
Tatoeba.en.la | 49.9 | 0.691 |
opus-2020-04-21.zip
- dataset: opus
- model: transformer
- pre-processing: normalization + SentencePiece
- a sentence initial language token is required in the form of
>>id<<
(id = valid target language ID) - download: opus-2020-04-21.zip
- test set translations: opus-2020-04-21.test.txt
- test set scores: opus-2020-04-21.eval.txt
Benchmarks
testset | BLEU | chr-F |
---|---|---|
Tatoeba.en.la | 50.1 | 0.693 |