- dataset: opus+bt
- model: transformer-align
- source language(s): eng
- target language(s): hun
- model: transformer-align
- pre-processing: normalization + SentencePiece (spm32k,spm32k)
- download: opus+bt-2021-04-13.zip
- test set translations: opus+bt-2021-04-13.test.txt
- test set scores: opus+bt-2021-04-13.eval.txt
testset | BLEU | chr-F | #sent | #words | BP |
---|---|---|---|---|---|
newssyscomb2009.eng-hun | 19.0 | 0.512 | 502 | 9733 | 1.000 |
newstest2009.eng-hun | 19.3 | 0.506 | 2525 | 54965 | 1.000 |
Tatoeba-test.eng-hun | 40.5 | 0.631 | 10000 | 58902 | 0.966 |
- dataset: opusTCv20210807+bt
- model: transformer-big
- source language(s): eng
- target language(s): hun
- raw source language(s): eng
- raw target language(s): hun
- model: transformer-big
- pre-processing: normalization + SentencePiece (spm32k,spm32k)
- download: opusTCv20210807+bt_transformer-big_2022-02-25.zip
- test set translations: opusTCv20210807+bt_transformer-big_2022-02-25.test.txt
- test set scores: opusTCv20210807+bt_transformer-big_2022-02-25.eval.txt
testset | BLEU | chr-F | #sent | #words | BP |
---|---|---|---|---|---|
newssyscomb2009.eng-hun | 20.7 | 0.51929 | 502 | 9733 | 1.000 |
newstest2009.eng-hun | 20.3 | 0.50987 | 2525 | 54965 | 1.000 |
Tatoeba-test-v2021-08-07.eng-hun | 39.1 | 0.62329 | 10000 | 61061 | 0.994 |