- dataset: opusTCv20210807+pft
- model: transformer-align
- source language(s): ukr
- target language(s): ces slk
- raw source language(s): ukr
- raw target language(s): ces slk
- model: transformer-align
- pre-processing: normalization + SentencePiece (spm32k,spm32k)
- a sentence initial language token is required in the form of
>>id<<(id = valid target language ID) - valid language labels: >>ces<< >>slk<<
- download: opusTCv20210807+pft_transformer-align_2022-03-08.zip
- test set translations: opusTCv20210807+pft_transformer-align_2022-03-08.test.txt
- test set scores: opusTCv20210807+pft_transformer-align_2022-03-08.eval.txt
| testset | BLEU | chr-F | #sent | #words | BP |
|---|---|---|---|---|---|
| Tatoeba-test-v2021-08-07.ukr-ces | 52.6 | 0.69251 | 1787 | 8550 | 0.994 |
- dataset: opusTCv20210807+pft
- model: transformer-align
- source language(s): ukr
- target language(s): ces
- raw source language(s): ukr
- raw target language(s): ces
- model: transformer-align
- pre-processing: normalization + SentencePiece (spm32k,spm32k)
- a sentence initial language token is required in the form of
>>id<<(id = valid target language ID) - valid language labels:
- download: opusTCv20210807+pft_transformer-align_2022-03-17.zip
- test set translations: opusTCv20210807+pft_transformer-align_2022-03-17.test.txt
- test set scores: opusTCv20210807+pft_transformer-align_2022-03-17.eval.txt
| testset | BLEU | chr-F | #sent | #words | BP |
|---|---|---|---|---|---|
| Tatoeba-test-v2021-08-07.ukr-ces | 52.8 | 0.69545 | 1787 | 8549 | 0.995 |
| Tatoeba-test-v2021-08-07.ukr-ces | 54.2 | 0.70661 | 1787 | 8550 | 0.998 |