- dataset: opusTCv20210807
- model: transformer-big
- source language(s): ita
- target language(s): bel bel_Latn orv_Cyrl rus ukr
- raw source language(s): ita
- raw target language(s): bel orv rus ukr
- model: transformer-big
- 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_transformer-big_2022-03-13.zip
- test set translations: opusTCv20210807_transformer-big_2022-03-13.test.txt
- test set scores: opusTCv20210807_transformer-big_2022-03-13.eval.txt
| testset | BLEU | chr-F | #sent | #words | BP |
|---|---|---|---|---|---|
| Tatoeba-test-v2021-08-07.ita-bel | 32.5 | 0.52986 | 264 | 1513 | 1.000 |
| Tatoeba-test-v2021-08-07.ita-bel_Latn | 5.7 | 0.476 | 1 | 8 | 0.867 |
| Tatoeba-test-v2021-08-07.ita-multi | 45.9 | 0.65738 | 10000 | 60666 | 0.988 |
| Tatoeba-test-v2021-08-07.ita-orv | 1.7 | 0.14338 | 8 | 41 | 1.000 |
| Tatoeba-test-v2021-08-07.ita-rus | 44.8 | 0.64943 | 10045 | 65765 | 0.992 |
| Tatoeba-test-v2021-08-07.ita-ukr | 46.5 | 0.66326 | 5000 | 25294 | 1.000 |
- dataset: opusTCv20210807
- model: transformer-big
- source language(s): ita
- target language(s): bel bel_Latn orv_Cyrl rus ukr
- raw source language(s): ita
- raw target language(s): bel orv rus ukr
- model: transformer-big
- 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_transformer-big_2022-03-19.zip
- test set translations: opusTCv20210807_transformer-big_2022-03-19.test.txt
- test set scores: opusTCv20210807_transformer-big_2022-03-19.eval.txt
| testset | BLEU | chr-F | #sent | #words | BP |
|---|---|---|---|---|---|
| Tatoeba-test-v2021-08-07.ita-bel | 33.3 | 0.55214 | 264 | 1513 | 1.000 |
| Tatoeba-test-v2021-08-07.ita-bel_Latn | 5.7 | 0.460 | 1 | 8 | 0.867 |
| Tatoeba-test-v2021-08-07.ita-multi | 46.5 | 0.66062 | 10000 | 60666 | 0.987 |
| Tatoeba-test-v2021-08-07.ita-orv | 2.1 | 0.14404 | 8 | 41 | 1.000 |
| Tatoeba-test-v2021-08-07.ita-rus | 46.2 | 0.65834 | 10045 | 65765 | 0.987 |
| Tatoeba-test-v2021-08-07.ita-ukr | 48.1 | 0.67290 | 5000 | 25294 | 0.997 |
- dataset: opusTCv20210807
- model: transformer-big
- source language(s): ita
- target language(s): bel bel_Latn orv_Cyrl rus ukr
- raw source language(s): ita
- raw target language(s): bel orv rus ukr
- model: transformer-big
- 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_transformer-big_2022-03-23.zip
- test set translations: opusTCv20210807_transformer-big_2022-03-23.test.txt
- test set scores: opusTCv20210807_transformer-big_2022-03-23.eval.txt
| testset | BLEU | chr-F | #sent | #words | BP |
|---|---|---|---|---|---|
| Tatoeba-test-v2021-08-07.ita-bel | 33.3 | 0.55571 | 264 | 1513 | 0.993 |
| Tatoeba-test-v2021-08-07.ita-bel_Latn | 5.9 | 0.493 | 1 | 8 | 0.549 |
| Tatoeba-test-v2021-08-07.ita-multi | 46.6 | 0.66149 | 10000 | 60666 | 0.985 |
| Tatoeba-test-v2021-08-07.ita-orv | 2.1 | 0.14466 | 8 | 41 | 1.000 |
| Tatoeba-test-v2021-08-07.ita-rus | 46.2 | 0.65840 | 10045 | 65765 | 0.985 |
| Tatoeba-test-v2021-08-07.ita-ukr | 48.3 | 0.67483 | 5000 | 25294 | 0.995 |