metadata
license: cc-by-nc-sa-4.0
language:
- tr
- en
pipeline_tag: translation
Opus Tatoeba | Turkish -> English
- dataset: opus
- model: transformer
- source language(s): tur
- target language(s): eng
- model: transformer
- pre-processing: normalization + SentencePiece (spm32k,spm32k)
- download: opus-2021-02-18.zip
- test set translations: opus-2021-02-18.test.txt
- test set scores: opus-2021-02-18.eval.txt
Benchmarks
| testset | BLEU | chr-F | #sent | #words | BP |
|---|---|---|---|---|---|
| newsdev2016-entr.tur-eng | 27.9 | 0.546 | 1001 | 22011 | 0.927 |
| newstest2016-entr.tur-eng | 24.2 | 0.526 | 3000 | 66175 | 0.942 |
| newstest2017-entr.tur-eng | 24.9 | 0.533 | 3007 | 67703 | 0.943 |
| newstest2018-entr.tur-eng | 27.0 | 0.548 | 3000 | 68725 | 0.957 |
| Tatoeba-test.tur-eng | 58.4 | 0.725 | 10000 | 77701 | 0.966 |