OPUS-MT-train/work-spm/mg-en/README.md

16 lines
641 B
Markdown
Raw Normal View History

2020-01-10 17:45:42 +03:00
# opus-2020-01-09.zip
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download: [opus-2020-01-09.zip](https://object.pouta.csc.fi/OPUS-MT-models/mg-en/opus-2020-01-09.zip)
* test set translations: [opus-2020-01-09.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/mg-en/opus-2020-01-09.test.txt)
* test set scores: [opus-2020-01-09.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/mg-en/opus-2020-01-09.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| GlobalVoices.mg.en | 27.6 | 0.522 |
| Tatoeba.mg.en | 50.2 | 0.607 |