OPUS-MT-train/work-spm/en-ceb/README.md
2020-01-10 16:45:42 +02:00

16 lines
639 B
Markdown

# opus-2020-01-08.zip
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download: [opus-2020-01-08.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-ceb/opus-2020-01-08.zip)
* test set translations: [opus-2020-01-08.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-ceb/opus-2020-01-08.test.txt)
* test set scores: [opus-2020-01-08.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-ceb/opus-2020-01-08.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| JW300.en.ceb | 51.3 | 0.704 |
| Tatoeba.en.ceb | 31.3 | 0.600 |