# opus-2019-12-04.zip

* dataset: opus
* model: transformer
* pre-processing: normalization + tokenization + BPE
* download: [opus-2019-12-04.zip](https://object.pouta.csc.fi/OPUS-MT-models/et+fi-en/opus-2019-12-04.zip)
* test set translations: [opus-2019-12-04.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/et+fi-en/opus-2019-12-04.test.txt)
* test set scores: [opus-2019-12-04.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/et+fi-en/opus-2019-12-04.eval.txt)

## Benchmarks

| testset               | BLEU  | chr-F |
|-----------------------|-------|-------|
| newsdev2015-enfi.fi.en 	| 22.4 	| 0.510 |
| newsdev2018-enet.et.en 	| 25.6 	| 0.536 |
| newstest2015-enfi.fi.en 	| 23.1 	| 0.517 |
| newstest2016-enfi.fi.en 	| 25.9 	| 0.543 |
| newstest2017-enfi.fi.en 	| 28.5 	| 0.564 |
| newstest2018-enet.et.en 	| 26.3 	| 0.543 |
| newstest2018-enfi.fi.en 	| 21.1 	| 0.488 |
| newstest2019-fien.fi.en 	| 25.3 	| 0.541 |
| newstestB2016-enfi.fi.en 	| 21.3 	| 0.503 |
| newstestB2017-enfi.fi.en 	| 24.3 	| 0.531 |
| newstestB2017-fien.fi.en 	| 24.3 	| 0.531 |
| Tatoeba.et.en 	| 42.1 	| 0.637 |