# opusTCv20210807+pft_transformer-align_2022-03-08.zip

* dataset: opusTCv20210807+pft
* model: transformer-align
* source language(s): ukr
* target language(s): mol ron
* raw source language(s): ukr
* raw target language(s): mol ron
* model: transformer-align
* 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+pft_transformer-align_2022-03-08.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/ukr-ron/opusTCv20210807+pft_transformer-align_2022-03-08.zip)
* test set translations: [opusTCv20210807+pft_transformer-align_2022-03-08.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ukr-ron/opusTCv20210807+pft_transformer-align_2022-03-08.test.txt)
* test set scores: [opusTCv20210807+pft_transformer-align_2022-03-08.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ukr-ron/opusTCv20210807+pft_transformer-align_2022-03-08.eval.txt)

## Benchmarks

| testset | BLEU  | chr-F | #sent | #words | BP |
|---------|-------|-------|-------|--------|----|
| Tatoeba-test-v2021-08-07.ukr-multi 	| 89.4 	| 0.85575 	| 2 	| 13 	| 1.000 |