zls-zls

  • source group: South Slavic languages

  • target group: South Slavic languages

  • OPUS readme: zls-zls

  • model: transformer

  • source language(s): bul mkd srp_Cyrl

  • target language(s): bul mkd srp_Cyrl

  • model: transformer

  • pre-processing: normalization + SentencePiece (spm32k,spm32k)

  • a sentence initial language token is required in the form of >>id<< (id = valid target language ID)

  • download original weights: opus-2020-07-27.zip

  • test set translations: opus-2020-07-27.test.txt

  • test set scores: opus-2020-07-27.eval.txt

Benchmarks

testset BLEU chr-F
Tatoeba-test.bul-hbs.bul.hbs 19.3 0.514
Tatoeba-test.bul-mkd.bul.mkd 31.9 0.669
Tatoeba-test.hbs-bul.hbs.bul 18.0 0.636
Tatoeba-test.hbs-mkd.hbs.mkd 19.4 0.322
Tatoeba-test.mkd-bul.mkd.bul 44.6 0.679
Tatoeba-test.mkd-hbs.mkd.hbs 5.5 0.152
Tatoeba-test.multi.multi 26.5 0.563

System Info:

Downloads last month
15
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Spaces using Helsinki-NLP/opus-mt-zls-zls 7