eng hin source group: English target group: Hindi OPUS readme: eng hin model: transformer align source language(s): eng target language(s): hin model: transformer align pre processing: normalization + SentencePiece (spm32k,spm32k) download original weights: opus 2020 06 17.zip test set translations: opus 2020 06 17.test.txt test set scores: opus 2020 06 17.eval.txt Benchmarks testset BLEU chr F newsdev2014.eng.hin 6.9 0.296 newstest2014 hien.eng.hin 9.9 0.323 Tatoeba test.eng.hin 16.1 0.447 System Info: hf name: eng hin source languages: eng target languages: hin opus readme url: https://github.com/Helsinki NLP/Tatoeba Challenge/tree/master/models/eng hin/README.md original repo: Tatoeba Challenge tags: ['translation'] languages: ['en', 'hi'] src constituents: {'eng'} tgt constituents: {'hin'} src multilingual: False tgt multilingual: False prepro: normalization + SentencePiece (spm32k,spm32k) url model: https://object.pouta.csc.fi/Tatoeba MT models/eng hin/opus 2020 06 17.zip url test set: https://object.pouta.csc.fi/Tatoeba MT models/eng hin/opus 2020 06 17.test.txt src alpha3: eng tgt alpha3: hin short pair: en hi chrF2 score: 0.447 bleu: 16.1 brevity penalty: 1.0 ref len: 32904…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy