Edit model card

bnt-eng

  • source group: Bantu languages

  • target group: English

  • OPUS readme: bnt-eng

  • model: transformer

  • source language(s): kin lin lug nya run sna swh toi_Latn tso umb xho zul

  • target language(s): eng

  • model: transformer

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

  • download original weights: opus2m-2020-07-31.zip

  • test set translations: opus2m-2020-07-31.test.txt

  • test set scores: opus2m-2020-07-31.eval.txt

Benchmarks

testset BLEU chr-F
Tatoeba-test.kin-eng.kin.eng 31.7 0.481
Tatoeba-test.lin-eng.lin.eng 8.3 0.271
Tatoeba-test.lug-eng.lug.eng 5.3 0.128
Tatoeba-test.multi.eng 23.1 0.394
Tatoeba-test.nya-eng.nya.eng 38.3 0.527
Tatoeba-test.run-eng.run.eng 26.6 0.431
Tatoeba-test.sna-eng.sna.eng 27.5 0.440
Tatoeba-test.swa-eng.swa.eng 4.6 0.195
Tatoeba-test.toi-eng.toi.eng 16.2 0.342
Tatoeba-test.tso-eng.tso.eng 100.0 1.000
Tatoeba-test.umb-eng.umb.eng 8.4 0.231
Tatoeba-test.xho-eng.xho.eng 37.2 0.554
Tatoeba-test.zul-eng.zul.eng 40.9 0.576

System Info:

Downloads last month
17
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-bnt-en 7