Edit model card

pqe-eng

  • source group: Eastern Malayo-Polynesian languages

  • target group: English

  • OPUS readme: pqe-eng

  • model: transformer

  • source language(s): fij gil haw mah mri nau niu rap smo tah ton tvl

  • target language(s): eng

  • model: transformer

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

  • download original weights: opus-2020-06-28.zip

  • test set translations: opus-2020-06-28.test.txt

  • test set scores: opus-2020-06-28.eval.txt

Benchmarks

testset BLEU chr-F
Tatoeba-test.fij-eng.fij.eng 26.9 0.361
Tatoeba-test.gil-eng.gil.eng 49.0 0.618
Tatoeba-test.haw-eng.haw.eng 1.6 0.126
Tatoeba-test.mah-eng.mah.eng 13.7 0.257
Tatoeba-test.mri-eng.mri.eng 7.4 0.250
Tatoeba-test.multi.eng 12.6 0.268
Tatoeba-test.nau-eng.nau.eng 2.3 0.125
Tatoeba-test.niu-eng.niu.eng 34.4 0.471
Tatoeba-test.rap-eng.rap.eng 10.3 0.215
Tatoeba-test.smo-eng.smo.eng 28.5 0.413
Tatoeba-test.tah-eng.tah.eng 12.1 0.199
Tatoeba-test.ton-eng.ton.eng 41.8 0.517
Tatoeba-test.tvl-eng.tvl.eng 42.9 0.540

System Info:

Downloads last month
30
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-pqe-en 6