Back to all models
translation mask_token:
Query this model
🔥 This model is currently loaded and running on the Inference API. ⚠️ This model could not be loaded by the inference API. ⚠️ This model can be loaded on the Inference API on-demand.
JSON Output
API endpoint  

⚡️ Upgrade your account to access the Inference API

Share Copied link to clipboard

Monthly model downloads

Helsinki-NLP/opus-mt-en-bnt Helsinki-NLP/opus-mt-en-bnt
N/a downloads
last 30 days

pytorch

tf

Contributed by

Language Technology Research Group at the University of Helsinki university
1 team member · 1325 models

How to use this model directly from the 🤗/transformers library:

			
Copy to clipboard
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-en-bnt") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-en-bnt")
Uploaded in S3

eng-bnt

  • source group: English

  • target group: Bantu languages

  • OPUS readme: eng-bnt

  • model: transformer

  • source language(s): eng

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

  • 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-2020-07-26.zip

  • test set translations: opus-2020-07-26.test.txt

  • test set scores: opus-2020-07-26.eval.txt

Benchmarks

testset BLEU chr-F
Tatoeba-test.eng-kin.eng.kin 12.5 0.519
Tatoeba-test.eng-lin.eng.lin 1.1 0.277
Tatoeba-test.eng-lug.eng.lug 4.8 0.415
Tatoeba-test.eng.multi 12.1 0.449
Tatoeba-test.eng-nya.eng.nya 22.1 0.616
Tatoeba-test.eng-run.eng.run 13.2 0.492
Tatoeba-test.eng-sna.eng.sna 32.1 0.669
Tatoeba-test.eng-swa.eng.swa 1.7 0.180
Tatoeba-test.eng-toi.eng.toi 10.7 0.266
Tatoeba-test.eng-tso.eng.tso 26.9 0.631
Tatoeba-test.eng-umb.eng.umb 5.2 0.295
Tatoeba-test.eng-xho.eng.xho 22.6 0.615
Tatoeba-test.eng-zul.eng.zul 41.1 0.769

System Info: