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-zls-zls Helsinki-NLP/opus-mt-zls-zls
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-zls-zls") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-zls-zls")
Uploaded in S3

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: