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

opus-mt-en_el_es_fi-en_el_es_fi

Benchmarks

testset BLEU chr-F
newsdev2015-enfi.en.fi 16.0 0.498
newssyscomb2009.en.es 29.9 0.570
newssyscomb2009.es.en 29.7 0.569
news-test2008.en.es 27.3 0.549
news-test2008.es.en 27.3 0.548
newstest2009.en.es 28.4 0.564
newstest2009.es.en 28.4 0.564
newstest2010.en.es 34.0 0.599
newstest2010.es.en 34.0 0.599
newstest2011.en.es 35.1 0.600
newstest2012.en.es 35.4 0.602
newstest2013.en.es 31.9 0.576
newstest2015-enfi.en.fi 17.8 0.509
newstest2016-enfi.en.fi 19.0 0.521
newstest2017-enfi.en.fi 21.2 0.539
newstest2018-enfi.en.fi 13.9 0.478
newstest2019-enfi.en.fi 18.8 0.503
newstestB2016-enfi.en.fi 14.9 0.491
newstestB2017-enfi.en.fi 16.9 0.503
simplification.en.en 63.0 0.798
Tatoeba.en.fi 56.7 0.719