Helsinki-NLP/opus-mt-en-dra

The language is Dravidian languages . The language's initial language token is required in the form of >>id<< (id = valid target language ID) The language token should be used to indicate a valid language ID . The original weights: opus-2020-07-26.zip and set translations: Opus 2020-07/26.test.eval.txt. The language tokens: English, Dravidian languages, Arabic, French, Spanish, English, Arabic and Arabic . The model is based on the Tatoeba-Challenge language language challenge . For example, the language challenge was created by Helsinki-based NLP-NLP-LNLP .,