Helsinki-NLP/opus-mt-es-ar

A sentence initial language token is required in the form of >>id<< (id = valid target language ID) The language is Spanish, Arabic, and the language is Arabic . The model is called "Spa-ara" and the model is based on the language language of the language used in the language of a sentence . The language's original weights: opus-2020-07-03.zip and set translations: Opus 2020-07/03.test.eval.txt. The model was created from the Tatoeba-Challenge language challenge . The full version of this article is available in the OLSN-NLP toolbook, "Opus2020-,