Helsinki-NLP/opus-mt-no-no

A sentence initial language token is required in the form of >>id<< (id = valid target language ID) The original weights: opus-2020-06-17.zip/opus-2019/2026/OpUS readme: nor-nor-or-opus-2020/1926/OPUS . The language tokens are required to indicate a valid language ID and a sentence is required to be normalized . The model is called Tatoeba-Challenge . The full version of this article is available to download and test runs: Opus 2020/06/1925/Opus2020/0626/opus2020/26/1919 . The Norwegian,