Helsinki-NLP/opus-mt-sv-ZH

A sentence initial language token is required in the form of >>id (id) (id = valid target language ID) The dataset is based on languages: cmn,cn,yue,ze_zh,zh_cn,zh . The dataset has original weights: opus-2020-01-16.zip and original translations: Opus-202001/16.eval.test.txt. The dataset was created from a database of languages called the OPUS. The OPUS readme has been updated to reflect current language standards and language diversity. The language tokens are required to be used in the context of a sentence. The system is designed to be able to use,