New Project: EasyNMT (github.com/UKPLab/EasyNMT)
Easy-to-use, state-of-the-art Neural Machine Translation using @huggingface and @fairseq.
- Translation for 150+ languages
- Sentence & document translation
- Automatic Language Detection
Colab example: colab.research.google.com/drive/1X47vgSi…
Easy-to-use, state-of-the-art Neural Machine Translation using @huggingface and @fairseq.
- Translation for 150+ languages
- Sentence & document translation
- Automatic Language Detection
Colab example: colab.research.google.com/drive/1X47vgSi…
Currently 4 state-of-the-art models are supported:
- OPUS-MT models from @HelsinkiNLP (individual models for 150+languages)
- mBART50 many-to-many translation for 50 langs from @facebookai
- m2m_100 many-to-many translation for 100 langs from @facebookai (418M and 1.2B version)
- OPUS-MT models from @HelsinkiNLP (individual models for 150+languages)
- mBART50 many-to-many translation for 50 langs from @facebookai
- m2m_100 many-to-many translation for 100 langs from @facebookai (418M and 1.2B version)
Document translation: Transformer-based models have a length limit of 512 / 1024 word pieces.
EasyNMT is able to translate documents of any lengths by splitting it into smaller chunks, translating these, and then reconstructing the full document.
EasyNMT is able to translate documents of any lengths by splitting it into smaller chunks, translating these, and then reconstructing the full document.
Automatic language detection: Only specific the target language. The source language is detected automatically thanks to fastText model (170+ languages).
• • •
Missing some Tweet in this thread? You can try to
force a refresh
