Translation models made in Helsinki are now integrated in Hugging Face transformers

Hugging Face is taking its first steps into machine translation thanks to researchers in Helsinki, who now provide 1008 machine translation models covering 140 different languages. Hugging Face is a company  aiming to democratize natural language processing.

“We have taken the initiative to broadly share data and pre-trained models that can be used world-wide for research and development of high-quality NLP tools. Our goal is to improve the language coverage of current translation systems that still primarily look at English and a handful of high-resource languages,” explains Professor of Language Technology Jörg Tiedemann.

It is now possible to quickly deploy translation engines and to re-use technology for further development and optimization of language interfaces for an increasing number of the world’s languages.

Translation and language-based interactive AI can enable interpersonal communication between people who speak different languages and empower people around the world to participate in online and in-person commerce.

“The collaborations with Hugging Face and also the Wikimedia Foundation demonstrate the immense interest in our initiative and we are proud to be part of the general movement towards open science, resources and re-usable components in the field of NLP,” says Tiedemann.

Check out how it works and find your language here.
The actual OPUS-MT github here.