No Language Left Behind by Meta

An open-source language translation system for 200 languages

106 followers

FAIR (Facebook AI Research) built and open-sourced a state-of-the-art AI model that now translates between 200 different languages. The code and models are made available today as part of the Fairseq package.
No Language Left Behind by Meta gallery image
Free
Launch Team
Universal-3 Pro by AssemblyAI
Universal-3 Pro by AssemblyAI
The first promptable speech model for production
Promoted

What do you think? …

Sarah Wright
The No Language Left Behind project is an open-source language translation system from FAIR (Facebook AI Research) capable of translating 200 languages between each other. It made up of 50 billion parameters. The code and models were made available today as part of the Fairseq package. One of the most interesting things about this "universal speech translator" is its attempt to expand language translation to less-covered languages. That's important to Meta's vision for the metaverse and the augmented reality glasses it's working on, as well as its core products (the modeling techniques from this work have already been applied to improve translations on Facebook and Instagram (and Wikipedia too).