metaai·lightalo unofficial · independent
Universe / Speech & Sound / No Language Left Behind
Speech & Sound · 2022

No Language Left Behind

No Language Left Behind (NLLB-200)

200 languages, one model, published in Nature

open source 600M / 1.3B / 3.3B dense; 54.5B MoE params

Latest: NLLB-200 54.5B MoE (Jul 2022); published in Nature Jun 2024

A single translation model covering 200 languages (202 language–script variants) — including 150+ low-resource ones like Asturian and Luganda — released July 6, 2022 with the FLORES-200 benchmark and training data. It averaged a 44% BLEU improvement over prior state of the art and later powered Wikipedia's Content Translation tool. Peer-reviewed in Nature (2024).

Why it matters

Proved a single model could translate 200 languages, including 150+ low-resource ones, with a 44% average BLEU gain over the prior state of the art. Its FLORES-200 benchmark became the standard multilingual test set, NLLB powers Wikipedia's Content Translation tool, and the work was peer-reviewed in Nature in 2024.

Facts

Try it yourself

Lineage

Led toSeamlessM4T & the Seamless familyLanguage Technology Partner Program + BOUQuET

See the whole family tree →

Sources

More in Speech & Sound

Universal Speech TranslatorMassively Multilingual SpeechAudioCraftVoiceboxAudioboxwav2vec 2.0

Read the Speech & Sound story on the sky →

✦ Open on the map Explore Speech & Sound Quiz me