Omnilingual ASR
Speech recognition for 1,600+ languages — most for the first time
Latest: Omnilingual ASR (Nov 10, 2025)
A FAIR-built suite of open-source speech-recognition models released November 10, 2025 that transcribes more than 1,600 languages — including ~500 low-resource languages never before supported by any ASR system — and extends zero-shot to 5,400+ languages from just a few paired examples. Released under Apache 2.0 in sizes from 300M to 7B parameters.
Why it matters
Expanded open speech recognition from MMS's 1,107 languages to more than 1,600, about 500 of them never transcribed by any ASR system, with zero-shot extension to 5,400+ from a few examples. Apache 2.0 weights from 300M to 7B and a pip package make it the most language-inclusive ASR anyone can deploy.
Facts
- Covers nearly every spoken language with a known script — 1,600+ natively, 5,400+ via zero-shot in-context learning.
- Scales self-supervised speech pre-training to 7B parameters with an LLM-inspired decoder.
- A new language can be added with only a handful of paired audio-text examples, no retraining.
- Trained on 4.3 million hours of audio; achieves character error rate below 10% for 78% of supported languages.
- Effectively covers nearly every spoken language with a known script — and communities can add a new language with just a few examples.
Try it yourself
Explore languages (Meta demo) ↗ pip install omnilingual-asr ↗ Model on Hugging Face (7B LLM-ASR) ↗
Lineage
Sources
arXiv ↗GitHub · omnilingual-asr ↗Meta AI research ↗