Meta Open-Sources Omnilingual ASR Supporting 1,600+ Languages
tom_doerr · x · 2026-08-02
Meta (facebookresearch) has open-sourced Omnilingual ASR, a speech recognition system capable of transcribing audio in over 1,600 languages.
The project has already garnered 2.9k stars on GitHub. Alongside the full source code, the repository includes detailed per-language evaluation results for its 7B model, providing a robust open-source tool for the recognition and preservation of global low-resource languages.
More from Models
- Tencent Releases UI-Mate-27B, a Desktop GUI Agent Model — tencent · 2026-08-24
- Sakana AI translation outperforms Google and DeepL in Japanese-English benchmarks — SakanaAILabs · 2026-08-24
- Developer haider makes his own LLM tier list after disagreeing with theo's rankings — haider1 · 2026-08-24
- Mystery OxAlpha Beats Claude; Alibaba Raises $10B for AI — 创业邦 · 2026-08-24
- OpenAI and Google cut LLM prices; mystery OxAlpha model beats Claude on DeepSWE — 创业邦 · 2026-08-24
- AI News Digest: DeepSeek Weekend Discounts, GPT-5.6 Sol Price Cut, Alibaba's $10B AI Raise — APPSO · 2026-08-24