ainewsblitz.com

Breaking

Meta Open-Sources Omnilingual ASR, a Speech Recognition System Spanning More Than 1,600 Languages

Meta Open-Sources Omnilingual ASR, a Speech Recognition System Spanning More Than 1,600 Languages
  • Open Source
  • Foundation Models
  • Research & Papers

Meta's Fundamental AI Research (FAIR) team has released Omnilingual ASR, an open-source speech recognition system that transcribes audio in more than 1,600 languages—roughly 500 of which had never before been supported by an automatic speech recognition model. Announced on November 10, 2025, the release is aimed squarely at the long tail of the world's languages that mainstream transcription tools have historically ignored.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year