• Meta has unveiled its new open source automatic speech recognition (ASR) system, capable of transcribing more than 1,600 languages, a significant expansion compared to OpenAI’s Whisper model, which only supports 99 languages.
  • This move marks Meta’s return to the open source AI community, potentially reshaping accessibility in multilingual communication.
  • The introduction of this comprehensive ASR model could enhance global communication tools and foster inclusivity in technology.

[via]