hugpadhugpad

FermionResearch / Phonon-1

Audio1499Updated Oct 23, 2026
Hugging Face

Downloads

149

Likes

9

Last updated

Oct 23, 2026

License

apache-2.0

Phonon-1 is an open speech recognition model for English. It downloads in 415 MB, runs on a laptop or a datacenter GPU, and transcribes an hour of audio in about two and a half minutes.

Tasks & library

  • automatic speech recognition
  • mlx

Tags

  • mlx
  • apple-silicon
  • speech-to-text
  • asr
  • stt
  • on-device

Technical specifications

ParametersNot available
Librarymlx
Languagesen
Base modelQwen/Qwen3-ASR-0.6B
Licenseapache-2.0