linuxserver/docker-faster-whisper gpu-v3.3.0-ls48

on GitHub

CI Report:

N/A

LinuxServer Changes:

Full Changelog: gpu-v3.2.0-ls47...gpu-v3.3.0-ls48

Remote Changes:

• Add FunASR speech-to-text backend (--stt-library funasr) defaulting to FunAudioLLM/SenseVoiceSmall (@LauraGPT)
  • Non-autoregressive and notably faster than Whisper; supports English, Chinese, Cantonese, Japanese, and Korean well
  • Install with the funasr extra (pip install '.[funasr]')