text-generation-webui/extensions/whisper_stt
2023-03-10 11:47:16 +01:00
..
README.md added installation instructions 2023-03-10 11:47:16 +01:00
requirements.txt first implementation 2023-03-09 12:46:50 +01:00
script.py tweaked Whisper parameters 2023-03-09 21:18:46 +01:00

Installation instructions

  • On all platforms, run pip install -r requirements.txt in this folder
  • You need PortAudio to run the speech recognition. Below are guides for all platforms

Windows

  • You don't need to do anything, pyaudio already comes with PortAudio included on Windows.

Mac

brew install portaudio
brew link --overwrite portaudio
pip install pyaudio

Linux

  • You have to use your distro's package manager to install PortAudio.

Ubuntu / Debian / Mint

sudo apt install portaudio19-dev python3-pyaudio

Arch / Manjaro

sudo pacman -S portaudio

Fedora

sudo dnf -y install portaudio