No description
  • Python 99%
  • Makefile 0.8%
  • Inno Setup 0.2%
Find a file
2022-09-26 20:13:40 +01:00
.vscode Switch to sounddevice 2022-09-26 20:13:40 +01:00
.gitignore Add transcriber and Makefile 2022-09-24 19:08:06 +01:00
Buzz.spec Switch to sounddevice 2022-09-26 20:13:40 +01:00
gui.py Switch to sounddevice 2022-09-26 20:13:40 +01:00
LICENSE Create LICENSE 2022-09-26 00:49:28 +01:00
main.py Switch to sounddevice 2022-09-26 20:13:40 +01:00
Makefile Switch to sounddevice 2022-09-26 20:13:40 +01:00
README.md Set up language and model selection 2022-09-26 15:04:09 +01:00
requirements.txt Switch to sounddevice 2022-09-26 20:13:40 +01:00
transcriber.py Switch to sounddevice 2022-09-26 20:13:40 +01:00

Buzz

Buzz transcribes audio from your computer's microphones to text using OpenAI's Whisper. Buzz works by splitting audio recordings into chunks and transcribing the chunks to text using Whisper.

Requirements

To set up Buzz, first install ffmpeg (needed to run Whisper).

# on Ubuntu or Debian
sudo apt update && sudo apt install ffmpeg

# on MacOS using Homebrew (https://brew.sh/)
brew install ffmpeg

# on Windows using Chocolatey (https://chocolatey.org/)
choco install ffmpeg

# on Windows using Scoop (https://scoop.sh/)
scoop install ffmpeg

Build

To build Buzz, run:

pip install -r requirements.txt
make buzz