Working with the Source Code

Prerequisites for running the Code

1. Turn on stereo mix settings on windows if you want to fetch the PCs audio
2. Install and add ffmpeg to your PATH
3. Install CUDA to your system
4. Install Python (Version 3.10) to your system
5. Install Git to your system
6. Git clone or download this repository
7. pip install -r requirements.txt -U (or install.bat)

_All examples in the documentation work. Only difference is running them using "python audioWhisper.py" instead of "audioWhisper\audioWhisper.exe".