This is a Visual Studio Code Dev Container for the openai's Whisper Speech Recognition Model for ease of use and devlopment.
The main file is taken from the example on Whisper's repo and sample audio is taken from online using ffmpeg
ffmpeg converting video to audio script ->
ffmpeg -i https://test.com/test.m3u8 -map 0:0 -vn -b:a 320k audio.mp3