I'm trying to process large video/audio files and extract timestamps and songs played during the video.
For example, processing a large Twitch stream VOD to find out that songs A, B and C were played at time stamps 1:00:23- 1:03:12, 1:34:23-1:38:43, and 2:21:56-2:24:45.
The ideal solution would be a library I could use to run this locally since I don't think any APIs would want to handle large audio files hours long.
I've looked at a few different libraries such as aubio and shazamcli already, but they don't seem to fit what I'm trying to do. I'm not too familiar with the audio processing space overall.