Repo contains code to tokenize audio files into multiple useful chunks based on pauses and save the details to a csv file for furthur analysis.
Code usage:
python3 audio_tokenizer_auditok.py -url "https://www.youtube.com/watch?v=2vTZ_0dpG-0"
python3 audio_tokenizer_webrtc.py -url "https://www.youtube.com/watch?v=2vTZ_0dpG-0"
OR
python3 audio_tokenizer_auditok.py -filepath "/home/aswin/Downloads/audio1.wav"
python3 audio_tokenizer_webrtc.py -filepath "/home/aswin/Downloads/audio1.wav"