audio file to text conversion using whisper,resemblyzer,scikit-learn,numpy,ffmpeg,torch and tkinter.

for downloading models for whisper go to https://github.com/openai/whisper

requires python 3.11 or higher

requires resemblyzer,scikit-learn,numpy,torch,tkinter,ffmpeg,ffprobe

this script uses openai whisper models

for supported languages check at https://github.com/openai/whisper

cuda may not supported on macos or nvidia gpu lacked pcs or other devices