/OpenAiWhisper-audio-segmenting

open ai whisper speech to text + audio input file segmenting. This program processes an mp3 file into 4 smaller chunks while reducing the bitrate to 64kbps. Then it processes all the chunks using OpenAi Whisper to turn the speech into a single text file. Starting file size can't be too large though or it will use too much RAM for a standard repl.

Primary LanguagePython

This repository is not active