Use whisper for detecting human voice and record voice in file

[nicolasboulet]

Hello,

I would like to know if it is possible to use whisper.cpp to detect sentences spoken by a human voice and then record them into audio files, one detected sentence per file. The goal is to be able to detect the sentences locally and then perform the speech-to-text conversion on a more powerful instance by sending the audio files in order to achieve a better result with a larger model.