Const-me / Whisper

High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model
Mozilla Public License 2.0
7.67k stars 665 forks source link

Thank you and question about output files #129

Open robinkoehler opened 1 year ago

robinkoehler commented 1 year ago

Thank you so much for making this tool available! It is an incredible time saver over the native whisper command line, and so much faster too.

I was wondering if I can coerce this into providing multiple text file output formats at the same time? My workflow often requires the .txt, the .srt and the .vtt. Would it be possible to have a multi pick field for the output format?

Secondly, is there a way to drop in multiple files at once for batch processing?

I appreciate your time and thank you in advance for a reply!