search

Const-me / Whisper

High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model
Mozilla Public License 2.0
7.65k stars 664 forks source link

I want to process multiple files with WhisperDesktop #174

Closed kbuwel closed 9 months ago

kbuwel commented 9 months ago

There are numerous audio files in the folder. It takes a long time and it is difficult to convert the entire file. It would be nice to have the ability to specify a folder within WhisperDesktop and then select all files in that folder for processing. It would be nice if the corresponding folder and recognized files were recorded in the recognition results. For example, it would be good to write it like this: a a.wav hi

RickArcher108 commented 9 months ago

Use Whisperer. Works like a charm:

Download from:

https://github.com/tigros/Whisperer/releases/download/2.8/Whisperer.zip then you would download ggml-large.binhttps://huggingface.co/ggerganov/whisper.cpp/blob/main/ggml-large.bin from https://huggingface.co/ggerganov/whisper.cpp/tree/main

Rick Archer Buddha at the Gas Pump https://batgap.com @.***

From: kbuwel @.> Sent: Monday, September 18, 2023 12:00 PM To: Const-me/Whisper @.> Cc: Subscribed @.***> Subject: [Const-me/Whisper] I want to process multiple files with WhisperDesktop (Issue #174)

There are numerous audio files in the folder. It takes a long time and it is difficult to convert the entire file. It would be nice to have the ability to specify a folder within WhisperDesktop and then select all files in that folder for processing. It would be nice if the corresponding folder and recognized files were recorded in the recognition results. For example, it would be good to write it like this: a a.wav hi

— Reply to this email directly, view it on GitHubhttps://github.com/Const-me/Whisper/issues/174, or unsubscribehttps://github.com/notifications/unsubscribe-auth/A7JTFIL5GT34RCRKAEQF2LTX3B42TANCNFSM6AAAAAA45A2PIE. You are receiving this because you are subscribed to this thread.Message ID: @.**@.>>

NikosDi commented 9 months ago

It's better not to give the link of specific releases like the one above. You linked v2.8 which is the previous one than the current.

The current release is here: https://github.com/tigros/Whisperer/releases