search

sandrohanea / whisper.net

Whisper.net. Speech to text made simple using Whisper Models
MIT License
512 stars 78 forks source link

Faster transcription #89

Closed yakovw closed 10 months ago

yakovw commented 1 year ago

I tried using WithThreads I have a very powerful processor But it didn't help anything, although it took more power from the processor, but it took the same amount of time, which means I just lost Is there something I'm doing wrong? I tried too WithSpeedUp2x And then it just doesn't transcribe anything! Thanks for this wonderful library and for your help

sandrohanea commented 10 months ago

For faster transcription, you can use different runtime versions (e.g. Whisper.net.Runtime.Cublas for nvidia GPU)

Not all the computations are offloaded to GPU even if Cublas is used: see more info in https://github.com/ggerganov/whisper.cpp/tree/master

This library is a wrapper around whisper.cpp, so it cannot run faster than that.

If you have some option where https://github.com/ggerganov/whisper.cpp/tree/master is running considerably faster than whisper.net => it might be an issue in this wrapper (e.g. in parsing the wave file). but nothing like that was reported yet.