You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Great work on the implementation! Just wondering if you have considered the integration of other whisper models into the pipeline, such as faster-whisper (https://github.com/SYSTRAN/faster-whisper?tab=readme-ov-file) which may be faster than the original models?
Also, on another note, if I would like to add that functionality, which file should I look at to understand how to do the integration?
The text was updated successfully, but these errors were encountered:
Currently I have looked into other whisper models to use, though I have not invested time into implementing such thing. I would love to do that, but currently I am investing time into making a server control panel for remote machines for like runpod and other VPS type hosts.
I'm also in the process of making the project more modular by taking taking stuff from the transcribe_audio.py file and making them independently into a module setting like in modules folder. Everything is sort of a spaghetti code right now.
So if you want to implement Faster Whisper, Currently the files to look at are:
Great work on the implementation! Just wondering if you have considered the integration of other whisper models into the pipeline, such as faster-whisper (https://github.com/SYSTRAN/faster-whisper?tab=readme-ov-file) which may be faster than the original models?
Also, on another note, if I would like to add that functionality, which file should I look at to understand how to do the integration?
The text was updated successfully, but these errors were encountered: