-
Notifications
You must be signed in to change notification settings - Fork 147
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Issues with Python Setup #61
Comments
You could make it so that the code takes a config file instead of arguments. If you make this PR it would work and I will merge:
Normally the default mic index works. Otherwise you can print out the mic devices and select the index that makes the most sense. Other backends could be added to support int8 such as transformers or ctranslate2. For this current work fp32 is the default for cpu and fp16 for GPU |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
First off, I want to say thank you for making this. It's been a lifesaver so far.
Second, I'm very new to this kind of project and python in general, so I apologize if this question is obvious or nonsensical. The CLI commands are great, but I'm trying to do the same setup in python (specifying the device, the model, the mic, etc.). I know that the init function sets everything to a default value, but I was wondering if there was a way to set these qualities manually in a separate python file so that any user can download my code and have it work with your whisper_mic.py file out of the box. I also wondered about how to find the mic index that I need and how to set the FP16/FP32/INT8 options. I keep getting a warning that FP16 isn't supported on my cpu, which causes it to default to FP32. I'd like to set it to FP32 from the start. If I have to modify the whisper_mic.py file itself, I understand, but I just wanted to make sure there wasn't any other way.
The text was updated successfully, but these errors were encountered: