Way to Offline Speaker Diarization with Hugging Face

1.5k views Asked by At

I am looking for Offline / locally saved model for speaker diarization with Hugging face without Authentication.
I have gone through google and found no relevant links for the same.
Is there any link/method to do the same?

Thanks in advance

1

There are 1 answers

0
Amir Pourmand On

If you're interested in using pyannote for speaker diarization offline, the maintainer provides a helpful tutorial on how to achieve this. You can find it in the FAQ section.

The key idea is to download the model from Hugging Face and then use the local path to the model instead of the Hugging Face URL. This approach allows you to work offline with the models. Additionally, there are two Jupyter notebooks available to guide you through offline usage:

Here are also two Jupyter notebooks guiding you through offline usage: