Download old pre-trained models from torch.hub?

[picheny-nyu]

I was resurrecting some old code for a student project to illustrate diarization performance. I no longer seem to be able to download the diehard models using torch.hub.load. Is this correct, and I have to upgrade to the newest pyannote version? I saw another post with the same problem (no resolution).

Thanks
Michael Picheny

[github-actions]

Thank you for your issue.
We found the following entry in the FAQ which you may find helpful:

• Can I use gated models (and pipelines) offline?

Feel free to close this issue if you found an answer in the FAQ.

If your issue is a feature request, please read this first and update your request accordingly, if needed.

If your issue is a bug report, please provide a minimum reproducible example as a link to a self-contained Google Colab notebook containing everthing needed to reproduce the bug:

• installation
• data preparation
• model download
• etc.

Providing an MRE will increase your chance of getting an answer from the community (either maintainers or other power users).

Companies relying on pyannote.audio in production may contact me via email regarding:

• paid scientific consulting around speaker diarization and speech processing in general;
• custom models and tailored features (via the local tech transfer office).

This is an automated reply, generated by FAQtory

[hbredin]

The old torch.hub thing is no longer supported since pyannote 2.x (we are now at pyannote 3.x).
You should revert to pyannote 1.x but I would not recommend that as the performance of those old models is way behind what pyannote/speaker-diarization-3.0 can do.

[stale]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

[eyaler]

solution:

!pip install pyannote.core==4.1 pyannote.pipeline==1.5.2 pyannote.audio==1.1.1
!wget -nc https://raw.githubusercontent.com/pyannote/pyannote-audio/1.1.1/hubconf.py -P /root/.cache/torch/hub/pyannote_pyannote-audio_main
import torch
import pyannote.core #https://github.com/pyannote/pyannote-audio/issues/561
pipeline = torch.hub.load('pyannote/pyannote-audio', 'dia', trust_repo=True)