Skip to content
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

Diarize: Everything assigned to Speaker 01 #592

Open
mwallinger-tu opened this issue Nov 21, 2023 · 5 comments
Open

Diarize: Everything assigned to Speaker 01 #592

mwallinger-tu opened this issue Nov 21, 2023 · 5 comments

Comments

@mwallinger-tu
Copy link

I am currently transcribing and diarizing a set of 1-on-1 interviews. In the diarized transcripts everything is assigned to Speaker_01.

whisperx p3_audio.aac --model large-v2 --diarize --min_speakers 2 --max_speakers 2 --batch_size 4 --hf_token TOKEN --language en

@vladgrand2
Copy link

I also noticed that in pyannote.diarazation 3.1 all speakers go to one person. So edit diarize.py and set model_name="pyannote/speaker-diarization-3.0" instead of model_name="pyannote/speaker-diarization-3.1"

@mwallinger-tu
Copy link
Author

Thanks. That resolved the issues

@rrfaria
Copy link

rrfaria commented Dec 3, 2023

Perhaps it is related to it
image

@omarsiddiqi224
Copy link

I am also running into that error. Unfortunately changing the model_name="pyannote/speaker-diarization-3.1" to model_name="pyannote/speaker-diarization-3.0" in diarize.py did not help. do you know how I can solve this?

@santialferez
Copy link
Contributor

Hi, I think you also need to update to pyannote v3.1.1 to fix the problem

santialferez added a commit to santialferez/whisperX that referenced this issue Dec 26, 2023
ben256 pushed a commit to kaiconversations/whisperX that referenced this issue Jun 5, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants