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
I performed hyper-parameter optimization for the pre-trained speaker diarization pipeline on my own dataset
as per the instruction provided in the tutorial.
But how can we apply the optimized Speaker Dairization pipeline with locally-trained or fine-tuned components (mentioned above) to an audio file of our choice? (especially in python-script, instead of shell-based commands)
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I performed hyper-parameter optimization for the pre-trained speaker diarization pipeline on my own dataset
as per the instruction provided in the tutorial.
https://github.com/pyannote/pyannote-audio/tree/master/tutorials/pipelines/speaker_diarization
Also, I have some fine-tuned or locally-trained components such as SAD, SCD etc.
For pre-trained speaker diarization pipeline, applying on an audio file of our choice is really simple with the following instructions:
import torch
pipeline = torch.hub.load('pyannote/pyannote-audio', 'dia')
test_file = {'uri': 'filename', 'audio': '/path/to/your/filename.wav'}
diarization = pipeline(test_file)
But how can we apply the optimized Speaker Dairization pipeline with locally-trained or fine-tuned components (mentioned above) to an audio file of our choice? (especially in python-script, instead of shell-based commands)
Beta Was this translation helpful? Give feedback.
All reactions