Open MyraBaba opened 1 year ago
same problem
You might get this error if you haven't accepted the user agreements, as mentioned in the writeup =>
To enable Speaker Diarization, include your Hugging Face access token (read) that you can generate from Here after the --hf_token argument and accept the user agreement for the following models: Segmentation and Speaker-Diarization-3.1 (if you choose to use Speaker-Diarization 2.x, follow requirements here instead.)
Traceback (most recent call last): File "test.py", line 31, in
diarize_model = whisperx.DiarizationPipeline(use_auth_token="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", device=device)
File "/home/sabuhigurbani/.local/lib/python3.8/site-packages/whisperx/diarize.py", line 16, in init
self.model = Pipeline.from_pretrained(model_name, use_auth_token=use_auth_token).to(device)
File "/home/sabuhigurbani/.local/lib/python3.8/site-packages/pyannote/pipeline/pipeline.py", line 100, in getattr
raise AttributeError(msg)
AttributeError: 'SpeakerDiarization' object has no attribute 'to'
Just executed example on: https://github.com/m-bain/whisperX#python-usage--