Open biagioscalingipsy opened 1 month ago
They seem to be downloaded once and stay put, so work offline. Download it once via the simple whisperx --diarize ...
, as per the instructions here, then check where they are (Linux: find ~/.cache -type f -size +1M -mmin -60
), usually they land here:
ls ~/.cache/torch/pyannote/
models--pyannote--segmentation-3.0 models--pyannote--speaker-diarization-3.1 models--pyannote--wespeaker-voxceleb-resnet34-LM
and that is it, the Huggingface (HF) token not needed anymore (as all offline by then).
Hello! I would like to use WhisperX and Pyannote to combine automatic transcription and diarization. I can do it on Colab using the Huggingface (HF) token, but I would like to avoid entering the HF token every time. So I was thinking of downloading them locally and loading them when needed. I can do this for WhisperX but not for Pyannote. Therefore, I can do the automatic transcription but cannot proceed with the annotation. I followed these tutorials on how to use Pyannote and the offline pipelines and downloaded everything, but it still doesn't work. Can you help me?
I download pytorch_model.bin and configuration.yaml for voice_activity_detection, then yaml files for segmentation and speaker_diarization and put them in working directory. Then I used this code: