Fix Windows GPU diarization for YouDub

[Zhuyuanbin]

No description provided.

[gemini-code-assist]

Code Review

This pull request introduces several changes to optimize imports and audio loading. It defers the imports of umap and hdbscan to runtime, replaces torchaudio.load with soundfile.read for audio loading, and adds support for a local ModelScope cache directory. Feedback on the changes points out that removing the top-level import of Inference and Model from pyannote.audio will cause a NameError in other parts of the code where they are still used. It is recommended to use a try...except block at the top level to handle these optional imports safely.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

[gemini-code-assist]

Removing the top-level import of Inference and Model will cause a NameError in do_segmentation (line 225) because Inference is used there but is no longer in the global scope. To avoid import errors on systems where pyannote.audio is not installed while keeping the imports available globally, you can use a try...except ImportError block at the top level.

Suggested change

	parser = argparse.ArgumentParser(description='Speaker diarization inference.')
	try:
	from pyannote.audio import Inference, Model
	except ImportError:
	Inference = None
	Model = None
	parser = argparse.ArgumentParser(description='Speaker diarization inference.')

[gemini-code-assist]

With Inference and Model imported at the top level using a try...except block, this local import is no longer necessary and can be removed.

    segmentation_params = {