It's getting more and more difficult to tune and evaluate diarization pipelines with different models or combinations of models, even with a GPU.
Idea
Implement a caching mechanism to save segmentation and embedding outputs to disk. For example, we could use ~/.diart/cache by default, and even allow users to change it with --cache.
This could be implemented as an additional parameter of SpeakerDiarization:
Where cache: str | Path | None. Using cache=None would prevent caching, cache="default" would use ~/.diart/cache and cache=Path(/some/dir) or cache="/some/dir" would dump/load the cache to/from that directory.
The caching logic could even be implemented as a wrapper of SegmentationModel and EmbeddingModel.
Problem
It's getting more and more difficult to tune and evaluate diarization pipelines with different models or combinations of models, even with a GPU.
Idea
Implement a caching mechanism to save segmentation and embedding outputs to disk. For example, we could use
~/.diart/cacheby default, and even allow users to change it with--cache. This could be implemented as an additional parameter ofSpeakerDiarization:Where
cache: str | Path | None. Usingcache=Nonewould prevent caching,cache="default"would use~/.diart/cacheandcache=Path(/some/dir)orcache="/some/dir"would dump/load the cache to/from that directory.The caching logic could even be implemented as a wrapper of
SegmentationModelandEmbeddingModel.