4.0.2

pyannote/pyannote-audio4.0.2Nov 19, 2025by github-actions[bot]

AI Summary

Patch release with bug fixes for torch compatibility, new pipeline convenience methods, and performance improvements.

Key Highlights

BREAKING: Binarize.__call__ now returns string tracks instead of int
Pinned torch/torchcodec/torchaudio versions to avoid segmentation fault
Added Pipeline.cuda() convenience method
Added preload option to Pipeline.__call__
CLI can now apply pipeline on directory of audio files

Breaking Changes

Binarize.__call__ returns string tracks instead of int

New Features

Pipeline.cuda() method for easy GPU migration
preload option to force audio preloading in memory
CLI directory processing for batch audio file processing
Vectorized permutate function for faster performance

Full Release Notes

## What's Changed

- BREAKING(util): make `Binarize.__call__` return `string` tracks (instead of `int`) [@benniekiss](https://github.com/benniekiss/)
- fix(torch): pin `torch`, `torchcodec`, and `torchaudio` versions to [avoid segmentation fault](https://github.com/meta-pytorch/torchcodec/issues/995) 
- fix(pyannoteAI): update pyannoteAI wrapper to return both regular and exclusive diarization
- feat(pipeline): add `Pipeline.cuda()` convenience method [@tkanarsky](https://github.com/tkanarsky/)
- feat(pipeline): add `preload` option to base `Pipeline.__call__` to force preloading audio in memory ([@antoinelaurent](https://github.com/antoinelaurent/))
- feat(cli): add option to apply pipeline on a directory of audio files
- improve(util): make `permutate` faster thanks to vectorized cost function

## New Contributors
* @tkanarsky made their first contribution in https://github.com/pyannote/pyannote-audio/pull/1950

**Full Changelog**: https://github.com/pyannote/pyannote-audio/compare/4.0.1...4.0.2