build(deps-dev): update pyannote-audio requirement from <4,>=3.3.0 to >=3.3.0,<5 - #6

Sourced from pyannote-audio's changelog.

Version 4.0.7 (2026-06-30)

• fix(pipeline): add missing support for subfolder in Pipeline.from_pretrained
• feat(pipeline): add basic support for (sequential) batch inference

Version 4.0.5 (2026-06-22)

• improve(telemetry): reduce number of sent packages @​litdarya
• feat(cli): add --average-case option to optimize command @​antoinelaurent
• fix(task): fix Task.prepare_data to support saving preprocessors that produce int values in metadata @​lylyhan

Version 4.0.4 (2026-02-07)

• feat(sample): add transcription of sample file
• setup: relax torch dependencies constraints
• fix(pipeline): fix HF authentication for Speechbrain speaker embedding @​krisoye

Version 4.0.3 (2025-12-07)

• feat(cli): add --revision option to most CLI commands
• feat(util): add Calibration.safe_transform method (supports NaNs as well as any shape)
• fix(model): fix Model.from_pretrained to support lightning 2.6+
• setup: update pyannote-database dependency to 6.1+

Version 4.0.2 (2025-11-19)

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

Version 4.0.1 (2025-10-10)

• feat: allow passing preloaded pipeline config to get_pipeline
• setup: update pyannoteai-sdk dependency to 0.3.0
• fix: relax version constraint on OpenTelemetry dependencies
• improve: warn (instead of raise) when passing unsupported arguments to speaker diarization pipeline

Version 4.0.0 (2025-09-29)

TL;DR

Improved speaker assignment and counting

pyannote/speaker-diarization-community-1 pretrained pipeline relies on VBx clustering instead of agglomerative hierarchical clustering (as suggested by BUT Speech@FIT researchers Petr Pálka and Jiangyu Han).

Exclusive speaker diarization

... (truncated)

• c3795f2 improve(telemetry): reduce number of sent packages (#2025)
• 365704d feat: add support for opentelemetry (#1896)
• See full diff in compare view

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)