Skip to content

chore: prepare 0.1.2 release#8

Merged
loookashow merged 1 commit into
mainfrom
fix/speaker-count-clustering
May 6, 2026
Merged

chore: prepare 0.1.2 release#8
loookashow merged 1 commit into
mainfrom
fix/speaker-count-clustering

Conversation

@loookashow
Copy link
Copy Markdown
Contributor

Summary

Prepare 0.1.2 with the latest diarization quality improvements and updated benchmark documentation.

Changes

  • Improve automatic speaker-count selection with silhouette refinement plus a small larger-k prior.
  • Keep the previous temporal speaker-label smoothing improvements documented in the pipeline docs.
  • Add scripts/benchmark_rttm.py for reproducible audio+RTTM benchmark runs across VoxConverse, AMI, and similar datasets.
  • Update package version metadata to 0.1.2 and sync runtime diarize.__version__.
  • Update README/docs with current VoxConverse numbers and preliminary AMI validation.
  • Document known limitations around speaker-count errors and speaker label fragmentation.

Validation

  • python -m ruff check .
  • python -m ruff format --check .
  • python -m pytest tests/test_diarize.py -q
  • python -m mkdocs build --strict --site-dir /private/tmp/diarize-site

@codecov-commenter
Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

@loookashow loookashow merged commit 4f25d27 into main May 6, 2026
9 checks passed
@loookashow loookashow deleted the fix/speaker-count-clustering branch May 6, 2026 09:50
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants