leo 96f97ed2d0 ✨(summary) improve speaker assignment ...

Speaker-to-participant assignment relie on WhisperX word timings, but
incorrect word durations in the output can lead to inaccurate overlap
scoring and wrong user attribution. Add a custom heuristic to trim
overly long word durations before computing assignments.

2026-05-12 16:58:07 +02:00

..

api

♻️(summary) refactor tasks signature and make transcription tz-aware

2026-05-06 18:33:03 +02:00

assets

🐛(summary) complete webm support

2026-05-11 23:00:54 +02:00

models

🐛(summary) relax whisperX payload format

2026-04-15 10:11:36 +02:00

unit

✨(summary) improve speaker assignment

2026-05-12 16:58:07 +02:00

__init__.py

✅(summary) add minimal test suite for health endpoint

2026-03-18 20:19:52 +01:00

conftest.py

✨(summary) add multi-tenant support and v2 tasks / API

2026-04-01 17:43:43 +02:00