github m-bain/whisperX v3.5.1

latest releases: v3.3.5, v3.4.4
6 hours ago

Backport of word-level timestamp fixes from v3.8.2.

Bug Fixes

  • Restore original CTC forced-alignment (f2609a6): PR #986 caused all words to anchor to the start of the segment window (silence) instead of actual speech. Reverts get_trellis/backtrack to the original PyTorch tutorial implementation. Fixes #1220.
  • Fix blank_id hardcoded to 0 (636f298): Broke alignment for HuggingFace models where blank is [pad], not index 0.

Full Changelog: v3.5.0...v3.5.1

Don't miss a new whisperX release

NewReleases is sending notifications on new releases.