whisperX · Issues· 223 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #1283
How to speed up diarization speed for WhisperX?
Updated Sep 12, 2026 - #1468
FFmpeg and PyTorch problem after second run
Updated Aug 27, 2026 - #297
Silence with background noise causing transcript to misalign
bugUpdated Aug 26, 2026 - #1467
Feature Request: Add NVIDIA NeMo Sortformer as an Optional Speaker Diarization Backend
Updated Aug 25, 2026 - #1382
error message whisperx python
Updated Aug 24, 2026 - #1374
When whisperx can suport torch==2.9.1
Updated Aug 17, 2026 - #1449
Fix for #1220 (PR #1367) was reintroduced by #1386 — wildcard alignment code is back in v3.8.3+
Updated Aug 15, 2026 - #298
A "phantom language" can ruin the whole transcription
bugUpdated Aug 11, 2026 - #1440
Potential optimisation: temp-file mode for load_audio() to reduce memory on long audio
enhancementhelp wantedUpdated Aug 7, 2026 - #1247
Word-level timestamps from WhisperX are inaccurate compared to Montreal Forced Aligner (MFA)
Updated Aug 3, 2026 - #1461
uv pip install whisperx error
Updated Jul 30, 2026 - #1456
`SubtitlesWriter` long-term vision?
Updated Jul 28, 2026 - #1457
`hf_token` can only be passed as a CLI argument
Updated Jul 28, 2026 - #1310
Why WhisperX's sentence segmentation not working for Chinese?
Updated Jul 18, 2026 - #1451
Aligner gives inaccurate timestamps for a 25s audio segment (chunk from a larger clip)
Updated Jul 13, 2026