fix: bypass whisperx with faster-whisper direct for CUDA 13 / RTX 500…#11
Open
vashdao wants to merge 1 commit into
Open
fix: bypass whisperx with faster-whisper direct for CUDA 13 / RTX 500…#11vashdao wants to merge 1 commit into
vashdao wants to merge 1 commit into
Conversation
…0 series compatibility
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Fix: Bypass whisperX with faster-whisper for CUDA 13 / RTX 5000 series compatibility
whisperX has irreconcilable dependency conflicts with newer pyannote.audio, speechbrain, and torchaudio on Windows with CUDA 13 (RTX 4090/5090). This fix bypasses whisperX entirely and uses faster-whisper directly, which supports word-level timestamps natively. Tested and working on RTX 5090 with CUDA 13.