Fix TorchScript model loading and temp directory creation #772
Conversation
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
- Add support for TorchScript checkpoint format (used by wav2lip_gan.pth) - Change map_location from lambda to string for TorchScript compatibility - Create temp directory before VideoWriter to prevent silent failures - Add weights_only=False parameter for PyTorch security warning - Fix librosa.filters.mel call for newer librosa versions (use sr= keyword) Fixes unpickling errors and silent video generation failures with modern PyTorch and librosa versions.
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Outdated suggestions cannot be applied.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.
Problem
The current inference.py fails with modern PyTorch and the official TorchScript checkpoints:
Solution
This PR adds:
Testing
Tested with:
Before/After
Before: UnpicklingError on model load
After: Successfully generates lip-synced videos