audio
https://github.com/pytorch/audio
Python
Data manipulation and transformation for audio signal processing, powered by PyTorch
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported2 Subscribers
Add a CodeTriage badge to audio
Help out
- Issues
- rnnt_loss: per-sequence logits offset is computed in int and overflows for large-vocabulary batches
- torchaudio.save silently saturates PCM-scale int16 input after the TorchCodec migration
- forced_align (CPU) segfaults when frames * (2*targets+1) exceeds 2^31: 32-bit loop index overflow
- Fix 32-bit index overflow and error-path leak in forced_align (CPU)
- Conformer output depends on padding, silently hurting accuracy at inference (convolution module ignores lengths)
- Fix #4205 (Fix padding leakage in Conformer convolution module)
- Python 3.14 support
- Fix #2867
- Fix #3059
- Fix CUCTC top-k shared memory offset
- Docs
- Python not yet supported