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
- Fix transforms.Fade silently promoting float16/bfloat16 waveforms to float32
- Compute _get_strided strides after padding so non-contiguous input works (closes #3856)
- Enable Windows ARM64 native wheel builds
- forced_align returns a sub-optimal path when two predecessor states tie
- Return a most-likely path from forced_align when predecessors tie
- transforms.MFCC: top_db clamp reduces over the time axis and cannot be disabled
- [Codemod][FbcodePyreModeHeaderRemoval] [batch:20/N] [shard:11/N] Remove Pyre mode headers
- Raise in vad on non-finite input instead of reporting silence (closes #4216)
- transforms.Vad silently returns an empty tensor when the waveform contains one non-finite sample
- rnnt_loss: per-sequence logits offset is computed in int and overflows for large-vocabulary batches
- Docs
- Python not yet supported