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
- torchaudio.load to optionally accept a target sample_rate (and maybe backend=)
- Add support for spatial feature extraction on multi-microphone data
- Metadata mode for torchaudio.dataset
- Need more detail and tutorial on how to use the language model to decrease the word rate error.
- [v0.12] torchaudio.info reports num_frames=0 for MP3
- Cleanup conda channel flags, make sure we can switch easily between pytorch-nightly, pytorch-test and pytorch
- Define TORCHAUDIO_API for better visbility control
- Initial condition support for torchaudio.functional.lfilter
- Proposal for the integration of Tree-constrained Pointer Generator and Minimum Biasing Word Error (MBWE) training for contextual ASR
- large resampling kernels slow ALSO on the forward pass
- Docs
- Python not yet supported