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
- Distributed dataparallel implementation of WaveRNN training
- Add support for bitrate in sox_io backend
- Support WaveRNN inference with different sampling mode
- Refactor pipeline_tacotron2 and remove `unwrap_distributed`
- Refactor the TTS pipeline example
- Refactor text_preprocessor into a class in Tacotron2 example
- Add Multi-channel Support and Beamforming Modules to Torchaudio
- Move the WaveRNN inference wrapper to infer method
- Some tests are not skipped properly
- Confusing IID behavior in masking transforms.
- Docs
- Python not yet supported