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
- Correct mistake in trellis evaluation in accordance with the CTC paper
- ffmpeg libraries now must be installed, breaking on users machines
- Fix ITokenizer return type annotation
- fix bug: matrix multiplication errors caused by discontinuous memory
- Packaging Regression in v2.9.0: torchaudio.load fails on non-shared Python builds
- Add skip condition to vggish_pipeline_test test
- Compile with CUDA 13.0 e Nvidia 5090 SM_120
- Do not assume batch_size=1 in `_Wav2Vec2Model`'s forward
- Add installation script for windows arm64 dependencies
- Compile CUDA 13 on Nvidia 5090 sm_120
- Docs
- Python not yet supported