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
- OPUS reading is ~3x slower compared to ffmpeg in a subprocess
- Replace _get_mat_trace when torch.linalg.trace is ready to use.
- Add HiFi-GAN
- Add pretrained weights from Voxpopuli
- Add xfolding to tacotron2 infer pipeline
- Add training recipes for HuBERT model pre-training and ASR fine-tuning
- Make TextProcessor object inherit `torch.nn.Module`.
- Moving WaveRNN padding into the model
- kaldi.fbank alternative in librosa?
- There is a contraction in WaveRNNInferenceWrapper during inference when batched
- Docs
- Python not yet supported