audio icon indicating copy to clipboard operation
audio copied to clipboard

Data manipulation and transformation for audio signal processing, powered by PyTorch

Results 324 audio issues
Sort by recently updated
recently updated
newest added

### 🚀 The feature A pytorch differentiable `sosfilt()` implementation like in [https://docs.scipy.org/doc/scipy/reference/generated/scipy.signal.sosfilt.html](https://docs.scipy.org/doc/scipy/reference/generated/scipy.signal.sosfilt.html), will allow for filtering data along one dimension using cascaded second-order sections. This should allow for a better...

### 🐛 Describe the bug By [documentation ](https://pytorch.org/audio/stable/generated/torchaudio.load.html) of `torchaudio.load()`, the expected behaviour for handling 24-bit WAV files is the following: > Since torch does not support int24 dtype, 24-bit...

### 🐛 Describe the bug It's not building with last version of cuda 12.6.1 in jetson agx orin ```bash #!/usr/bin/env bash set -ex echo "Building torchaudio ${TORCHAUDIO_VERSION}" apt-get update apt-get...

Differential Revision: D64008689

fb-exported
CLA Signed

Typo in the word "installation"

CLA Signed

### 🚀 The feature Support users to obtain the encoding and decoding capabilities of non-GPU devices (may be a out-of-tree device of torch) by using the familiar APIs of torchaudio/torio.io....

This PR fixes small typo in the warning logs for pytorch/audio

CLA Signed

### 🚀 The feature There is an example for hubert training [here](https://github.com/pytorch/audio/tree/main/examples/self_supervised_learning), but has no example about real-time av-asr for other languages. ### Motivation, pitch I'm woking on lipreading without...

PLEASE NOTE THAT THE TORCHAUDIO REPOSITORY IS NO LONGER ACTIVELY MONITORED. You may not get a response. For open discussions, visit https://discuss.pytorch.org/.

CLA Signed

Depends on https://github.com/pytorch/test-infra/pull/5728 Works for https://github.com/pytorch/pytorch/issues/114850

CLA Signed