audio
audio copied to clipboard
pytorch
Data manipulation and transformation for audio signal processing, powered by PyTorch
### 🐛 Describe the bug Torchaudio ffmpeg cpp extension crashes when used with encoders that do not have threading capabilities e.g. mulaw. Easily reproducable by running the following script: ```...
### 🚀 The feature Trying to use nightly pyTorch builds which use cu128 on Blackwell NVIDIA GPUs. "torchvision 0.22.0.dev20250316+cu128 requires torch==2.8.0.dev20250315+cu128, but you have torch 2.6.0 which is incompatible." ###...
### 🚀 The feature During building do not download sox and use already installed version, just like already is done with ffmpeg. ### Motivation, pitch On systems with functioning package...
# Missing Relative Positional Encoding in Conformer Implementation ## Issue Description The current Conformer implementation in Torchaudio is missing the relative sinusoidal positional encoding scheme that is a key component...
Motivation: we're using a custom pytorch build and have patch release more recently than upstream. While those updates do not change any abi, we want to allow torchaudio/torchvision (https://github.com/pytorch/vision/pull/8936) to...
Summary: X-link: https://github.com/pytorch/text/pull/2285 X-link: https://github.com/pytorch/vision/pull/8919 Remove headers flagged by facebook-unused-include-check over fbcode.pytorch. + format and autodeps This is a codemod. It was automatically generated and will be landed once it...
When the `python -OO` flag is used, doc strings are no longer stored, and __doc__ always returns None. This makes the library fail at import time for a rather dubious...
Enable building torchaudio from source against already existing ffmpeg Fixes [#3789](https://github.com/pytorch/audio/issues/3789)
I attempted to install PyTorch and torchaudio on the Nvidia Jetson AGX Orin 64G. The installation of PyTorch was relatively successful, with version torch-2.0.0a0 installed. However, when I followed your...
