audio
audio copied to clipboard
pytorch
Data manipulation and transformation for audio signal processing, powered by PyTorch
### 🐛 Describe the bug I discovered a memory leak in one of my datasets that I tracked down to resampling audio of varying length. The following code is a...
### 🐛 Describe the bug Calling `torchaudio.load` with a file-like object as argument to load FLAC-encoded files sometimes returns incomplete tensors. It seems to happen with non-trivial tensors after a...
## 🚀 Feature torchaudio should work on Android and iOS platforms ## Motivation Mobile apps need a fast way to preprocess audio (i.e. generate spectrograms). ## Pitch I would love...
### 🚀 The feature I would like to have or add (by myself, maybe?) pre-emphasis filtering into the audio processing step. ### Motivation, pitch As we all know, pre-emphasis boosts...
This commit replaces `torch.hub.load_state_dict_from_url` with `torchaudio.utils.download_asset`. The motivation of this change is that `download_asset` provides more consistent behavior of caching and local file path management. This change is, strictly speaking,...
Python 3.7 introduced postponed evaluation of annotation. https://docs.python.org/3/whatsnew/3.7.html Enabling this allows the code to use the exported name in annotation. As a result we can directly annotate functions with exported...
1. Get rid of custom download function (use `torch.hub.download_url_to_file`) 2. Remove `lang` from test function argument
* Not for merge. * No need to review. * Reference point for my WIP Kaldi feature transforms.
Adds first version of iOS build script that includes only csrc files with no third party dependencies. Sample run command: ``` LIBTORCH_HEADER_ROOT="/path/LibTorch-Lite/install/include" IOS_ARCH="x86_64" ./build_ios.sh ```