audio
audio copied to clipboard
pytorch
Data manipulation and transformation for audio signal processing, powered by PyTorch
### 🐛 Describe the bug The example code from [`torchaudio.models.wav2vec2.utils.import_fairseq_model`](https://pytorch.org/audio/stable/generated/torchaudio.models.wav2vec2.utils.import_fairseq_model.html) fails due to a shape mismatch between the extracted features and the reference features from the original Fairseq model. Specifically,...
### 🐛 Describe the bug https://github.com/pytorch/audio/blob/ea5de17755d657508c84c4dce8970b614008adcf/examples/tutorials/tacotron2_pipeline_tutorial.py#L164-L173 This code make error. It's occured on dp package. so I don't know exactly which should be made a issue. But anyway this documentaion...
### 🐛 Describe the bug It seems ` torch.ops.torchaudio.forced_align` function does not support `cuda:n` when n>0, if I set device='cuda:0', it works well, but if I set device='cuda:1', I got...
Dear TorchAudio users, TorchAudio is the most popular audio library for PyTorch. It has critical transforms, models and datasets that we know the community relies on. That is why we...
Add encoding="utf-8" to work with all the languages
### 🐛 Describe the bug Occasionally, a core dump error may occur with a specific audio file as input, which a Python exception cannot capture. This error is rare, but...
I'm trying to work with frequencies below 20hz, preferably at 18,98hz but as the documentation says it only supports above 4000, 8000, and 9000. Even though is there a way...
### 🐛 Describe the bug `torchaudio` not detecting `ffmpeg` installed from the `conda-forge` channel. **Environment:** To reproduce, set up the following environment: ```bash conda create -n test_env python=3.10.6 ffmpeg=6.1.2 -c...
### 🐛 Describe the bug Using hardware accelerated video encoding(NVENC) will result in low quality, blocky video. Setting ffmpeg encoder option to 'slow' or 'lossless' does not help Here is...
### 🚀 The feature FFmpeg makes it easy to write raw audio data without any headers. For example for opus encoding, it looks something like this: ``` input_stream = ffmpeg.input(...
