sanyam5/audio

simple audio I/O for pytorch

Load Audio files directly into PyTorch Tensors

Audio library for PyTorch

• Support audio I/O (Load files)

Load the following formats into a torch Tensor

• mp3, wav, aac, ogg, flac, avr, cdda, cvs/vms,
• aiff, au, amr, mp2, mp4, ac3, avi, wmv,
• mpeg, ircam and any other format supported by libsox.

Dependencies

• libsox v14.3.2 or above

Quick install on OSX (Homebrew):

brew install sox

Linux (Ubuntu):

sudo apt-get install sox libsox-dev libsox-fmt-all

Installation

python setup.py install

Quick Usage

import torchaudio
sound, sample_rate = torchaudio.load('foo.mp3')

API Reference

torchaudio.load

loads an audio file into a Tensor
audio.load(
	string,  # path to file
	out=None, # optionally pass output Tensor (any CPU Tensor type)
)