Audio Augmentations
Audio augmentations library for PyTorch for audio in the time-domain, with support for stochastic data augmentations as used often in self-supervised / contrastive learning.
Usage
We can define several audio augmentations, which will be applied sequentially to a raw audio waveform:
from audio_augmentations import *
audio, sr = torchaudio.load("tests/classical.00002.wav")
num_samples = sr * 5
transforms = [
RandomResizedCrop(n_samples=num_samples),
RandomApply([PolarityInversion()], p=0.8),
RandomApply([Noise(min_snr=0.3, max_snr=0.5)], p=0.3),
RandomApply([Gain()], p=0.2),
RandomApply([HighLowPass(sample_rate=sr)], p=0.8),
RandomApply([Delay(sample_rate=sr)], p=0.5),
RandomApply([PitchShift(
n_samples=num_samples,
sample_rate=sr
)], p=0.4),
RandomApply([Reverb(sample_rate=sr)], p=0.3)
]
We can return either one or many versions of the same audio example:
transform = Compose(transforms=transforms)
transformed_audio = transform(audio)
>> transformed_audio.shape[0] = 1
> transformed_audio.shape[0] = 4
">
audio = torchaudio.load("testing/classical.00002.wav")
transform = ComposeMany(transforms=transforms, num_augmented_samples=4)
transformed_audio = transform(audio)
>> transformed_audio.shape[0] = 4
Similar to the torchvision.datasets interface, an instance of the Compose or ComposeMany class can be supplied to a torchaudio dataloaders that accept transform=.
Optional
Install WavAugment for reverberation / pitch shifting:
pip install git+https://github.com/facebookresearch/WavAugment
Cite
You can cite this work with the following BibTeX:
@misc{spijkervet_torchaudio_augmentations,
doi = {10.5281/ZENODO.4748582},
url = {https://zenodo.org/record/4748582},
author = {Spijkervet, Janne},
title = {Spijkervet/torchaudio-augmentations},
publisher = {Zenodo},
year = {2021},
copyright = {MIT License}
}
2.6k Dec 30, 2022
27 Jan 01, 2023
1 Jan 10, 2022
20.8k Jan 03, 2023
1k Dec 26, 2022
3 May 01, 2022
124 Dec 22, 2022
2 Jan 20, 2022
8 Nov 25, 2022
2 Nov 23, 2021
197 Dec 31, 2022
50 Nov 21, 2022
232 Jan 03, 2023
12 Oct 22, 2022
13 Oct 03, 2022
1 Feb 13, 2022
56 Nov 22, 2022
8 Jun 19, 2022
13 Oct 21, 2022
2 Feb 04, 2022