A Pytorch library for audio data augmentation. Inspired by audiomentations. Useful for deep learning.
Project description
Audio data augmentation in PyTorch. Inspired by audiomentations.
- Supports CPU and GPU - speed is a priority
- Supports batches of multichannel (or mono) audio
- Transforms extend
nn.Module
, so they can be integrated as a part of a pytorch neural network model - Most transforms are differentiable
- Three modes:
per_batch
,per_example
andper_channel
- Cross-platform compatibility
- Permissive MIT license
- Aiming for high test coverage
Setup
pip install torch-audiomentations
Usage example
import torch
from torch_audiomentations import Compose, Gain, PolarityInversion
# Initialize augmentation callable
apply_augmentation = Compose(
transforms=[
Gain(
min_gain_in_db=-15.0,
max_gain_in_db=5.0,
p=0.5,
),
PolarityInversion(p=0.5)
]
)
torch_device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
# Make an example tensor with white noise.
# This tensor represents 8 audio snippets with 2 channels (stereo) and 2 s of 16 kHz audio.
audio_samples = torch.rand(size=(8, 2, 32000), dtype=torch.float32, device=torch_device) - 0.5
# Apply augmentation. This varies the gain and polarity of (some of)
# the audio snippets in the batch independently.
perturbed_audio_samples = apply_augmentation(audio_samples, sample_rate=16000)
Contribute
Contributors welcome!
Join the Asteroid's slack
to start discussing about torch-audiomentations
with us.
Motivation: Speed
We don't want data augmentation to be a bottleneck in model training speed. Here is a comparison of the time it takes to run 1D convolution:
Current state
torch-audiomentations is in an early development stage, so the APIs are subject to change.
Waveform transforms
AddBackgroundNoise
Added in v0.5.0
Add background noise to the input audio.
Gain
Added in v0.1.0
Multiply the audio by a random amplitude factor to reduce or increase the volume. This technique can help a model become somewhat invariant to the overall gain of the input audio.
Warning: This transform can return samples outside the [-1, 1] range, which may lead to clipping or wrap distortion, depending on what you do with the audio in a later stage. See also https://en.wikipedia.org/wiki/Clipping_(audio)#Digital_clipping
ApplyImpulseResponse
Added in v0.5.0
Convolve the given audio with impulse responses.
PeakNormalization
Added in v0.2.0
Apply a constant amount of gain, so that highest signal level present in each audio snippet in the batch becomes 0 dBFS, i.e. the loudest level allowed if all samples must be between -1 and 1.
This transform has an alternative mode (apply_to="only_too_loud_sounds") where it only applies to audio snippets that have extreme values outside the [-1, 1] range. This is useful for avoiding digital clipping in audio that is too loud, while leaving other audio untouched.
PolarityInversion
Added in v0.1.0
Flip the audio samples upside-down, reversing their polarity. In other words, multiply the waveform by -1, so negative values become positive, and vice versa. The result will sound the same compared to the original when played back in isolation. However, when mixed with other audio sources, the result may be different. This waveform inversion technique is sometimes used for audio cancellation or obtaining the difference between two waveforms. However, in the context of audio data augmentation, this transform can be useful when training phase-aware machine learning models.
Shift
Added in v0.5.0
Shift the audio forwards or backwards, with or without rollover
ShuffleChannels
To be added in v0.6.0
Given multichannel audio input (e.g. stereo), shuffle the channels, e.g. so left can become right and vice versa. This transform can help combat positional bias in machine learning models that input multichannel waveforms.
If the input audio is mono, this transform does nothing except emit a warning.
Changelog
[v0.6.0] - 2021-02-22
Added
- Implement
ShuffleChannels
[v0.5.1] - 2020-12-18
Fixed
- Fix a bug where
AddBackgroundNoise
did not work on CUDA - Fix a bug where symlinked audio files/folders were not found when looking for audio files
- Use torch.fft.rfft instead of the torch.rfft (deprecated in pytorch 1.7) when possible. As a
bonus, the change also improves performance in
ApplyImpulseResponse
.
[v0.5.0] - 2020-12-08
Added
- Release
AddBackgroundNoise
andApplyImpulseResponse
- Implement
Shift
Changed
- Make
sample_rate
optional. Allow specifyingsample_rate
in__init__
instead offorward
. This means torchaudio transforms can be used inCompose
now.
Removed
- Remove support for 1-dimensional and 2-dimensional audio tensors. Only 3-dimensional audio tensors are supported now.
Fixed
- Fix a bug where one could not use the
parameters
method of thenn.Module
subclass - Fix a bug where files with uppercase filename extension were not found
[v0.4.0] - 2020-11-10
Added
- Implement
Compose
for applying multiple transforms - Implement utility functions
from_dict
andfrom_yaml
for loading data augmentation configurations from dict, json or yaml - Officially support differentiability in most transforms
[v0.3.0] - 2020-10-27
Added
- Add support for alternative modes
per_batch
andper_channel
Changed
- Transforms now return the input unchanged when they are in eval mode
[v0.2.0] - 2020-10-19
Added
- Implement
PeakNormalization
- Expose
convolve
in the API
Changed
- Simplify API for using CUDA tensors. The device is now inferred from the input tensor.
[v0.1.0] - 2020-10-12
Added
- Initial release with
Gain
andPolarityInversion
Development
Setup
A GPU-enabled development environment for torch-audiomentations can be created with conda:
conda create --name torch-audiomentations-gpu python=3.7.3
conda activate torch-audiomentations-gpu
conda install pytorch=1.7.1 cudatoolkit=10.1 -c pytorch
conda env update
Run tests
pytest
Conventions
- Format python code with black
- Use Google-style docstrings
- Use explicit relative imports, not absolute imports
Acknowledgements
The development of torch-audiomentations is kindly backed by Nomono
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for torch-audiomentations-0.6.0.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | b34613bb074d9aa8a7a823d14b911f29518359d529bdd647ccb7b68e57e5d0a5 |
|
MD5 | 9ab6c043c552835902b29ce742b06d3e |
|
BLAKE2b-256 | 62d3bd3b3672a7b5da7704a35a8e5f8e8cbd0a57bc3e4acfb9e81112b0d6eaf6 |
Hashes for torch_audiomentations-0.6.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 1ff79a2eb06c733528a068c30b79463f882ab630c4f98831ede6cec1df9d3bb4 |
|
MD5 | 9e201bf2508c26e9155429ab1f2bf1d3 |
|
BLAKE2b-256 | bed72c6525c8127320993785c7ba15fcac1bba37575687ecb0b19506b2ec7cdb |