Audio augmentations library for PyTorch for audio in the time-domain

Related tags

Audiotorchaudio-augmentations
Overview

Audio Augmentations

DOI

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}
}
Comments
  • Delay augmentation on cuda

    Delay augmentation on cuda

    Hi. Currently the delay augmentation doesn't work on gpu since part of the signal is on cpu. I think making thebeginning tensor same as the audio tensor device should fix it. Thanks. https://github.com/Spijkervet/torchaudio-augmentations/blob/d044f9d020e12032ab9280acf5f34a337e72d212/torchaudio_augmentations/augmentations/delay.py#L31

    opened by sidml 2
  • Correctness unit test would be great

    Correctness unit test would be great

    For some transforms, we can test if the values are actually correct by manually computing the expected value. For example, PolarityInversion could be test with some tiny tensors like [[0.1, 0.5, -1.0]]. Reverse as well. Probably only those two? Still, it'd be better than not having any.

    opened by keunwoochoi 2
  • Default value of `max_snr` in `Noise`

    Default value of `max_snr` in `Noise`

    1.0 of SNR with signal and white noise would be a really heavily corrupted signal. Could we set it to be a little more reasonable value?

    Related; it'd be great if one can hear some examples of the augmented result.

    opened by keunwoochoi 2
  • End-to-end PitchShift transform tests

    End-to-end PitchShift transform tests

    This merge requests adds end-to-end pitch transformation detection with librosa's pYIN pitch detection, to test if the applied transformation yields the expected pitch transposition.

    opened by Spijkervet 0
  • Unittests

    Unittests

    This adds various unittests and fixes to multi-channel input for Reverb, Pitch, Reverse and HighLowPass filter augmentations. It also removes Essentia as a dependency, and instead uses julius for IRR filtering.

    opened by Spijkervet 0
  • import error

    import error

    when i import torchaudio_augmentation

    I got the error

    RuntimeError : torchaudio.sox_effects.sox_effects.effect_names requires module: torchaudio._torchaudio

    how can I deal with it?

    opened by EavnJeong 0
  • Snr db

    Snr db

    Hi, Thanks for the interesting work. Allow me to suggest this change for two reasons:

    • Expressing SNR in dB cancels the doubt there might be between power SNR and RMS SNR.
    • When sampling an SNR, it feels to me like it makes more sense to uniformly sample from the log scale of the dB than on the linear range. This way you ensure that your low SNR have as much chances as your high SNR.

    I hope it makes sens. I'd be glad to discuss further about that.

    opened by wesbz 0
  • sanity check for duration

    sanity check for duration

    In transforms where the duration may change, if the input audio is shorter than n_samples, the error message is not intuitive. I forgot but in some case, the multiprocessing-based dataloader silently died. Maybe it's worth checking it somewhere?

    opened by keunwoochoi 0
  • Shapes are still a bit confusing

    Shapes are still a bit confusing

    From ComposeMany.__call__(), is x also a ch, time shape 2-dim tensor? And I'm sure what would be the expected behavior by this function, especially the shape of the output.

    opened by keunwoochoi 3
Releases(v0.2.3)
Owner
Janne
Music producer, machine learning in MIR & occasional ethical hacker
Janne
GitHub Repository
Minimal command-line music player written in Python

pyms Minimal command-line music player written in Python. Designed with elegance and minimalism. Resizes dynamically with your terminal. Dependencies

12 Sep 23, 2022
Python I/O for STEM audio files

stempeg = stems + ffmpeg Python package to read and write STEM audio files. Technically, stems are audio containers that combine multiple audio stream

Fabian-Robert Stöter 72 Dec 23, 2022
Telegram Bot to play music in VoiceChat with Channel Support and autostarts Radio.

VCPlayerBot Telegram bot to stream videos in telegram voicechat for both groups and channels. Supports live streams, YouTube videos and telegram media

Abdisamad Omar Mohamed 1 Oct 15, 2021
Bot Music Pintar. Created by Rio

🎶 Rio Music 🎶 Kalo Fork Star Ya Bang Hehehe Requirements 📝 FFmpeg NodeJS nodesource.com Python 3.8+ or 3.7 PyTgCalls Generate String Using Replit ⤵

RioProjectX 7 Jun 15, 2022
Python tools for the corpus analysis of popular music.

CATCHY Corpus Analysis Tools for Computational Hook discovery Python tools for the corpus analysis of popular music recordings. The tools can be used

Jan VB 20 Aug 20, 2022
Simple discord bot by @merive 🤖

Parzibot Powerful and Useful Discord Bot on Python. The source code of the bot is available to everyone. Parzibot uses English language. This is free

merive_ 3 Dec 28, 2022
voice assistant made with python that search for covid19 data(like total cases, deaths and etc) in a specific country

covid19-voice-assistant voice assistant made with python that search for covid19 data(like total cases, deaths and etc) in a specific country installi

Miguel 2 Dec 05, 2021
Frescobaldi LilyPond Editor

README for Frescobaldi Homepage: http://www.frescobaldi.org/ Main author: Wilbert Berendsen Frescobaldi is a LilyPond sheet music text editor. It aims

Frescobaldi 600 Dec 29, 2022
Spotipy - Player de música simples em Python

Spotipy Player de música simples em Python, utilizando a biblioteca Pysimplegui para a interface gráfica. Este tocador é bastante simples em si, mas p

Adelino Almeida 4 Feb 28, 2022
Carnatic Notes Predictor for audio files

Carnatic Notes Predictor for audio files Link for live application: https://share.streamlit.io/pradeepak1/carnatic-notes-predictor-for-audio-files/mai

1 Nov 06, 2021
Music generation using ml / dl

Data analysis Document here the project: deep_music Description: Project Description Data Source: Type of analysis: Please document the project the be

0 Jul 03, 2022
Synthesia but open source, made in python and free

PyPiano Synthesia but open source, made in python and free Requirements are in requirements.txt If you struggle with installation of pyaudio, run : pi

DaCapo 11 Nov 06, 2022
Official implementation of A cappella: Audio-visual Singing VoiceSeparation, from BMVC21

Y-Net Official implementation of A cappella: Audio-visual Singing VoiceSeparation, British Machine Vision Conference 2021 Project page: ipcv.github.io

Juan F. Montesinos 12 Oct 22, 2022
Audio features extraction

Yaafe Yet Another Audio Feature Extractor Build status Branch master : Branch dev : Anaconda : Install Conda Yaafe can be easily install with conda. T

Yaafe 231 Dec 26, 2022
pyo is a Python module written in C to help digital signal processing script creation.

pyo is a Python module written in C to help digital signal processing script creation.

Olivier Bélanger 1.1k Jan 01, 2023
Analysis of voices based on the Mel-frequency band

Speaker_partition_module Analysis of voices based on the Mel-frequency band. Goal: Identification of voices speaking (diarization) and calculation of

1 Feb 06, 2022
Conferencing Speech Challenge

ConferencingSpeech 2021 challenge This repository contains the datasets list and scripts required for the ConferencingSpeech challenge. For more detai

73 Nov 29, 2022
Official implementation of A cappella: Audio-visual Singing VoiceSeparation, from BMVC21

Y-Net Official implementation of A cappella: Audio-visual Singing VoiceSeparation, British Machine Vision Conference 2021 Project page: ipcv.github.io

Juan F. Montesinos 12 Oct 22, 2022
The venturimeter works on the principle of Bernoulli's equation, i.e., the pressure decreases as the velocity increases.

The venturimeter works on the principle of Bernoulli's equation, i.e., the pressure decreases as the velocity increases. The cross-section of the throat is less than the cross-section of the inlet pi

Shankar Mahadevan L 1 Dec 03, 2021
Voice package for Pycord adding extra features.

VoiceIO Voice package for Pycord adding extra features. Example Down bellow is an example of what you can currently do. import voiceio process = voic

pycord 1 Dec 24, 2021