iver56/audiomentations
A Python library for audio data augmentation. Useful for making audio ML models work well in the real world, not just in the lab.
This tool helps audio machine learning engineers improve their models' real-world performance by artificially expanding audio datasets. It takes existing audio recordings and applies various realistic transformations like adding noise, shifting pitch, or changing tempo, producing new, varied versions of the original audio. This is ideal for anyone developing or training AI models that process sound.
2,239 stars. Used by 5 other packages. Available on PyPI.
Use this if you need to make your audio-based AI models more robust and perform well outside of controlled lab environments by generating diverse training data.
Not ideal if you need a PyTorch-specific solution with GPU acceleration, as a dedicated alternative is available for that.
Stars
2,239
Forks
211
Language
Python
License
MIT
Category
Last pushed
Dec 27, 2025
Commits (30d)
0
Dependencies
7
Reverse dependents
5
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/iver56/audiomentations"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
Rikorose/DeepFilterNet
Noise supression using deep filtering
torchsynth/torchsynth
A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.
marl/openl3
OpenL3: Open-source deep audio and image embeddings
archinetai/audio-data-pytorch
A collection of useful audio datasets and transforms for PyTorch.
ductho-le/WaveDL
A Scalable Deep Learning Framework for Wave-Based Inverse Problems