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.
Offers 40+ composable transforms including frequency-domain effects (pitch shifting, EQ, filtering), convolution-based room simulation, and codec compression, with an albumentations-inspired API for chainable augmentations. Operates on CPU using NumPy and librosa for waveform processing, supporting both mono and multichannel audio with direct integration into TensorFlow/Keras and PyTorch training loops.
2,239 stars and 562,579 monthly downloads. Used by 5 other packages. Available on PyPI.
Stars
2,239
Forks
211
Language
Python
License
MIT
Category
Last pushed
Dec 27, 2025
Monthly downloads
562,579
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
marl/openl3
OpenL3: Open-source deep audio and image embeddings
ductho-le/WaveDL
A Scalable Deep Learning Framework for Wave-Based Inverse Problems
Spijkervet/torchaudio-augmentations
Audio transformations library for PyTorch
torchsynth/torchsynth
A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.
Rikorose/DeepFilterNet
Noise supression using deep filtering