# 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.

Repository: https://github.com/iver56/audiomentations
Canonical: https://ross.abutalabs.com/products/audiomentations
Homepage: https://iver56.github.io/audiomentations/
Language: Python
License: MIT
License Family: permissive
Topics: audio, sound, data-augmentation, augmentation, sound-processing, python, machine-learning, music, deep-learning, audio-effects, audio-data-augmentation, dsp
Last push: 2026-04-13T22:04:14+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 77, release rhythm 35, longevity 100
- inputs: {"age_days": 2759, "days_push": 142, "days_rel": 354, "gap_med": 60, "n_releases_24m": 8}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2314, forks 220 (observed 2026-08-28T04:06:36.717753+00:00)

## What it is
Audiomentations is a Python library for audio data augmentation with an API inspired by albumentations. It provides fast CPU-based waveform transforms for mono and multichannel audio that integrate into TensorFlow/Keras and PyTorch training pipelines.

## Use cases
- augment audio data for training speech recognition models
- add noise, pitch shift, and time stretch to audio samples
- improve robustness of audio ML models with synthetic variations
- augment multichannel audio for deep learning pipelines
- prepare audio datasets for Kaggle competitions
- apply random audio transforms during model training

## When to choose
- you need a well-maintained, widely used audio augmentation library for Python
- you train audio models with TensorFlow/Keras or PyTorch on CPU
- you want a composable, albumentations-style API with many transforms
- you need support for both mono and multichannel audio

## When to avoid
- you need GPU-accelerated augmentation inside PyTorch - use torch-audiomentations instead
- you need real-time audio effects processing rather than offline dataset augmentation
- your project is not in Python

## Facets
- artifact type: library
- maturity: stable
- function: audio-processing, machine-learning, data-generation
- domain: machine-learning, deep-learning, speech-processing
- platform: python, windows, cross-platform
- tags: data-augmentation, audio-deep-learning, dsp, pytorch, tensorflow, kaggle, audio, linux, macos

## Member repositories
- iver56/audiomentations (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:36.717753+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:39:27.176164+00:00, confidence not recorded.
  - readme: https://github.com/iver56/audiomentations (fetched 2026-08-28T04:06:36.717753+00:00, sha cf2f58825127)
  - homepage: https://iver56.github.io/audiomentations/ (fetched 2026-08-29T10:19:25.336250+00:00, sha 218f20f5c3e6)
  - registry_pypi: https://pypi.org/pypi/audiomentations/json (fetched 2026-08-29T10:19:25.345334+00:00, sha 4b865adfbbbc)
- Data as of 2026-08-30T08:39:29.467469+00:00.