# timsainb/noisereduce

Noise reduction in python using spectral gating (speech, bioacoustics, audio, time-domain signals)

Repository: https://github.com/timsainb/noisereduce
Canonical: https://ross.abutalabs.com/products/noisereduce
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2025-08-19T04:41:53+00:00

## Health v2 (maintenance only)
Score: 39/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 37, release rhythm 8, longevity 100
- inputs: {"age_days": 2737, "days_push": 379, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1874, forks 267 (observed 2026-08-28T04:05:47.341628+00:00)

## What it is
A Python library for noise reduction in time-domain signals using spectral gating, supporting stationary and non-stationary noise reduction, with a PyTorch-based implementation usable as an nn.Module. It targets speech, bioacoustics, and physiological signals.

## Use cases
- remove background noise from speech recordings
- denoise audio in python
- clean up bioacoustic field recordings
- reduce noise from physiological signals
- integrate audio denoising into a pytorch model
- denoise long recordings with multiprocessing

## When to choose
- you need a simple, well-tested spectral gating denoiser in Python
- you want a PyTorch module that fits into a larger neural network
- you work with speech, bioacoustics, or physiological signals

## When to avoid
- you need deep-learning-based speech enhancement with state-of-the-art quality
- you need real-time streaming denoising in a production audio pipeline

## Facets
- artifact type: library
- maturity: active
- function: audio-processing, machine-learning
- domain: speech-processing, machine-learning
- platform: python, cross-platform
- tags: spectral-gating, denoising, pytorch, bioacoustics, speech-enhancement, audio

## Member repositories
- timsainb/noisereduce (main) score 39

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:47.341628+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 2026-08-30T03:14:48.641530+00:00, confidence not recorded.
  - readme: https://github.com/timsainb/noisereduce (fetched 2026-08-28T04:05:47.341628+00:00, sha f96f2a98df99)
  - registry_pypi: https://pypi.org/pypi/noisereduce/json (fetched 2026-08-29T10:53:48.218571+00:00, sha cfeb14c871b7)
- Data as of 2026-08-30T08:39:29.467469+00:00.