# jameslyons/python_speech_features

This library provides common speech features for ASR including MFCCs and filterbank energies.

Repository: https://github.com/jameslyons/python_speech_features
Canonical: https://ross.abutalabs.com/products/python_speech_features
Language: Python
License: MIT
License Family: permissive
Last push: 2021-10-20T10:08:48+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 4689, "days_push": 1778, "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 2423, forks 607 (observed 2026-08-28T04:06:50.671186+00:00)

## What it is
A Python library for extracting common speech features used in automatic speech recognition, including MFCCs, filterbank energies, log filterbank energies, and spectral subband centroids. It provides simple NumPy-based functions with configurable parameters for windowing, filtering, and preemphasis.

## Use cases
- extract mfcc features from audio
- compute filterbank energies for speech recognition
- feature extraction for asr models
- convert wav audio to mfcc vectors
- preprocess speech data for machine learning

## When to choose
- you need standard MFCC or filterbank features in Python with minimal setup
- you want a lightweight, well-documented NumPy-based feature extractor
- you're prototyping speech recognition or audio classification pipelines

## When to avoid
- you need GPU-accelerated or streaming feature extraction
- you need actively maintained software with recent updates
- you need end-to-end speech recognition rather than just feature extraction

## Facets
- artifact type: library
- maturity: maintenance
- function: audio-processing, speech-recognition, machine-learning
- domain: speech-processing, machine-learning
- platform: python, cross-platform
- tags: mfcc, filterbank-energies, asr-features, signal-processing, numpy, audio

## Member repositories
- jameslyons/python_speech_features (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:50.671186+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 2026-08-30T02:33:00.247444+00:00, confidence not recorded.
  - readme: https://github.com/jameslyons/python_speech_features (fetched 2026-08-28T04:06:50.671186+00:00, sha d4cd9b63bf49)
  - registry_pypi: https://pypi.org/pypi/python_speech_features/json (fetched 2026-08-29T10:13:10.737491+00:00, sha f10e2306e643)
- Data as of 2026-08-30T08:39:29.467469+00:00.