# cmusphinx/sphinx4

Pure Java speech recognition library

Repository: https://github.com/cmusphinx/sphinx4
Canonical: https://ross.abutalabs.com/products/sphinx4
Language: Java
License: NOASSERTION
License Family: other
Last push: 2022-10-18T04:01:35+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4531, "days_push": 1415, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1437, forks 582 (observed 2026-08-28T04:04:43.783396+00:00)

## What it is
Sphinx-4 is a speaker-independent, continuous speech recognition library written entirely in Java, originating from CMU and industry research labs. It runs on any platform with a JVM without native compilation and is released under a BSD-style license.

## Use cases
- transcribe audio recordings to text in Java
- add offline voice command recognition to a desktop app
- build a speaker-independent speech recognizer on the JVM
- recognize continuous speech without cloud services
- experiment with speech recognition algorithms in research
- convert spoken audio from wav files into text

## When to choose
- you need pure-Java, cross-platform speech recognition with no native dependencies
- you want fully offline recognition without sending audio to a cloud API
- you need an embeddable ASR library inside a JVM application

## When to avoid
- you need state-of-the-art accuracy on noisy or large-vocabulary audio (modern deep-learning ASR is stronger)
- you are not on the JVM and cannot use Java
- you need active development or frequent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: speech-recognition, audio-processing, machine-learning
- domain: speech-processing, machine-learning
- platform: jvm, cross-platform
- tags: speech-recognition, java, offline-asr, cmu-sphinx, natural-language-processing

## Member repositories
- cmusphinx/sphinx4 (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:43.783396+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 2026-08-30T04:36:43.683345+00:00, confidence not recorded.
  - readme: https://github.com/cmusphinx/sphinx4 (fetched 2026-08-28T04:04:43.783396+00:00, sha a25751723fd8)
- Data as of 2026-08-30T08:39:29.467469+00:00.