# mozilla/DeepSpeech

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

Repository: https://github.com/mozilla/DeepSpeech
Canonical: https://ross.abutalabs.com/products/deepspeech
Language: C++
License: MPL-2.0
License Family: copyleft
Topics: deep-learning, machine-learning, neural-networks, tensorflow, speech-recognition, speech-to-text, deepspeech, embedded, on-device, offline
Archived: true
Last push: 2025-06-19T12:52:51+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 27, release rhythm 8, longevity 100
- inputs: {"age_days": 3744, "days_push": 440, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 26771, forks 4079 (observed 2026-08-28T04:11:47.121492+00:00)

## What it is
DeepSpeech is an open-source, offline speech-to-text engine based on Baidu's Deep Speech research paper and implemented with TensorFlow. It can run in real time on devices from a Raspberry Pi 4 to GPU servers, with pre-trained models and tooling for training custom models.

## Use cases
- transcribe audio to text offline on a Raspberry Pi
- run speech recognition on-device without cloud services
- convert voice recordings to text in real time
- train a custom speech-to-text model
- add voice input to an embedded device

## When to choose
- you need fully offline, on-device speech recognition on low-power hardware
- you want to fine-tune or train your own speech model with TensorFlow
- you need a lightweight STT engine for embedded Linux devices

## When to avoid
- you need an actively maintained project - DeepSpeech is officially discontinued
- you need state-of-the-art accuracy on modern hardware, where newer engines like Whisper or Coqui STT are better
- you need cloud-scale multilingual transcription

## Facets
- artifact type: library
- maturity: abandoned
- function: speech-recognition, machine-learning, deep-learning
- domain: speech-processing, machine-learning, embedded-systems
- platform: cross-platform, embedded, python, cpp
- tags: speech-to-text, offline, on-device, tensorflow, discontinued, raspberry-pi, linux, gpu

## Member repositories
- mozilla/DeepSpeech (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:47.121492+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 2026-08-29T16:55:49.856088+00:00, confidence not recorded.
  - readme: https://github.com/mozilla/DeepSpeech (fetched 2026-08-28T04:11:47.121492+00:00, sha 8faa55befa29)
- Data as of 2026-08-30T08:39:29.467469+00:00.