PocketSphinx is a compact, speaker-independent continuous speech recognition engine originating from Carnegie Mellon University’s CMU Sphinx work.
Unlike newer neural speech recognition systems that depend on large models and substantial computational resources, PocketSphinx uses established statistical speech recognition techniques whose relatively modest resource requirements remain useful for embedded applications, offline command recognition, constrained hardware and specialised recognition tasks.
The project provides both a standalone command-line program and programming interfaces for applications needing direct control of decoding. It can recognise complete utterances, process live audio in speech segments and perform forced alignment against known text. Current PocketSphinx also incorporates functionality that was previously supplied separately by SphinxBase.
This is free and open source software.
Key Features
- Large-vocabulary, speaker-independent continuous speech recognition using compact acoustic and language models.
- Designed to operate efficiently where memory and processing resources are limited.
- Completely offline recognition without sending recorded speech to external services.
- Command-line program for decoding audio files and standard input streams.
- Live recognition mode that detects speech segments and processes them individually.
- Single-utterance mode for treating each supplied recording as one recognition unit.
- Forced alignment of recorded speech against a supplied sequence of words.
- Optional phone-level alignment for obtaining finer-grained timing information.
- State-level alignment for applications requiring detailed acoustic model positioning.
- Recognition results can include start times, durations, probabilities and recognised text.
- Line-delimited JSON output simplifies integration with scripts and data-processing tools.
- Configurable acoustic models, pronunciation dictionaries and language models.
- JSGF grammar support for applications built around constrained command vocabularies.
- C API for integrating speech recognition directly into native applications.
- Python bindings provide access to the recognizer from Python applications and scripts.
- Configuration can be exported as JSON and subsequently loaded for reproducible setups.
- Includes facilities for determining suitable SoX parameters for preparing recognition input.
- Can receive microphone audio through external capture tools such as SoX.
Website: github.com/cmusphinx/pocketsphinx
Support:
Developer: David Huggins-Daines (current maintainer) and many contributors
License: BSD 2-Clause “Simplified” License
PocketSphinx is written in C. Learn C with our recommended free books and free tutorials.
Related Software
| Speech Recognition Tools | |
|---|---|
| Whisper | Automatic speech recognition (system trained on 680,000 hours of data |
| Flashlight | Fast, flexible machine learning library written entirely in C++. |
| Coqui STT | Deep-learning toolkit for training and deploying speech-to-text models |
| Kaldi | C++ toolkit designed for speech recognition researchers. |
| SpeechBrain | All-in-one conversational AI toolkit based on PyTorch |
| Handy | Offline speech-to-text application |
| ESPnet | End-to-End speech processing toolkit |
| deepspeech.pytorch | Implementation of DeepSpeech2 using Baidu Warp-CTC. |
| Whispering | Transcription application with global speech-to-text functionality |
| Julius | Two-pass large vocabulary continuous speech recognition engine |
| CMUSphinx | Speech recognition system for mobile and server applications |
| Simon | Flexible speech recognition software |
| hyprwhspr | Native speech-to-text designed for Arch / Omarchy |
| ostt | Open Speech-to-Text |
| DeepSpeech | TensorFlow implementation of Baidu's DeepSpeech architecture. |
| OpenSeq2Seq | TensorFlow-based toolkit for sequence-to-sequence models |
| Eesen | End-to-End Speech Recognition |
Read our verdict in the software roundup.
 Explore our comprehensive directory of recommended free and open source software. Our carefully curated collection spans every major software category.This directory is part of our ongoing series of informative articles for Linux enthusiasts. It features hundreds of detailed reviews, along with open source alternatives to proprietary solutions from major corporations such as Google, Microsoft, Apple, Adobe, IBM, Cisco, Oracle, and Autodesk. You’ll also find interesting projects to try, hardware coverage, free programming books and tutorials, and much more. Discovered a useful open source Linux program that we haven’t covered yet? Let us know by completing this form. |
Please read our Comment Policy before commenting.