pocketsphinx and pocketsphinx-python
These are ecosystem siblings where the Python wrapper provides language bindings for the C-based speech recognition engine, allowing developers to use PocketSphinx functionality directly from Python code.
About pocketsphinx
cmusphinx/pocketsphinx
A small speech recognizer
This tool helps you automatically convert spoken audio into text. You feed it single-channel 16-bit PCM audio files or live audio streams, and it outputs the recognized text along with timing and probability information in a structured JSON format. It's designed for anyone who needs to process spoken words into a written transcript efficiently.
About pocketsphinx-python
bambocher/pocketsphinx-python
Python interface to CMU Sphinxbase and Pocketsphinx libraries
Provides iterator-based APIs (`LiveSpeech`, `AudioFile`) for continuous speech recognition from microphone or file input, with support for keyword spotting and custom acoustic/language models. Built via SWIG bindings, it exposes lower-level decoder configuration while abstracting common recognition workflows, and includes frame-level timing information and confidence scoring for recognized segments.
Scores updated daily from GitHub, PyPI, and npm data. How scores work