Algorithms and implementations, also some awesome notes.

PocketSphinx is a lightweight speech recognition engine, specifically tuned for handheld and mobile devices, though it works equally well on the desktop

Build your own AI friend

A stripped down version of whisper.cpp - just the encoder

ESP32S3 Wakeword/Keyword Spotting starter project with ready to go ML model

Speech to Text SDK for Node.js

Automatic Speech Recognition

sph2pipe v2.5. We do not maintain this, and/or accept pull requests; just keeping a good and always available copy of the tool.

Voice100 includes neural TTS/ASR models. Inference of Voice100 is low cost as its models are tiny and only depend on CNN without recursion.

阿里云的实时语音识别服务(ASR)没有提供C的SDK,项目中需要,看了它java sdk的实现,就做了个C版demo

This repository contains a codebase to build automatic speech recognition (ASR) systems for iCub and run them within YARP. It also proposes new articulatory-based and unsupervised models for ASR.

This is FreeSwitch module that can do VAD and ASR with IFLYTEK websocket api.

Speech Recognition in Asterisk with Vosk Server

State-of-the-art (ranked #1 Aug 2022) German Speech Recognition in 284 lines of C++. This is a 100% private 100% offline 100% free CLI tool.

Next-gen AI+IoT framework for T2/T3/T5AI/ESP32/and more – Fast IoT and AI Agent hardware integration

Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment