Speech-to-text server framework with next-gen Kaldi
$ git clone https://github.com/k2-fsa/sherpa.gitReal-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, LicheePi4A etc.
WebSocket, gRPC and WebRTC speech recognition server based on Vosk and Kaldi libraries
Espresso: A Fast End-to-End Neural Speech Recognition Toolkit
Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.
A Deep-Learning-Based Chinese Speech Recognition System εΊδΊζ·±εΊ¦ε¦δΉ ηδΈζθ―ι³θ―ε«η³»η»
Production First and Production Ready End-to-End Speech Recognition Toolkit
Data from GitHub Β· snapshot Sep 24, 2026