
sherpa-ncnn
by k2-fsa (organization)
Real-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. (description from the project’s GitHub page)
Repository facts
- Stars
- 1,794
- Forks
- 223
- Open issues and pull requests
- 66
- Primary language
- C++
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- k2-fsa · Organization
- Created
- Sep 4, 2022
- Last push
- Oct 20, 2025
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 7,624: FireRedTeam/FireRedASR2S
A SOTA Industrial-Grade All-in-One ASR system with ASR, VAD, LID, and Punc modules. FireRedASR2 supports Chinese (Mandarin, 20+ dialects/accents), English, code-switching, and bot…
716 starsPythonApache-2.0Last push Jun 2, 2026
Rank 8,719: shashikg/WhisperS2T
An Optimized Speech-to-Text Pipeline for the Whisper Model Supporting Multiple Inference Engine
581 starsJupyter NotebookMITLast push Aug 27, 2024
Rank 2,613: BayesWitnesses/m2cgen
Transform ML models into a native code (Java, C, Python, Go, JavaScript, Visual Basic, C#, R, PowerShell, PHP, Dart, Haskell, Ruby, F#, Rust) with zero dependencies
3,000 starsPythonMITLast push Aug 3, 2024
Rank 6,091: k2-fsa/sherpa
Speech-to-text server framework with next-gen Kaldi
1,008 starsC++Apache-2.0Last push Oct 18, 2026
Rank 6,313: sandrohanea/whisper.net
Whisper.net. Speech to text made simple using Whisper Models
950 starsC#MITLast push Oct 18, 2026
Rank 6,710: jtkim-kaist/VAD
Voice activity detection (VAD) toolkit including DNN, bDNN, LSTM and ACAM based VAD. We also provide our directly recorded dataset.
866 starsMATLABNo license file detectedLast push Jun 9, 2021