k2-fsa/sherpa-onnx

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

Language modelsC++#asr#onnx#windows#linux#macos

1.9 Steady Magnitude out of 10. Star growth looks organic. Data as of September 18, 2026.

Open on Seismograph Open on GitHub

About the project

A collection of offline speech processing tools built on next-gen Kaldi and onnxruntime: speech recognition and synthesis, speaker diarization and identification, VAD, speech enhancement, source separation, and keyword spotting. Runs on servers, mobile, and embedded devices without an internet connection.

Useful for

Add offline speech recognition to an Android or iOS app using the provided bindings
Generate video subtitles with built-in ASR and punctuation restoration
Run VAD and speaker diarization on a Raspberry Pi to label meeting recordings

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

8 stars so far today, about 10 expected by the end of the day.
GitHub Trending C++ today: #11, +25 stars.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 14,844
Stars in a day: 10
Forks: 1,707
Issues and pull requests: 3,818
Watchers: 121
Language: C++
License: Apache-2.0
Latest release: v1.13.8 · September 10, 2026
Created: September 1, 2022
Last push: September 17, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

September 18, 2026GitHub Trending C++ today: #11, +25 stars

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/k2-fsa/sherpa-onnx.svg?lang=en)](https://gitnova.dev/en/r/k2-fsa/sherpa-onnx)

Similar projects

8.6
TheoLeeCJ/SemIf
An open reproduction of the Jev-style semantic decision interface: reads typed option probabilities directly from a 4B model's logits without generating text. Runs on a single RTX 3090.

BreakoutLanguage modelsPython+600 stars in a day
7.1
vinnylarouge/jevlike
A small trainable model that picks one option from a changing list of text options in a single forward pass, an open alternative to TypeSafe's Jev. Aimed at developers who need fast classification or menu selection…

Early signalLanguage modelsPython+148 stars in a day
6.9
Continuum-AI-Corp/OrcaBonsai-27B-Uncensored
A tool for runtime refusal ablation in the compressed Ternary Bonsai 2 27B LLM: it projects the residual stream to remove the refusal direction without modifying or re-quantizing weights. Runs on Apple Silicon via MLX.

Early signalLanguage modelsPython+365 stars in a day
6.4
TianyuCodings/NanoJev
A nano replica of Jev built on Qwen3-0.6B that outputs probability distributions over candidates in a single forward pass with no token decoding, plus a training pipeline and game demos (maze, Snake).

Early signalLanguage modelsPython+344 stars in a day
6.3
zhengkid/Dream-RSI
Research project on recursive self-improvement: past discovery histories become a replay simulator used to evaluate and refine exploration policies. Code is still being prepared; paper and demo are available.

Early signalLanguage models+137 stars in a day
5.0
ekzhang/openjev-sglang
HTTP server implementing the TypeSafe/Jev API for structured text classification on Qwen3.6-35B-A3B via SGLang; returns answer probabilities without generating a chain of thought.

Early signalLanguage modelsPython+74 stars in a day