{"full_name":"k2-fsa/sherpa-onnx","owner":"k2-fsa","name":"sherpa-onnx","shard":"1","url":"https://github.com/k2-fsa/sherpa-onnx","description":"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","homepage":"https://k2-fsa.github.io/sherpa/onnx/index.html","topics":["asr","onnx","windows","linux","macos","cpp","android","ios","raspberry-pi","aarch64","arm32","csharp","dotnet","mfc","speech-to-text"],"tag_pages":["aarch64","android","asr","cpp","csharp","dotnet","ios","linux","macos","onnx","raspberry-pi","speech-to-text","windows"],"language":"C++","license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/71431748?v=4","created_at":"2022-09-01T05:47:33Z","pushed_at":"2026-11-13T16:38:00Z","metrics":{"stars":15968,"forks":1878,"watchers":119,"issues":1659,"prs":2396,"releases":195,"issues_open":568,"issues_closed":1091,"prs_open":83,"prs_closed":121,"prs_merged":2192,"discussions":120},"growth":{"day":{"stars":21,"forks":1,"base_day":"2026-11-15"}},"history":{"dates":["2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[15857,15884,15905,15906,15929,15947,15968],"forks":[1863,1868,1870,1872,1874,1877,1878],"watchers":[null,119,119,119,119,119,119],"issues_open":[null,571,569,569,567,568,568],"prs_open":[null,83,79,81,81,83,83]},"boards":{},"same_owner":[{"full_name":"k2-fsa/OmniVoice","name":"OmniVoice","shard":"1","boards":{}}],"issues":[{"number":1193,"title":"Questions related to MeloTTS ","comments":66,"created_at":"2024-07-31T02:06:36Z"},{"number":2120,"title":"OpenHamrony 系统上运行项目SherpaOnnxTts 报createCircularBuffer未导出","comments":49,"created_at":"2025-04-14T01:50:19Z"},{"number":569,"title":"Installing multiple voices ","comments":35,"created_at":"2024-02-01T14:30:11Z"},{"number":920,"title":"[Need help] How to realize Syllable-level Voice Recognition with sherpa-onnx Open Vocabulary Keyword Spotting","comments":30,"created_at":"2024-05-25T20:21:02Z"},{"number":1081,"title":"TTS bug","comments":28,"created_at":"2024-07-06T23:39:28Z"},{"number":633,"title":"Whisper onnxruntime exception on Android","comments":27,"created_at":"2024-03-04T13:42:46Z"},{"number":176,"title":"Installing ONNX for Windows gives error for cmake -DCMAKE_BUILD_TYPE=Release ..","comments":27,"created_at":"2023-06-13T17:11:15Z"},{"number":2515,"title":"Rockchip RK3588上npu推理耗时比cpu长","comments":23,"created_at":"2025-08-21T11:48:45Z"}],"discussions":[{"number":4191,"title":"OpenValet: sherpa-onnx KWS + Parakeet in an open-source macOS voice agent","comments":1,"category":"Show and tell","created_at":"2026-11-12T07:00:45Z"},{"number":4166,"title":"Murmur (murmurtts.com): Kokoro on Intel Macs with sherpa-onnx","comments":0,"category":"Show and tell","created_at":"2026-11-06T06:41:36Z"},{"number":3968,"title":"Piper vs Kokoro RTF on a 2-core ARM CPU, and what CPU contention costs (not a sherpa-onnx benchmark)","comments":2,"category":"General","created_at":"2026-09-20T19:36:29Z"},{"number":3939,"title":"License and redistribution of two speaker diarization ONNX models","comments":1,"category":"Q&A","created_at":"2026-09-09T06:27:02Z"},{"number":3903,"title":"sherpa-onnx + sensevoice android voice input keyboard","comments":1,"category":"Show and tell","created_at":"2026-08-28T09:23:44Z"},{"number":3900,"title":"Sherpa Transcript – 100% offline Android speech-to-text with live speaker diarization (Kroko Zipformer + ERes2Net)","comments":0,"category":"Show and tell","created_at":"2026-08-26T09:53:21Z"},{"number":3890,"title":"altgo：把 sherpa-onnx 内嵌进 Tauri 桌面端做本地语音输入的应用","comments":0,"category":"Show and tell","created_at":"2026-08-24T14:31:32Z"},{"number":3834,"title":"Procedure for hosting  sherpa ONNX  on Vivante NPU","comments":1,"category":"Q&A","created_at":"2026-08-03T05:56:20Z"}],"latest_release":{"name":"Forced alignment (fa) models","tag":"fa-models","published_at":"2026-11-11T14:59:02Z","body":"Acoustic models and pronunciation dictionaries for **forced alignment** with\n[sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx) — English\n(english_mfa v2.2.1 / v3.0.0 / v3.1.0) and Chinese\n(aishell3_pinyin / biaobei_pinyin / large_pinyin).\n\nModels, sources, package contents and usage are documented in\n[scripts/mfa/README.md](https://github.com/k2-fsa/sherpa-onnx/blob/master/scripts/mfa/README.md).\n","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}