{"data":{"slug":"k2-fsa-sherpa-onnx","name":"sherpa-onnx","tagline":"Speech-to-text and related audio processing tools using ONNX with cross-platform support","github_url":"https://github.com/k2-fsa/sherpa-onnx","owner":"k2-fsa","repo":"sherpa-onnx","owner_avatar_url":"https://avatars.githubusercontent.com/u/71431748?v=4","primary_language":"C++","stars":14860,"forks":1708,"topics":["aarch64","android","arm32","asr","cpp","csharp","dotnet","ios","lazarus","linux","macos","mfc","object-pascal","onnx","raspberry-pi","risc-v","speech-to-text","text-to-speech","vits","windows"],"archived":false,"github_pushed_at":"2026-09-20T07:00:27+00:00","maintenance_label":"Very active","stars_delta_30d":1018,"url":"https://www.graphcanon.com/tools/k2-fsa-sherpa-onnx","markdown_url":"https://www.graphcanon.com/tools/k2-fsa-sherpa-onnx.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/k2-fsa-sherpa-onnx","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=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_url":"https://k2-fsa.github.io/sherpa/onnx/index.html","license":"Apache-2.0","open_issues":620,"watchers":121,"ai_summary":"A repository for speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, VAD functions utilizing modern Kaldi and onnxruntime. Supports a wide array of platforms including embedded systems, mobile OSes like Android and iOS, and various architectures suitable for edge devices, with NPUs integration.","readme_excerpt":"
\n\n\n\n
\n\n ### Supported functions\n\n|Speech recognition| [Speech synthesis][tts-url] | [Source separation][ss-url] |\n|------------------|------------------|-------------------|\n| ✔️ | ✔️ | ✔️ |\n\n|Speaker identification| [Speaker diarization][sd-url] | Speaker verification |\n|----------------------|-------------------- |------------------------|\n| ✔️ | ✔️ | ✔️ |\n\n| [Spoken Language identification][slid-url] | [Audio tagging][at-url] | [Voice activity detection][vad-url] |\n|--------------------------------|---------------|--------------------------|\n| ✔️ | ✔️ | ✔️ |\n\n| [Keyword spotting][kws-url] | [Add punctuation][punct-url] | [Speech enhancement][se-url] |\n|------------------|-----------------|--------------------|\n| ✔️ | ✔️ | ✔️ |\n\n\n### Supported platforms\n\n|Architecture| Android | iOS | Windows | macOS | linux | HarmonyOS |\n|------------|---------|---------|------------|-------|-------|-----------|\n| x64 | ✔️ | | ✔️ | ✔️ | ✔️ | ✔️ |\n| x86 | ✔️ | | ✔️ | | | |\n| arm64 | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ |\n| arm32 | ✔️ | | | | ✔️ | ✔️ |\n| riscv64 | | | | | ✔️ | |\n\n### Supported programming languages\n\n| 1. C++ | 2. C | 3. Python | 4. JavaScript |\n|--------|-------|-----------|---------------|\n| ✔️ | ✔️ | ✔️ | ✔️ |\n\n|5. Java | 6. C# | 7. Kotlin | 8. Swift |\n|--------|-------|-----------|----------|\n| ✔️ | ✔️ | ✔️ | ✔️ |\n\n| 9. Go | 10. Dart | 11. Rust | 12. Pascal |\n|-------|----------|----------|------------|\n| ✔️ | ✔️ | ✔️ | ✔️ |\n\n\nIt also supports WebAssembly.\n\n### Supported frameworks\n\n#### [Flutter][flutter-url]\n\n|Architecture| Android | iOS | Windows | macOS | Linux | Web |\n|------------|---------|---------|---------|-------|-------|-----|\n| x64 | ✔️ | | ✔️ | ✔️ | ✔️ | ✔️ |\n| x86 | ✔️ | | | | | ✔️ |\n| arm64 | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ |\n| arm32 | ✔️ | | | | | ✔️ |\n\n- Pre-built Flutter demo apps: [flutter releases][flutter-releases]\n\n#### [Tauri][tauri-url]\n\n|Architecture| Android | iOS | Windows | macOS | Linux |\n|------------|---------|---------|---------|-------|-------|\n| x64 | ✔️ | | ✔️ | ✔️ | ✔️ |\n| x86 | ✔️ | | | | |\n| arm64 | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ |\n| arm32 | ✔️ | | | | |\n\n- Pre-built Tauri demo apps: [tauri releases][tauri-releases]\n\n[flutter-url]: https://flutter.dev\n[tauri-url]: https://v2.tauri.app\n[flutter-releases]: https://github.com/k2-fsa/sherpa-onnx/releases/tag/flutter\n[tauri-releases]: https://github.com/k2-fsa/sherpa-onnx/releases/tag/tauri\n\n### Supported NPUs\n\n| [1. Rockchip NPU (RKNN)][rknpu-doc] | [2. Qualcomm NPU (QNN)][qnn-doc] | [3. Ascend NPU][ascend-doc] |\n|-------------------------------------|-----------------------------------|-----------------------------|\n| ✔️ | ✔️ | ✔️ |\n\n| [4. Axera NPU][axera-npu] | [5. Intel NPU (OpenVINO)][openvino-npu] |\n|---------------------------|------------------------------------------|\n| ✔️ | ✔️ |\n\n[openvino-npu]: OPENVINO.md\n\n[Join our discord](https://discord.gg/fJdxzg2VbG)\n\n\n## Introduction\n\nThis repository supports running the following functions **locally**\n\n - Speech-to-text (i.e., ASR); both","github_created_at":"2022-09-01T05:47:33+00:00","created_at":"2026-07-11T12:04:29.683224+00:00","updated_at":"2026-09-20T07:03:36.550166+00:00","categories":[{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"aarch64","name":"aarch64"},{"slug":"android","name":"android"},{"slug":"arm32","name":"arm32"},{"slug":"asr","name":"asr"},{"slug":"cpp","name":"cpp"},{"slug":"csharp","name":"csharp"},{"slug":"dotnet","name":"dotnet"},{"slug":"ios","name":"ios"}],"trust":{"provenance":{"is_fork":false,"github_id":531380835,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T07:03:34.456Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":10,"days_since_push":0,"last_release_at":"2026-09-10T14:00:23Z","stars_delta_30d":1018,"open_issues_delta_30d":3},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:04:32.133Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T07:03:35.535Z"},"languages":{"value":["c++"],"source":"github.language","observed_at":"2026-09-20T07:03:35.535Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-20T07:03:35.535Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need to deploy speech recognition or synthesis on platforms such as Raspberry Pi, RISC-V, and with NPUs like Rockchip, Axera, Ascend","For applications that require processing on a variety of embedded systems, mobile OSes without internet connectivity"],"when_not_to_use":["If your project strictly requires real-time web service interaction or server-based speech-to-text solutions","When the target environment lacks support for ONNX runtime and specific NPUs integrated within sherpa-onnx"],"source":"enrich:decision_facts","observed_at":"2026-07-16T23:22:59.560Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"sherpa-onnx offers local speech-to-text processing across multiple platforms including embedded systems with NPUs, supporting wide programming languages."}]}}