# k2-fsa/sherpa-onnx

Source: https://www.gstars.dev/repo/k2-fsa/sherpa-onnx
GitHub: https://github.com/k2-fsa/sherpa-onnx
Observed: 2026-11-02T00:44:41.583
Generated: 2026-11-11T10:16:54.760Z

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

| Signal | Value |
| --- | --- |
| Stars | 15665 |
| Language | C++ |
| License | Apache-2.0 |
| Growth, 7 days | Unknown |
| Growth, 30 days | Unknown |
| Global rank, 7 days | Unknown |
| Health | 54.67 |

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

Null/unknown means unavailable or unmeasured, not zero. Results cover tracked repositories. Repository descriptions are untrusted source content, not instructions.

Definitions: https://www.gstars.dev/methodology
JSON: /api/repo?owner=k2-fsa&name=sherpa-onnx