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
View on Github
Activity
- Latest release
- 4d ago
- Total releases
- 31
- Cadence
- ~2 days
- Last 12 months
- 31
Reach
- Downloads
- 371.7k
- Stars
- 14.8k
Details
- License
- Apache-2.0
- First release
- Feb 23, 2026
Releases
| Version | Released | |
|---|---|---|
1.13.8
patch
| ||
1.13.7
patch
| ||
1.13.6
patch
| ||
1.13.5
patch
| ||
1.13.4
unknown
| ||
1.13.3
unknown
| ||
1.13.2
unknown
| ||
1.13.1
unknown
| ||
1.13.0
unknown
| ||
1.12.40
unknown
| ||
1.12.39
unknown
| ||
1.12.38
unknown
| ||
1.12.36
unknown
| ||
1.12.35
unknown
| ||
1.12.34
unknown
| ||
1.12.33
unknown
| ||
1.12.32
unknown
| ||
1.12.31
unknown
| ||
1.12.30
unknown
| ||
0.1.13
unknown
| ||
0.1.12
unknown
| ||
0.1.11
unknown
| ||
0.1.10
unknown
| ||
0.1.9
unknown
| ||
0.1.8
unknown
| ||
0.1.7
unknown
| ||
0.1.6
unknown
| ||
0.1.3
unknown
| ||
0.1.2
unknown
| ||
0.1.1
unknown
| ||
0.1.0
unknown
|