sherpa-onnx
Pilot it+558 this week★ 14,468 · 1,654 forks
Offline speech-to-text and text-to-speech engine
Worth a timeboxed spike before you bet on it.
Who it's for
Small teams building voice-enabled products
What it replaces
Cloud-based speech services like Google Cloud Speech-to-Text
The catch
High maintenance and customization required for specific use cases
Your first hour
Clone the repository and test the demo application on a local machine
The numbers
Stars14,468
Forks1,654
Stars added (7d)+558
Open issues627
LanguageC++
LicenceApache-2.0
Last pushUpdated today
Project age4 years old
Maintainers describe it as: “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”
aarch64androidarm32asrcppcsharpdotnetioslazaruslinux
sherpa-onnx, in short
- Should a small team use sherpa-onnx?
- Pilot it. Worth a timeboxed spike before you bet on it. Small teams building voice-enabled products
- What does sherpa-onnx actually do?
- Offline speech-to-text and text-to-speech engine
- What does sherpa-onnx replace?
- Cloud-based speech services like Google Cloud Speech-to-Text
- What is the downside of sherpa-onnx?
- High maintenance and customization required for specific use cases
- Can sherpa-onnx be used in a commercial product?
- Its licence is Apache-2.0, which is permissive and generally fine for commercial use. Confirm against the LICENSE file in the repository.