sepia-stt-server icon indicating copy to clipboard operation
sepia-stt-server copied to clipboard

Published 20 hours ago • verified publisher icon SEPIA-Framework

Request to add sherpa-ncnn and sherpa-onnx

Open csukuangfj opened this issue 1 year ago • 2 comments

They both support real-time speech recognition on embedded devices.

Please see

  • https://github.com/k2-fsa/sherpa-onnx
  • https://github.com/k2-fsa/sherpa-ncnn

Note: Please use our latest streaming zipformer for testing.

csukuangfj avatar Apr 24 '23 04:04 csukuangfj

I'm certainly interested in adding those engines, especially since I'll probably add 'onnxruntime' with the next update anyways.

Would you say the Sherpa design and API have matured enough now to be considered "ready for production"? What I want to avoid is implementing a very experimental build that still has a lot of moving parts.

fquirin avatar Apr 24 '23 08:04 fquirin

sherpa-ncnn can be considered stable for now.

sherpa-onnx is still under development.

csukuangfj avatar Apr 24 '23 09:04 csukuangfj