sherpa-onnx
sherpa-onnx copied to clipboard
k2-fsa
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...
cant we implement a method to detect the status of tts? currently speaking text that can be use to highlight the speaking text?
Just a quick FYI.. I've VERY QUICKLY (so bugs beware) added sherpa-onnx to this python tts-wrapper.. https://github.com/willwade/tts-wrapper?tab=readme-ov-file#sherpa-onnx We do fun things like listing available voices, auto downloading models and running...
I am using Mac M1 chipset, and when I execute build-swift-macos.h it is throwing an error: ``` libtool: error: unrecognised option: '-static' ```
Would it be possible to use sherpa-onnx to do voice conversion? (Changing voice in audio to something else) And maybe voice cloning for tts? (Clone voice from audio and generate...
Hi, was playing around with the VAD model and realized that the maximum speech duration is kept to around 20s regardless of the buffer size. Took a look at the...
If I want to extend the existing functionality for Whisper recognizer and pass a language at runtime, what would be a recommended approach? I looked at the decode() API, there...
Ordered by importance - [ ] Start and stop timestamps for each segment - [ ] New segment decoded callback (or I would like to know better how to stream...
Fixes #196 # Usage 1. When building sherpa-onnx, please pass ``` -DSHERPA_ONNX_ENABLE_ROCM=ON -DBUILD_SHARED_LIBS=ON ``` 2. when running sherpa-onnx, please use ``` --provider=rocm ``` (Please make sure you have installed ROCm...
## Update It was issue with the tokens file, it was invalid. maybe we can improve the error message? --- I tried to run tts model on macOS m1 with...
When enabling `cuda` on `Windows` it failed with the error ```console error: could not find native static library `onnxruntime`, perhaps an -L flag is missing? ``` Although I already link...