sherpa-onnx
sherpa-onnx copied to clipboard
k2-fsa
Speech-to-text, text-to-speech, speaker diarization, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V,...
Hi, I'm getting the following error while clicking the generate button. I see the issue with `getTtsFor_en_US_amy_low` and working fine with `getTtsForVCTK` I would greatly appreciate it if you could...
Hello and thank you so much for this great repo! Unfortunately, I came across a very strange bug. When using the standalone application "sherpa-onnx-non-streaming-tts-x64-v1.9.23.exe" from the release -- everything is...
hi, I could not convert it into a library for b4a(basic4android). Can you write an example for b4a?
Any one can create a offline ws example for nodejs Like the python one offline-websocket-client-decode-files-sequential.py @csukuangfj
When will speaker identification functionality be supported in the C# version of sherpa-onnx? Thanks! 请问c#版本中什么时间会支持说话人识别功能？ 谢谢!
Is there any models that I can use to find the word timestamp by passing in the audio file and transcript ?
I'm trying to use some updated versions of sherpa-onnx for TTS. I'm getting the following error with my own application and the example project included in the repo (android/SherpaOnnxTts folder)....
* What are the key differences between running models and processes with sherpa-onnx compared to the toriginal onnxruntime? * Specifically for silero-vad, are there any differences as well?
在windows下，Java需要通过jni或jna访问dll。以下为编译为dll的过程。 [jni编译过程.pdf](https://github.com/k2-fsa/sherpa-onnx/files/15329516/jni.pdf) [利用eclipse导出jar包.pdf](https://github.com/k2-fsa/sherpa-onnx/files/15329517/eclipse.jar.pdf)
This PR is to integrate Nemo's faster conformer transducer into sherpa-decoder. More commits to be added.
