Yi-Ting Chiu

I'm not entirely sure. Maybe you can check out this issue for potential solutions. https://github.com/microsoft/onnxruntime/issues/18973 The problem happens in the inference stage of the speech recognition module after voice activation...

Well... I'm using an apple silicon Mac so I don't use cuda. I hadn't actually tried running this project on an Nvidia machine yet

I created the dockerfile and added some docs in the readme for the Nvidia GPU passthrough container. It uses cuda:11.2.2-cudnn8. However, I haven't had the chance to test it. If...

Reopening this issue because it was never resolved. ## Why is this still relevant? - Configuring GPU acceleration for sherpa onnx asr is difficult. - FunASR requires an internet connection...

> Can you explain why it is difficult? [@t41372](https://github.com/t41372) **Goal:** We need to automate the setup process for Sherpa-ONNX as much as possible, since it's our default ASR option. If...

This issue is fixed and will be closed once #214 get merged into main along with 1.2 release. I'm moving sherpa-onnx related discussion to #219

Migration have been completed in dev branch and will be released along with 1.2. This issue will be closed with the release of 1.2

Yeah I tried and it doesn't work. The OBS browser is weird. Don't use the OBS browser source for now.

We have went through significant changes since this issue was opened. We now have a completely rewritten frontend in react. I believe that this issue have been resolved along with...

抱歉这么晚才来。 你的 Linux... 是不是有点太老了一些？你的 Linux 系统上的 glibc 太老了，我们项目用到的 `onnxruntime` 库需要新一些的这个库。 我对这方面不算特别熟悉，你可以搜一下看如何解决，不知道有没有办法整一个新一点的 glibc。 或是在彻底避开我们项目中用到 onnxruntime 的组件之后 (我觉得很难) 把 `pyproject.toml` 的 `onnxruntime` 和 `sherpa-onnx` 那两行删掉，主要就是 sherpa onnx，但还有其他组件会用到 onnxruntime。你可以试试 ASR 改用 faster whisper...