K. S. Ernest (iFire) Lee

Thank you for your paper. Hope to review the code.

Can you check if opencl drivers are installed? Like `sudo apt install opencl-headers ocl-icd-opencl-dev -y`. Also what linux and what hardware.

I have no idea but maybe it's confused trying to use opencl on amd vs opencl on nvidia.

As far as I know we wrote the capture node because we weren't able to get the record node to work 3-4 years ago.

@AllenDang Here was the original design documentation. https://github.com/godotengine/godot-proposals/issues/2013

People have mentioned combining silence detection with whisper as a first thought, but I am concerned about the total latency of the voice transcription.

AI based VAD is also a thing, and that was my approach for iree and whisper-jax.

I was looking into Audio denoising powered by ONNX Runtime for enhanced clarity. https://github.com/DakeQQ/Audio-Denoiser-ONNX

Here's our discord. https://discord.gg/H3s3PD49XC

Awesome about the vulkan integration. We did metal integration once, maybe it'll be easy this time too.