I have my microphone setup on Jetson and was looking how to run my .pb or onnx model on Jetson and how to feed the input of the audio to the model on Jetson?
Thanks in Advance!
This looks more related to Jetson Nano, we are moving this to the Jetson Nano forum to get better help.
Sure, Thank you.
Could you check if the below sample can meet your requirement?
I have already looked into this GitHub link from previous topics of Nvidia Developer Forum.
Here he deployed the model in TensorRT, but in my case I was not able to do the same with TensorRT (Error while working with trtexec to create an engine with onnx file)
Could you please guide me if there is any other approach or example that will help me proceed further?
Does your model work with ONNXRuntime?
If yes, you can replace the inference part with ONNXRuntime API for your use case.
The ONNXRuntime package can be found on our eLinux page below:
Thank you, I am still working on it and I will update you