I have a trained SVM model and LSTM model saved in .h5 and .pb format for scream detection and I want to know how should I make my model run on Jetson Nano.
I have also setup the Jetson Nano with all the installations.
Please guide me on how to proceed further.
Does Jetson Nano support scream detection using a usb microphone? If yes, what is the process to do so?
There is an audio inference example in our Deepstream SDK.
Could you check if it can meet your requirement?
I have checked the example and tried the Deepstream SDK, but was not able to accomplish the requirement.
Could you please guide me with some other way to approach the scream detection using a usb microphone on jetson nano?
This Deepstream sdk is not related to my project.
I want to ask another question, 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!
Could you check the below sample instead?
It supports inference with a live microphone.
Sure, Thank you! I am still working on it and will update you on it