Hi @ashmadan01, you would need to implement a program (presumably either with the TensorRT Python or C++ API) that loads your ONNX model, performs any pre-processing of the audio, calls the TensorRT engine with it, and gets the maximum-likelihood output classification. Some of this is specific to the kind of model that Matlab exported, and the input/output layers that it expects. The image classification and object detection examples had to implement something similar underneath to support models like ResNet, SSD, YOLO, ect.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Is there any step-by-step python example of audio classification using nano? | 8 | 1933 | May 20, 2022 | |
| How to feed an Audio using the USB microphone on Jetson Nano to my trained model? | 7 | 729 | August 17, 2022 | |
| Inferring image classification model in Jetson nano | 2 | 836 | April 12, 2022 | |
| How to set up my own onnx model on jetson nano | 0 | 397 | June 23, 2020 | |
| Inference with jetson nano | 3 | 830 | June 14, 2022 | |
| Does Jetson Nano support scream detection using a usb microphone? If yes, what is the process to do so? | 6 | 574 | August 17, 2022 | |
| How can I use trained model from server and build it into applicaton using tensorrt | 9 | 829 | February 17, 2022 | |
| Model Performance Request | 3 | 295 | February 20, 2024 | |
| Jetson Nano - How to play sound when inference value reaches predefined value | 2 | 854 | October 15, 2021 | |
| How to inference Image Classification using Jetson NANO and CSI Camera for Custom CNN model | 5 | 1197 | May 17, 2022 |