Sherpa-onnx error

Robotics & Edge Computing Jetson & Embedded Systems Jetson Nano
1

I am getting below error while running Parakeet v3 600m model INT8.onnx files

what(): failed to load model with error: /media/nvidia/8c9249d6-0ce4-40a6-bd5a-0fad354db986/yxh/audio/onnxruntime/onnxruntime/core/graph/model_load_utils.h:57 void onnxruntime::model_load_utils::validateopsetfordomain(const std::unordered_map<std::__cxx11::basic_string, int>&, const onnxruntime::logging::logger&, bool, const string&, int)

Creating recognizer … terminate called after throwing an instance of ‘Ort::Exception’ what(): Failed to load model with error: /media/nvidia/8c9249d6-0ce4-40a6-bd5a-0fad354db986/yxh/audio/onnxruntime/onnxruntime/core/graph/model_load_utils.h:57 void onnxruntime::model_load_utils::ValidateOpsetForDomain(const std::unordered_map<std::__cxx11::basic_string, int>&, const onnxruntime::logging::Logger&, bool, const string&, int) ONNX Runtime only *guarantees* support for models stamped with official released onnx opset versions. Opset 17 is under development and support for this is limited. The operator schemas and or other functionality may change before next ONNX release and in this case ONNX Runtime will not guarantee backward compatibility. Current official support for domain ai.onnx is till opset 16. Aborted (core dumped)

3

Hi,

Based on the log, could you try to generate the ONNX model with opset 16 to see if it can work?

Thanks.

4

I tried, but getting same error. Is there any suitable working onnx runtime version available for jetson nano jetpack 4.6.6?

5

Hi,

As ONNXRuntime is a third-party library, please raise an issue to them to get more information.

Thanks.

6

problem is Parakeet v3 is transformer based model which is not supported on old GPU architecture of jetson nano

7

Hi,

You might need newer hardware if you want to deploy a recent model.
Thanks.