YamNet: Optimized for Qualcomm Devices

An audio event classifier trained on the AudioSet dataset to predict audio events from the AudioSet ontology employing the Mobilenet_v1 depthwise-separable convolution architecture.

This is based on the implementation of YamNet found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime	Precision	Chipset	SDK Versions	Download
ONNX	float	Universal	QAIRT 2.42, ONNX Runtime 1.25.0	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.25.0	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.25.0	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
QNN_DLC	w8a16	Universal	QAIRT 2.45	Download
QNN_DLC	w8a8	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download
TFLITE	w8a8	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit YamNet on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

Custom weights (e.g., fine-tuned checkpoints)
Custom input shapes
Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for YamNet on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.audio_classification

Model Stats:

Model checkpoint: yamnet.pth
Input resolution: 1x1x96x64
Number of parameters: 3.73M
Model size (float): 14.2 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
YamNet	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.15 ms	0 - 25 MB	NPU
YamNet	ONNX	float	Snapdragon® X2 Elite	0.09 ms	212 - 212 MB	NPU
YamNet	ONNX	float	Snapdragon® X Elite	0.167 ms	181 - 181 MB	NPU
YamNet	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.177 ms	0 - 39 MB	NPU
YamNet	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.223 ms	0 - 107 MB	NPU
YamNet	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.157 ms	0 - 26 MB	NPU
YamNet	ONNX	float	Qualcomm® QCS9075	0.309 ms	0 - 53 MB	NPU
YamNet	ONNX	float	Qualcomm® QCS8750	0.157 ms	0 - 26 MB	NPU
YamNet	ONNX	float	Qualcomm® QCS7181	0.167 ms	181 - 181 MB	NPU
YamNet	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.09 ms	0 - 29 MB	NPU
YamNet	ONNX	w8a16	Snapdragon® X2 Elite	0.069 ms	212 - 212 MB	NPU
YamNet	ONNX	w8a16	Snapdragon® X Elite	0.1 ms	149 - 149 MB	NPU
YamNet	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	0.115 ms	0 - 40 MB	NPU
YamNet	ONNX	w8a16	Qualcomm® QCS6490	13.391 ms	11 - 15 MB	CPU
YamNet	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	0.138 ms	0 - 104 MB	NPU
YamNet	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	3.39 ms	0 - 7 MB	CPU
YamNet	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.108 ms	0 - 28 MB	NPU
YamNet	ONNX	w8a16	Qualcomm® QCM6690	4.657 ms	3 - 9 MB	CPU
YamNet	ONNX	w8a16	Qualcomm® QCS9075	0.221 ms	0 - 49 MB	NPU
YamNet	ONNX	w8a16	Qualcomm® QCS7790	3.39 ms	0 - 7 MB	CPU
YamNet	ONNX	w8a16	Qualcomm® QCS8750	0.108 ms	0 - 28 MB	NPU
YamNet	ONNX	w8a16	Qualcomm® QCS7181	0.1 ms	149 - 149 MB	NPU
YamNet	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.09 ms	0 - 28 MB	NPU
YamNet	ONNX	w8a8	Snapdragon® X2 Elite	0.058 ms	212 - 212 MB	NPU
YamNet	ONNX	w8a8	Snapdragon® X Elite	0.096 ms	149 - 149 MB	NPU
YamNet	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.115 ms	0 - 45 MB	NPU
YamNet	ONNX	w8a8	Qualcomm® QCS6490	1.618 ms	0 - 6 MB	CPU
YamNet	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.165 ms	0 - 48 MB	NPU
YamNet	ONNX	w8a8	Qualcomm® QCS9075	0.221 ms	0 - 49 MB	NPU
YamNet	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	0.616 ms	0 - 7 MB	CPU
YamNet	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.095 ms	0 - 24 MB	NPU
YamNet	ONNX	w8a8	Qualcomm® QCM6690	0.875 ms	0 - 7 MB	CPU
YamNet	ONNX	w8a8	Qualcomm® QCS7790	0.616 ms	0 - 7 MB	CPU
YamNet	ONNX	w8a8	Qualcomm® QCS8750	0.095 ms	0 - 24 MB	NPU
YamNet	ONNX	w8a8	Qualcomm® QCS7181	0.096 ms	149 - 149 MB	NPU
YamNet	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.14 ms	0 - 23 MB	NPU
YamNet	QNN_DLC	float	Snapdragon® X2 Elite	0.202 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	float	Snapdragon® X Elite	0.276 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.179 ms	0 - 36 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® QCS8275	0.662 ms	0 - 20 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.214 ms	0 - 2 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® SA8775P	0.361 ms	0 - 23 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® SA8650P	0.361 ms	0 - 23 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® SA8255P	0.361 ms	0 - 23 MB	NPU
YamNet	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.157 ms	0 - 24 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	0.352 ms	0 - 38 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® SA7255P	0.662 ms	0 - 20 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® QCS9075	0.261 ms	0 - 2 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® SA8295P	0.56 ms	0 - 19 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® QCS8750	0.157 ms	0 - 24 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® QCS7181	0.276 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.098 ms	0 - 27 MB	NPU
YamNet	QNN_DLC	w8a16	Snapdragon® X2 Elite	0.153 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	w8a16	Snapdragon® X Elite	0.202 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	0.116 ms	0 - 37 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® QCS6490	0.612 ms	0 - 2 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® QCS8275	0.434 ms	0 - 24 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	0.14 ms	0 - 1 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® SA8775P	0.271 ms	0 - 26 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® SA8650P	0.271 ms	0 - 26 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® SA8255P	0.271 ms	0 - 26 MB	NPU
YamNet	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	0.166 ms	0 - 23 MB	NPU
YamNet	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.096 ms	0 - 27 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® QCM6690	0.501 ms	0 - 25 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® SA7255P	0.434 ms	0 - 24 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® SA8295P	0.433 ms	0 - 22 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® QCS9075	0.185 ms	0 - 2 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	0.212 ms	0 - 37 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® QCS7790	0.166 ms	0 - 23 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® QCS8750	0.096 ms	0 - 27 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® QCS7181	0.202 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.091 ms	0 - 26 MB	NPU
YamNet	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.152 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	w8a8	Snapdragon® X Elite	0.195 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.113 ms	0 - 37 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCS6490	0.623 ms	2 - 4 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCS8275	0.393 ms	0 - 26 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.127 ms	0 - 6 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® SA8775P	0.268 ms	0 - 26 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® SA8650P	0.268 ms	0 - 26 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® SA8255P	0.268 ms	0 - 26 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCS9075	0.184 ms	0 - 2 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.206 ms	0 - 37 MB	NPU
YamNet	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.166 ms	0 - 24 MB	NPU
YamNet	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.088 ms	0 - 23 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCM6690	0.438 ms	0 - 24 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® SA8295P	0.425 ms	0 - 22 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® SA7255P	0.393 ms	0 - 26 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCS7790	0.166 ms	0 - 24 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCS8750	0.088 ms	0 - 23 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCS7181	0.195 ms	0 - 0 MB	NPU
YamNet	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.15 ms	0 - 29 MB	NPU
YamNet	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.175 ms	0 - 43 MB	NPU
YamNet	TFLITE	float	Qualcomm® QCS8275	0.698 ms	0 - 27 MB	NPU
YamNet	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.218 ms	0 - 4 MB	NPU
YamNet	TFLITE	float	Qualcomm® SA8775P	0.374 ms	0 - 29 MB	NPU
YamNet	TFLITE	float	Qualcomm® SA8650P	0.374 ms	0 - 29 MB	NPU
YamNet	TFLITE	float	Qualcomm® SA8255P	0.374 ms	0 - 29 MB	NPU
YamNet	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.156 ms	0 - 26 MB	NPU
YamNet	TFLITE	float	Qualcomm® QCS8450 (Proxy)	0.352 ms	0 - 44 MB	NPU
YamNet	TFLITE	float	Qualcomm® SA7255P	0.698 ms	0 - 27 MB	NPU
YamNet	TFLITE	float	Qualcomm® QCS9075	0.274 ms	0 - 10 MB	NPU
YamNet	TFLITE	float	Qualcomm® SA8295P	0.59 ms	0 - 25 MB	NPU
YamNet	TFLITE	float	Qualcomm® QCS8750	0.156 ms	0 - 26 MB	NPU
YamNet	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.091 ms	0 - 25 MB	NPU
YamNet	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.103 ms	0 - 36 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCS6490	0.572 ms	0 - 6 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCS8275	0.41 ms	0 - 23 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.138 ms	0 - 1 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® SA8775P	0.29 ms	0 - 25 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® SA8650P	0.29 ms	0 - 25 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® SA8255P	0.29 ms	0 - 25 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCS9075	0.19 ms	0 - 6 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.205 ms	0 - 37 MB	NPU
YamNet	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.167 ms	0 - 22 MB	NPU
YamNet	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.102 ms	0 - 27 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCM6690	0.434 ms	0 - 22 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® SA8295P	0.425 ms	0 - 21 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® SA7255P	0.41 ms	0 - 23 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCS7790	0.167 ms	0 - 22 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCS8750	0.102 ms	0 - 27 MB	NPU

License

The license for the original implementation of YamNet can be found here.

References

Community

Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
For questions or feedback please reach out to us.

Downloads last month: -; Downloads are not tracked for this model. How to track

Paper for qualcomm/YamNet

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

Paper • 1704.04861 • Published Apr 17, 2017 • 1