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 1.24.3	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a16	Universal	QAIRT 2.43	Download
QNN_DLC	w8a8	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.19.1	Download
TFLITE	w8a8	Universal	QAIRT 2.43, TFLite 2.19.1	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	0.155 ms	0 - 24 MB	NPU
YamNet	ONNX	float	Snapdragon® X2 Elite	0.093 ms	8 - 8 MB	NPU
YamNet	ONNX	float	Snapdragon® X Elite	0.289 ms	8 - 8 MB	NPU
YamNet	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.172 ms	0 - 37 MB	NPU
YamNet	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.221 ms	0 - 10 MB	NPU
YamNet	ONNX	float	Qualcomm® QCS9075	0.29 ms	0 - 3 MB	NPU
YamNet	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.163 ms	0 - 25 MB	NPU
YamNet	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.103 ms	0 - 27 MB	NPU
YamNet	ONNX	w8a16	Snapdragon® X2 Elite	0.061 ms	0 - 0 MB	NPU
YamNet	ONNX	w8a16	Snapdragon® X Elite	0.208 ms	4 - 4 MB	NPU
YamNet	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	0.114 ms	0 - 39 MB	NPU
YamNet	ONNX	w8a16	Qualcomm® QCS6490	10.818 ms	16 - 20 MB	CPU
YamNet	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	0.13 ms	0 - 6 MB	NPU
YamNet	ONNX	w8a16	Qualcomm® QCS9075	0.217 ms	0 - 3 MB	NPU
YamNet	ONNX	w8a16	Qualcomm® QCM6690	4.686 ms	0 - 7 MB	CPU
YamNet	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.101 ms	0 - 22 MB	NPU
YamNet	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	3.396 ms	0 - 7 MB	CPU
YamNet	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.099 ms	0 - 27 MB	NPU
YamNet	ONNX	w8a8	Snapdragon® X2 Elite	0.073 ms	0 - 0 MB	NPU
YamNet	ONNX	w8a8	Snapdragon® X Elite	0.221 ms	4 - 4 MB	NPU
YamNet	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.111 ms	0 - 38 MB	NPU
YamNet	ONNX	w8a8	Qualcomm® QCS6490	1.614 ms	0 - 6 MB	CPU
YamNet	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.135 ms	0 - 14 MB	NPU
YamNet	ONNX	w8a8	Qualcomm® QCS9075	0.214 ms	0 - 3 MB	NPU
YamNet	ONNX	w8a8	Qualcomm® QCM6690	0.915 ms	0 - 7 MB	CPU
YamNet	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.096 ms	0 - 27 MB	NPU
YamNet	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	0.617 ms	0 - 7 MB	CPU
YamNet	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.141 ms	0 - 24 MB	NPU
YamNet	QNN_DLC	float	Snapdragon® X2 Elite	0.191 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	float	Snapdragon® X Elite	0.289 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.175 ms	0 - 36 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	0.674 ms	0 - 24 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.217 ms	0 - 1 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® SA8775P	0.364 ms	0 - 23 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® QCS9075	0.264 ms	0 - 2 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	0.36 ms	0 - 39 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® SA7255P	0.674 ms	0 - 24 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® SA8295P	0.557 ms	0 - 20 MB	NPU
YamNet	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.156 ms	0 - 21 MB	NPU
YamNet	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.102 ms	0 - 25 MB	NPU
YamNet	QNN_DLC	w8a16	Snapdragon® X2 Elite	0.177 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	w8a16	Snapdragon® X Elite	0.207 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	0.119 ms	0 - 35 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® QCS6490	0.622 ms	0 - 2 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	0.428 ms	0 - 25 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	0.143 ms	0 - 58 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® SA8775P	0.277 ms	0 - 24 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® QCS9075	0.188 ms	0 - 2 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® QCM6690	0.518 ms	0 - 22 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	0.213 ms	0 - 36 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® SA7255P	0.428 ms	0 - 25 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® SA8295P	0.429 ms	0 - 21 MB	NPU
YamNet	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.103 ms	0 - 26 MB	NPU
YamNet	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	0.17 ms	0 - 22 MB	NPU
YamNet	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.098 ms	0 - 25 MB	NPU
YamNet	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.152 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	w8a8	Snapdragon® X Elite	0.219 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.103 ms	0 - 35 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCS6490	0.624 ms	0 - 2 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	0.394 ms	0 - 24 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.136 ms	0 - 1 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® SA8775P	0.27 ms	0 - 24 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCS9075	0.184 ms	0 - 2 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCM6690	0.42 ms	0 - 22 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.206 ms	0 - 37 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® SA7255P	0.394 ms	0 - 24 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® SA8295P	0.414 ms	0 - 21 MB	NPU
YamNet	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.101 ms	0 - 26 MB	NPU
YamNet	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.168 ms	0 - 22 MB	NPU
YamNet	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.153 ms	0 - 30 MB	NPU
YamNet	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.186 ms	0 - 44 MB	NPU
YamNet	TFLITE	float	Qualcomm® QCS8275 (Proxy)	0.693 ms	0 - 29 MB	NPU
YamNet	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.217 ms	0 - 1 MB	NPU
YamNet	TFLITE	float	Qualcomm® SA8775P	0.386 ms	0 - 30 MB	NPU
YamNet	TFLITE	float	Qualcomm® QCS9075	0.27 ms	0 - 10 MB	NPU
YamNet	TFLITE	float	Qualcomm® QCS8450 (Proxy)	0.356 ms	0 - 46 MB	NPU
YamNet	TFLITE	float	Qualcomm® SA7255P	0.693 ms	0 - 29 MB	NPU
YamNet	TFLITE	float	Qualcomm® SA8295P	0.599 ms	0 - 27 MB	NPU
YamNet	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.155 ms	0 - 28 MB	NPU
YamNet	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.095 ms	0 - 25 MB	NPU
YamNet	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.115 ms	0 - 36 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCS6490	0.514 ms	0 - 6 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	0.417 ms	0 - 23 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.14 ms	0 - 2 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® SA8775P	0.295 ms	0 - 25 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCS9075	0.188 ms	0 - 6 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCM6690	0.43 ms	0 - 22 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.205 ms	0 - 37 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® SA7255P	0.417 ms	0 - 23 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® SA8295P	0.436 ms	0 - 21 MB	NPU
YamNet	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.101 ms	0 - 26 MB	NPU
YamNet	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.163 ms	0 - 22 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