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 1.24.1	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	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 2.17.0	Download
TFLITE	w8a8	Universal	QAIRT 2.43, TFLite 2.17.0	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® X2 Elite	0.092 ms	8 - 8 MB	NPU
YamNet	ONNX	float	Snapdragon® X Elite	0.274 ms	8 - 8 MB	NPU
YamNet	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.173 ms	0 - 38 MB	NPU
YamNet	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.22 ms	0 - 10 MB	NPU
YamNet	ONNX	float	Qualcomm® QCS9075	0.301 ms	0 - 3 MB	NPU
YamNet	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.152 ms	0 - 21 MB	NPU
YamNet	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.15 ms	0 - 25 MB	NPU
YamNet	ONNX	w8a16	Snapdragon® X2 Elite	0.062 ms	0 - 0 MB	NPU
YamNet	ONNX	w8a16	Snapdragon® X Elite	0.228 ms	4 - 4 MB	NPU
YamNet	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	0.115 ms	0 - 39 MB	NPU
YamNet	ONNX	w8a16	Qualcomm® QCS6490	10.025 ms	11 - 15 MB	CPU
YamNet	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	0.143 ms	0 - 2 MB	NPU
YamNet	ONNX	w8a16	Qualcomm® QCS9075	0.202 ms	0 - 3 MB	NPU
YamNet	ONNX	w8a16	Qualcomm® QCM6690	4.676 ms	1 - 8 MB	CPU
YamNet	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.106 ms	0 - 28 MB	NPU
YamNet	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	3.401 ms	0 - 7 MB	CPU
YamNet	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.105 ms	0 - 26 MB	NPU
YamNet	ONNX	w8a8	Snapdragon® X2 Elite	0.061 ms	0 - 0 MB	NPU
YamNet	ONNX	w8a8	Snapdragon® X Elite	0.219 ms	4 - 4 MB	NPU
YamNet	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.114 ms	0 - 38 MB	NPU
YamNet	ONNX	w8a8	Qualcomm® QCS6490	1.767 ms	0 - 6 MB	CPU
YamNet	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.14 ms	0 - 2 MB	NPU
YamNet	ONNX	w8a8	Qualcomm® QCS9075	0.215 ms	0 - 3 MB	NPU
YamNet	ONNX	w8a8	Qualcomm® QCM6690	0.888 ms	0 - 7 MB	CPU
YamNet	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.102 ms	0 - 22 MB	NPU
YamNet	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	0.625 ms	0 - 7 MB	CPU
YamNet	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.098 ms	0 - 27 MB	NPU
YamNet	QNN_DLC	float	Snapdragon® X2 Elite	0.187 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	float	Snapdragon® X Elite	0.284 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.17 ms	0 - 37 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	0.672 ms	0 - 21 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.211 ms	0 - 69 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® SA8775P	0.372 ms	0 - 23 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® QCS9075	0.263 ms	0 - 2 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	0.358 ms	0 - 38 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® SA7255P	0.672 ms	0 - 21 MB	NPU
YamNet	QNN_DLC	float	Qualcomm® SA8295P	0.539 ms	0 - 20 MB	NPU
YamNet	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.164 ms	0 - 25 MB	NPU
YamNet	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.153 ms	0 - 24 MB	NPU
YamNet	QNN_DLC	w8a16	Snapdragon® X2 Elite	0.156 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	w8a16	Snapdragon® X Elite	0.219 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	0.103 ms	0 - 35 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® QCS6490	0.607 ms	0 - 2 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	0.417 ms	0 - 23 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	0.128 ms	0 - 1 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	0.524 ms	0 - 22 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	0.212 ms	0 - 37 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® SA7255P	0.417 ms	0 - 23 MB	NPU
YamNet	QNN_DLC	w8a16	Qualcomm® SA8295P	0.427 ms	0 - 21 MB	NPU
YamNet	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.101 ms	0 - 21 MB	NPU
YamNet	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	0.178 ms	0 - 22 MB	NPU
YamNet	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.098 ms	0 - 25 MB	NPU
YamNet	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.164 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	w8a8	Snapdragon® X Elite	0.215 ms	0 - 0 MB	NPU
YamNet	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.109 ms	29 - 64 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCS6490	0.622 ms	0 - 2 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	0.395 ms	0 - 23 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.136 ms	0 - 57 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® SA8775P	0.277 ms	0 - 24 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCS9075	0.184 ms	2 - 4 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCM6690	0.431 ms	0 - 22 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.207 ms	0 - 37 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® SA7255P	0.395 ms	0 - 23 MB	NPU
YamNet	QNN_DLC	w8a8	Qualcomm® SA8295P	0.425 ms	0 - 21 MB	NPU
YamNet	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.096 ms	0 - 26 MB	NPU
YamNet	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.166 ms	0 - 22 MB	NPU
YamNet	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.085 ms	0 - 25 MB	NPU
YamNet	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.179 ms	0 - 44 MB	NPU
YamNet	TFLITE	float	Qualcomm® QCS8275 (Proxy)	0.712 ms	0 - 29 MB	NPU
YamNet	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.218 ms	0 - 1 MB	NPU
YamNet	TFLITE	float	Qualcomm® SA8775P	0.37 ms	0 - 30 MB	NPU
YamNet	TFLITE	float	Qualcomm® QCS9075	0.27 ms	0 - 10 MB	NPU
YamNet	TFLITE	float	Qualcomm® QCS8450 (Proxy)	0.354 ms	0 - 46 MB	NPU
YamNet	TFLITE	float	Qualcomm® SA7255P	0.712 ms	0 - 29 MB	NPU
YamNet	TFLITE	float	Qualcomm® SA8295P	0.597 ms	0 - 27 MB	NPU
YamNet	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.164 ms	0 - 28 MB	NPU
YamNet	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.153 ms	0 - 30 MB	NPU
YamNet	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.114 ms	0 - 35 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCS6490	0.543 ms	0 - 6 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	0.418 ms	0 - 22 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.138 ms	0 - 15 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® SA8775P	0.302 ms	0 - 24 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCS9075	0.188 ms	0 - 6 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCM6690	0.431 ms	0 - 21 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.207 ms	0 - 37 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® SA7255P	0.418 ms	0 - 22 MB	NPU
YamNet	TFLITE	w8a8	Qualcomm® SA8295P	0.436 ms	0 - 20 MB	NPU
YamNet	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.1 ms	0 - 22 MB	NPU
YamNet	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.167 ms	0 - 21 MB	NPU
YamNet	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.095 ms	0 - 24 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