TrOCR: Optimized for Qualcomm Devices

End-to-end text recognition approach with pre-trained image transformer and text transformer models for both image understanding and wordpiece-level text generation.

This is based on the implementation of TrOCR 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
QNN_DLC	float	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit TrOCR 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 TrOCR on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_to_text

Model Stats:

Model checkpoint: trocr-small-stage1
Input resolution: 320x320
Number of parameters (decoder): 38.3M
Model size (decoder) (float): 146 MB
Number of parameters (encoder): 23.0M
Model size (encoder) (float): 87.8 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
decoder	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	1.142 ms	1 - 220 MB	NPU
decoder	ONNX	float	Snapdragon® 8 Elite Mobile	1.25 ms	0 - 218 MB	NPU
decoder	ONNX	float	Snapdragon® X2 Elite	1.157 ms	68 - 68 MB	NPU
decoder	ONNX	float	Snapdragon® X Elite	2.232 ms	67 - 67 MB	NPU
decoder	ONNX	float	Snapdragon® X Elite	2.232 ms	67 - 67 MB	NPU
decoder	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.435 ms	0 - 247 MB	NPU
decoder	ONNX	float	Qualcomm® QCS8550 (Proxy)	2.101 ms	0 - 74 MB	NPU
decoder	ONNX	float	Qualcomm® QCS9075	2.739 ms	7 - 16 MB	NPU
decoder	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.25 ms	0 - 218 MB	NPU
decoder	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.137 ms	1 - 172 MB	NPU
decoder	QNN_DLC	float	Snapdragon® 8 Elite Mobile	1.249 ms	0 - 187 MB	NPU
decoder	QNN_DLC	float	Snapdragon® X2 Elite	1.63 ms	7 - 7 MB	NPU
decoder	QNN_DLC	float	Snapdragon® X Elite	2.172 ms	7 - 7 MB	NPU
decoder	QNN_DLC	float	Snapdragon® X Elite	2.172 ms	7 - 7 MB	NPU
decoder	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.358 ms	0 - 275 MB	NPU
decoder	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	4.119 ms	7 - 105 MB	NPU
decoder	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	1.989 ms	1 - 3 MB	NPU
decoder	QNN_DLC	float	Qualcomm® SA8775P	2.854 ms	7 - 106 MB	NPU
decoder	QNN_DLC	float	Qualcomm® SA8775P	2.854 ms	7 - 106 MB	NPU
decoder	QNN_DLC	float	Qualcomm® SA8775P	2.854 ms	7 - 106 MB	NPU
decoder	QNN_DLC	float	Qualcomm® QCS9075	2.557 ms	7 - 15 MB	NPU
decoder	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	2.703 ms	3 - 219 MB	NPU
decoder	QNN_DLC	float	Qualcomm® SA7255P	4.119 ms	7 - 105 MB	NPU
decoder	QNN_DLC	float	Qualcomm® SA8295P	2.663 ms	0 - 49 MB	NPU
decoder	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.249 ms	0 - 187 MB	NPU
decoder	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.116 ms	0 - 175 MB	NPU
decoder	TFLITE	float	Snapdragon® 8 Elite Mobile	1.214 ms	0 - 190 MB	NPU
decoder	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.404 ms	0 - 281 MB	NPU
decoder	TFLITE	float	Qualcomm® QCS8275 (Proxy)	4.202 ms	0 - 103 MB	NPU
decoder	TFLITE	float	Qualcomm® QCS8550 (Proxy)	2.042 ms	0 - 2 MB	NPU
decoder	TFLITE	float	Qualcomm® SA8775P	2.876 ms	0 - 102 MB	NPU
decoder	TFLITE	float	Qualcomm® SA8775P	2.876 ms	0 - 102 MB	NPU
decoder	TFLITE	float	Qualcomm® SA8775P	2.876 ms	0 - 102 MB	NPU
decoder	TFLITE	float	Qualcomm® QCS9075	2.594 ms	0 - 83 MB	NPU
decoder	TFLITE	float	Qualcomm® QCS8450 (Proxy)	2.459 ms	0 - 217 MB	NPU
decoder	TFLITE	float	Qualcomm® SA7255P	4.202 ms	0 - 103 MB	NPU
decoder	TFLITE	float	Qualcomm® SA8295P	2.669 ms	0 - 43 MB	NPU
decoder	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.214 ms	0 - 190 MB	NPU
encoder	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	4.156 ms	1 - 150 MB	NPU
encoder	ONNX	float	Snapdragon® 8 Elite Mobile	5.278 ms	16 - 166 MB	NPU
encoder	ONNX	float	Snapdragon® X2 Elite	4.579 ms	48 - 48 MB	NPU
encoder	ONNX	float	Snapdragon® X Elite	11.423 ms	47 - 47 MB	NPU
encoder	ONNX	float	Snapdragon® X Elite	11.423 ms	47 - 47 MB	NPU
encoder	ONNX	float	Snapdragon® 8 Gen 3 Mobile	7.824 ms	16 - 234 MB	NPU
encoder	ONNX	float	Qualcomm® QCS8550 (Proxy)	10.913 ms	0 - 60 MB	NPU
encoder	ONNX	float	Qualcomm® QCS9075	14.132 ms	15 - 19 MB	NPU
encoder	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	5.278 ms	16 - 166 MB	NPU
encoder	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	4.312 ms	1 - 115 MB	NPU
encoder	QNN_DLC	float	Snapdragon® 8 Elite Mobile	5.46 ms	2 - 113 MB	NPU
encoder	QNN_DLC	float	Snapdragon® X2 Elite	5.176 ms	2 - 2 MB	NPU
encoder	QNN_DLC	float	Snapdragon® X Elite	12.007 ms	2 - 2 MB	NPU
encoder	QNN_DLC	float	Snapdragon® X Elite	12.007 ms	2 - 2 MB	NPU
encoder	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	8.005 ms	0 - 192 MB	NPU
encoder	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	37.042 ms	2 - 107 MB	NPU
encoder	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	11.31 ms	2 - 4 MB	NPU
encoder	QNN_DLC	float	Qualcomm® SA8775P	13.979 ms	2 - 108 MB	NPU
encoder	QNN_DLC	float	Qualcomm® SA8775P	13.979 ms	2 - 108 MB	NPU
encoder	QNN_DLC	float	Qualcomm® SA8775P	13.979 ms	2 - 108 MB	NPU
encoder	QNN_DLC	float	Qualcomm® QCS9075	15.257 ms	2 - 12 MB	NPU
encoder	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	19.596 ms	0 - 306 MB	NPU
encoder	QNN_DLC	float	Qualcomm® SA7255P	37.042 ms	2 - 107 MB	NPU
encoder	QNN_DLC	float	Qualcomm® SA8295P	19.704 ms	2 - 232 MB	NPU
encoder	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	5.46 ms	2 - 113 MB	NPU
encoder	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	4.074 ms	0 - 110 MB	NPU
encoder	TFLITE	float	Snapdragon® 8 Elite Mobile	5.205 ms	6 - 118 MB	NPU
encoder	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	7.714 ms	7 - 198 MB	NPU
encoder	TFLITE	float	Qualcomm® QCS8275 (Proxy)	36.817 ms	7 - 120 MB	NPU
encoder	TFLITE	float	Qualcomm® QCS8550 (Proxy)	10.695 ms	7 - 9 MB	NPU
encoder	TFLITE	float	Qualcomm® SA8775P	13.51 ms	7 - 111 MB	NPU
encoder	TFLITE	float	Qualcomm® SA8775P	13.51 ms	7 - 111 MB	NPU
encoder	TFLITE	float	Qualcomm® SA8775P	13.51 ms	7 - 111 MB	NPU
encoder	TFLITE	float	Qualcomm® QCS9075	13.937 ms	6 - 65 MB	NPU
encoder	TFLITE	float	Qualcomm® QCS8450 (Proxy)	19.779 ms	7 - 311 MB	NPU
encoder	TFLITE	float	Qualcomm® SA7255P	36.817 ms	7 - 120 MB	NPU
encoder	TFLITE	float	Qualcomm® SA8295P	19.074 ms	8 - 236 MB	NPU
encoder	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	5.205 ms	6 - 118 MB	NPU

License

The license for the original implementation of TrOCR 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

Space using qualcomm/TrOCR 1

Paper for qualcomm/TrOCR

TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models

Paper • 2109.10282 • Published Sep 21, 2021 • 13