EasyOCR / README.md

v0.60.0

9a1bbfe verified 1 day ago

17.5 kB

	---
	library_name: pytorch
	license: other
	tags:
	- android
	pipeline_tag: image-to-text

	---

	![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/easyocr/web-assets/model_demo.png)

	# EasyOCR: Optimized for Qualcomm Devices

	EasyOCR is a machine learning model that can recognize text in images. It supports 80+ supported languages and all popular writing scripts.

	This is based on the implementation of EasyOCR found [here](https://github.com/JaidedAI/EasyOCR).
	This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/easyocr) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).

	Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) 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 2.45, ONNX Runtime 1.27.1 \| [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/easyocr/releases/v0.60.0/easyocr-onnx-float.zip)
	\| ONNX \| w8a8 \| Universal \| QAIRT 2.45, ONNX Runtime 1.27.1 \| [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/easyocr/releases/v0.60.0/easyocr-onnx-w8a8.zip)
	\| QNN_DLC \| float \| Universal \| QAIRT 2.45 \| [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/easyocr/releases/v0.60.0/easyocr-qnn_dlc-float.zip)
	\| TFLITE \| float \| Universal \| QAIRT 2.45 \| [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/easyocr/releases/v0.60.0/easyocr-tflite-float.zip)
	\| TFLITE \| w8a8 \| Universal \| QAIRT 2.45 \| [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/easyocr/releases/v0.60.0/easyocr-tflite-w8a8.zip)

	For more device-specific assets and performance metrics, visit [EasyOCR on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/easyocr).


	### Option 2: Export with Custom Configurations

	Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/easyocr) 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 [EasyOCR on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/easyocr) for usage instructions.

	## Model Details

	Model Type: Model_use_case.image_to_text

	Model Stats:
	- Input resolution: 608x800
	- Model checkpoint: easyocr-small-stage1
	- Model size (detector) (float): 79.2 MB
	- Model size (recognizer) (float): 14.7 MB
	- Number of parameters (detector): 20.8M
	- Number of parameters (recognizer): 3.84M

	## Performance Summary
	\| Model \| Runtime \| Precision \| Chipset \| Inference Time (ms) \| Peak Memory Range (MB) \| Primary Compute Unit
	\|---\|---\|---\|---\|---\|---\|---
	\| detector \| ONNX \| float \| Snapdragon® X2 Elite \| 19.976 ms \| 9 - 9 MB \| NPU
	\| detector \| ONNX \| float \| Snapdragon® X Elite \| 38.178 ms \| 36 - 36 MB \| NPU
	\| detector \| ONNX \| float \| Snapdragon® 8 Gen 3 Mobile \| 27.935 ms \| 1 - 232 MB \| NPU
	\| detector \| ONNX \| float \| Snapdragon® 8 Gen 1 Mobile \| 79.566 ms \| 8 - 248 MB \| NPU
	\| detector \| ONNX \| float \| Qualcomm® Dragonwing™ IQ-8275 \| 78.009 ms \| 6 - 15 MB \| NPU
	\| detector \| ONNX \| float \| Qualcomm® Dragonwing™ QCS8550 (Proxy) \| 37.906 ms \| 0 - 203 MB \| NPU
	\| detector \| ONNX \| float \| Qualcomm® QCS8450 \| 79.566 ms \| 8 - 248 MB \| NPU
	\| detector \| ONNX \| float \| Qualcomm® Dragonwing™ IQ-9075 \| 68.484 ms \| 5 - 14 MB \| NPU
	\| detector \| ONNX \| float \| Qualcomm® Dragonwing™ IQ-X7181 \| 38.178 ms \| 36 - 36 MB \| NPU
	\| detector \| ONNX \| float \| Qualcomm® Dragonwing™ Q-8750 \| 22.411 ms \| 3 - 168 MB \| NPU
	\| detector \| ONNX \| float \| Snapdragon® 8 Elite Mobile \| 22.411 ms \| 3 - 168 MB \| NPU
	\| detector \| ONNX \| float \| Snapdragon® 8 Elite Gen 5 Mobile \| 16.399 ms \| 3 - 171 MB \| NPU
	\| detector \| ONNX \| w8a8 \| Snapdragon® X2 Elite \| 6.731 ms \| 1 - 1 MB \| NPU
	\| detector \| ONNX \| w8a8 \| Snapdragon® X Elite \| 13.422 ms \| 20 - 20 MB \| NPU
	\| detector \| ONNX \| w8a8 \| Snapdragon® 8 Gen 3 Mobile \| 9.733 ms \| 2 - 215 MB \| NPU
	\| detector \| ONNX \| w8a8 \| Snapdragon® 8 Gen 1 Mobile \| 19.997 ms \| 2 - 215 MB \| NPU
	\| detector \| ONNX \| w8a8 \| Qualcomm® Dragonwing™ IQ-8275 \| 15.232 ms \| 1 - 5 MB \| NPU
	\| detector \| ONNX \| w8a8 \| Qualcomm® Dragonwing™ QCS8550 (Proxy) \| 13.005 ms \| 0 - 56 MB \| NPU
	\| detector \| ONNX \| w8a8 \| Qualcomm® QCS8450 \| 19.997 ms \| 2 - 215 MB \| NPU
	\| detector \| ONNX \| w8a8 \| Qualcomm® Dragonwing™ IQ-9075 \| 14.013 ms \| 1 - 4 MB \| NPU
	\| detector \| ONNX \| w8a8 \| Qualcomm® Dragonwing™ IQ-X7181 \| 13.422 ms \| 20 - 20 MB \| NPU
	\| detector \| ONNX \| w8a8 \| Qualcomm® Dragonwing™ Q-8750 \| 7.853 ms \| 2 - 165 MB \| NPU
	\| detector \| ONNX \| w8a8 \| Snapdragon® 8 Elite Mobile \| 7.853 ms \| 2 - 165 MB \| NPU
	\| detector \| ONNX \| w8a8 \| Snapdragon® 8 Elite Gen 5 Mobile \| 5.478 ms \| 0 - 165 MB \| NPU
	\| detector \| QNN_DLC \| float \| Snapdragon® X2 Elite \| 30.948 ms \| 6 - 6 MB \| NPU
	\| detector \| QNN_DLC \| float \| Snapdragon® X Elite \| 39.468 ms \| 6 - 6 MB \| NPU
	\| detector \| QNN_DLC \| float \| Snapdragon® 8 Gen 3 Mobile \| 28.153 ms \| 6 - 236 MB \| NPU
	\| detector \| QNN_DLC \| float \| Snapdragon® 8 Gen 1 Mobile \| 80.416 ms \| 6 - 260 MB \| NPU
	\| detector \| QNN_DLC \| float \| Qualcomm® Dragonwing™ IQ-8275 \| 76.834 ms \| 6 - 14 MB \| NPU
	\| detector \| QNN_DLC \| float \| Qualcomm® Dragonwing™ IQ-8275 \| 269.343 ms \| 1 - 170 MB \| NPU
	\| detector \| QNN_DLC \| float \| Qualcomm® Dragonwing™ QCS8550 (Proxy) \| 38.182 ms \| 6 - 8 MB \| NPU
	\| detector \| QNN_DLC \| float \| Qualcomm® SA8775P \| 67.972 ms \| 1 - 171 MB \| NPU
	\| detector \| QNN_DLC \| float \| Qualcomm® SA8650P \| 67.972 ms \| 1 - 171 MB \| NPU
	\| detector \| QNN_DLC \| float \| Qualcomm® SA8255P \| 67.972 ms \| 1 - 171 MB \| NPU
	\| detector \| QNN_DLC \| float \| Qualcomm® QCS8450 \| 80.416 ms \| 6 - 260 MB \| NPU
	\| detector \| QNN_DLC \| float \| Qualcomm® Dragonwing™ IQ-9075 \| 67.95 ms \| 6 - 14 MB \| NPU
	\| detector \| QNN_DLC \| float \| Qualcomm® Dragonwing™ IQ-X7181 \| 39.468 ms \| 6 - 6 MB \| NPU
	\| detector \| QNN_DLC \| float \| Qualcomm® Dragonwing™ Q-8750 \| 22.007 ms \| 6 - 171 MB \| NPU
	\| detector \| QNN_DLC \| float \| Qualcomm® SA7255P \| 269.343 ms \| 1 - 170 MB \| NPU
	\| detector \| QNN_DLC \| float \| Qualcomm® SA8295P \| 77.658 ms \| 0 - 184 MB \| NPU
	\| detector \| QNN_DLC \| float \| Snapdragon® 8 Elite Mobile \| 22.007 ms \| 6 - 171 MB \| NPU
	\| detector \| QNN_DLC \| float \| Snapdragon® 8 Elite Gen 5 Mobile \| 16.862 ms \| 6 - 182 MB \| NPU
	\| detector \| TFLITE \| float \| Snapdragon® 8 Gen 3 Mobile \| 28.083 ms \| 1 - 261 MB \| NPU
	\| detector \| TFLITE \| float \| Snapdragon® 8 Gen 1 Mobile \| 80.455 ms \| 1 - 284 MB \| NPU
	\| detector \| TFLITE \| float \| Qualcomm® Dragonwing™ IQ-8275 \| 76.816 ms \| 0 - 49 MB \| NPU
	\| detector \| TFLITE \| float \| Qualcomm® Dragonwing™ IQ-8275 \| 269.45 ms \| 1 - 175 MB \| NPU
	\| detector \| TFLITE \| float \| Qualcomm® Dragonwing™ QCS8550 (Proxy) \| 38.372 ms \| 1 - 3 MB \| NPU
	\| detector \| TFLITE \| float \| Qualcomm® SA8775P \| 68.005 ms \| 1 - 175 MB \| NPU
	\| detector \| TFLITE \| float \| Qualcomm® SA8650P \| 68.005 ms \| 1 - 175 MB \| NPU
	\| detector \| TFLITE \| float \| Qualcomm® SA8255P \| 68.005 ms \| 1 - 175 MB \| NPU
	\| detector \| TFLITE \| float \| Qualcomm® QCS8450 \| 80.455 ms \| 1 - 284 MB \| NPU
	\| detector \| TFLITE \| float \| Qualcomm® Dragonwing™ IQ-9075 \| 68.73 ms \| 0 - 49 MB \| NPU
	\| detector \| TFLITE \| float \| Qualcomm® Dragonwing™ Q-8750 \| 21.953 ms \| 1 - 171 MB \| NPU
	\| detector \| TFLITE \| float \| Qualcomm® SA7255P \| 269.45 ms \| 1 - 175 MB \| NPU
	\| detector \| TFLITE \| float \| Qualcomm® SA8295P \| 73.891 ms \| 1 - 186 MB \| NPU
	\| detector \| TFLITE \| float \| Snapdragon® 8 Elite Mobile \| 21.953 ms \| 1 - 171 MB \| NPU
	\| detector \| TFLITE \| float \| Snapdragon® 8 Elite Gen 5 Mobile \| 16.87 ms \| 1 - 181 MB \| NPU
	\| detector \| TFLITE \| w8a8 \| Snapdragon® 8 Gen 3 Mobile \| 7.182 ms \| 0 - 211 MB \| NPU
	\| detector \| TFLITE \| w8a8 \| Snapdragon® 8 Gen 1 Mobile \| 14.795 ms \| 0 - 210 MB \| NPU
	\| detector \| TFLITE \| w8a8 \| Qualcomm® Dragonwing™ QCS6490 \| 61.238 ms \| 0 - 24 MB \| NPU
	\| detector \| TFLITE \| w8a8 \| Qualcomm® Dragonwing™ IQ-8275 \| 11.107 ms \| 0 - 25 MB \| NPU
	\| detector \| TFLITE \| w8a8 \| Qualcomm® Dragonwing™ IQ-8275 \| 35.795 ms \| 0 - 155 MB \| NPU
	\| detector \| TFLITE \| w8a8 \| Qualcomm® Dragonwing™ QCS8550 (Proxy) \| 9.526 ms \| 0 - 3 MB \| NPU
	\| detector \| TFLITE \| w8a8 \| Qualcomm® SA8775P \| 10.091 ms \| 0 - 156 MB \| NPU
	\| detector \| TFLITE \| w8a8 \| Qualcomm® SA8650P \| 10.091 ms \| 0 - 156 MB \| NPU
	\| detector \| TFLITE \| w8a8 \| Qualcomm® SA8255P \| 10.091 ms \| 0 - 156 MB \| NPU
	\| detector \| TFLITE \| w8a8 \| Qualcomm® QCS8450 \| 14.795 ms \| 0 - 210 MB \| NPU
	\| detector \| TFLITE \| w8a8 \| Qualcomm® Dragonwing™ IQ-9075 \| 9.803 ms \| 0 - 24 MB \| NPU
	\| detector \| TFLITE \| w8a8 \| Qualcomm® Dragonwing™ Q-6690 \| 251.313 ms \| 0 - 208 MB \| NPU
	\| detector \| TFLITE \| w8a8 \| Qualcomm® Dragonwing™ Q-7790 \| 18.662 ms \| 0 - 173 MB \| NPU
	\| detector \| TFLITE \| w8a8 \| Qualcomm® Dragonwing™ Q-8750 \| 5.791 ms \| 0 - 159 MB \| NPU
	\| detector \| TFLITE \| w8a8 \| Qualcomm® SA7255P \| 35.795 ms \| 0 - 155 MB \| NPU
	\| detector \| TFLITE \| w8a8 \| Qualcomm® SA8295P \| 19.019 ms \| 0 - 152 MB \| NPU
	\| detector \| TFLITE \| w8a8 \| Snapdragon® 8 Elite Mobile \| 5.791 ms \| 0 - 159 MB \| NPU
	\| detector \| TFLITE \| w8a8 \| Snapdragon® 8 Elite Gen 5 Mobile \| 4.54 ms \| 0 - 162 MB \| NPU
	\| detector \| TFLITE \| w8a8 \| Snapdragon® 7 Gen 4 Mobile \| 18.662 ms \| 0 - 173 MB \| NPU
	\| recognizer \| ONNX \| float \| Snapdragon® X2 Elite \| 12.833 ms \| 1 - 1 MB \| NPU
	\| recognizer \| ONNX \| float \| Snapdragon® X Elite \| 20.103 ms \| 11 - 11 MB \| NPU
	\| recognizer \| ONNX \| float \| Snapdragon® 8 Gen 3 Mobile \| 16.417 ms \| 0 - 780 MB \| NPU
	\| recognizer \| ONNX \| float \| Snapdragon® 8 Gen 1 Mobile \| 27.901 ms \| 1 - 346 MB \| NPU
	\| recognizer \| ONNX \| float \| Qualcomm® Dragonwing™ IQ-8275 \| 23.126 ms \| 0 - 4 MB \| NPU
	\| recognizer \| ONNX \| float \| Qualcomm® Dragonwing™ QCS8550 (Proxy) \| 21.942 ms \| 0 - 15 MB \| NPU
	\| recognizer \| ONNX \| float \| Qualcomm® QCS8450 \| 27.901 ms \| 1 - 346 MB \| NPU
	\| recognizer \| ONNX \| float \| Qualcomm® Dragonwing™ IQ-9075 \| 24.316 ms \| 0 - 3 MB \| NPU
	\| recognizer \| ONNX \| float \| Qualcomm® Dragonwing™ IQ-X7181 \| 20.103 ms \| 11 - 11 MB \| NPU
	\| recognizer \| ONNX \| float \| Qualcomm® Dragonwing™ Q-8750 \| 12.16 ms \| 0 - 660 MB \| NPU
	\| recognizer \| ONNX \| float \| Snapdragon® 8 Elite Mobile \| 12.16 ms \| 0 - 660 MB \| NPU
	\| recognizer \| ONNX \| float \| Snapdragon® 8 Elite Gen 5 Mobile \| 11.698 ms \| 0 - 788 MB \| NPU
	\| recognizer \| ONNX \| w8a8 \| Snapdragon® X2 Elite \| 9.111 ms \| 1 - 1 MB \| NPU
	\| recognizer \| ONNX \| w8a8 \| Snapdragon® X Elite \| 10.557 ms \| 10 - 10 MB \| NPU
	\| recognizer \| ONNX \| w8a8 \| Snapdragon® 8 Gen 3 Mobile \| 7.981 ms \| 0 - 803 MB \| NPU
	\| recognizer \| ONNX \| w8a8 \| Snapdragon® 8 Gen 1 Mobile \| 15.601 ms \| 0 - 352 MB \| NPU
	\| recognizer \| ONNX \| w8a8 \| Qualcomm® Dragonwing™ IQ-8275 \| 12.023 ms \| 0 - 4 MB \| NPU
	\| recognizer \| ONNX \| w8a8 \| Qualcomm® Dragonwing™ QCS8550 (Proxy) \| 10.592 ms \| 0 - 296 MB \| NPU
	\| recognizer \| ONNX \| w8a8 \| Qualcomm® QCS8450 \| 15.601 ms \| 0 - 352 MB \| NPU
	\| recognizer \| ONNX \| w8a8 \| Qualcomm® Dragonwing™ IQ-9075 \| 11.918 ms \| 0 - 3 MB \| NPU
	\| recognizer \| ONNX \| w8a8 \| Qualcomm® Dragonwing™ IQ-X7181 \| 10.557 ms \| 10 - 10 MB \| NPU
	\| recognizer \| ONNX \| w8a8 \| Qualcomm® Dragonwing™ Q-8750 \| 7.54 ms \| 0 - 664 MB \| NPU
	\| recognizer \| ONNX \| w8a8 \| Snapdragon® 8 Elite Mobile \| 7.54 ms \| 0 - 664 MB \| NPU
	\| recognizer \| ONNX \| w8a8 \| Snapdragon® 8 Elite Gen 5 Mobile \| 8.17 ms \| 0 - 808 MB \| NPU
	\| recognizer \| QNN_DLC \| float \| Snapdragon® X2 Elite \| 12.915 ms \| 0 - 0 MB \| NPU
	\| recognizer \| QNN_DLC \| float \| Snapdragon® X Elite \| 20.763 ms \| 0 - 0 MB \| NPU
	\| recognizer \| QNN_DLC \| float \| Snapdragon® 8 Gen 3 Mobile \| 16.942 ms \| 0 - 859 MB \| NPU
	\| recognizer \| QNN_DLC \| float \| Snapdragon® 8 Gen 1 Mobile \| 28.841 ms \| 0 - 411 MB \| NPU
	\| recognizer \| QNN_DLC \| float \| Qualcomm® Dragonwing™ IQ-8275 \| 23.725 ms \| 0 - 3 MB \| NPU
	\| recognizer \| QNN_DLC \| float \| Qualcomm® Dragonwing™ IQ-8275 \| 57.668 ms \| 0 - 696 MB \| NPU
	\| recognizer \| QNN_DLC \| float \| Qualcomm® Dragonwing™ QCS8550 (Proxy) \| 22.193 ms \| 0 - 105 MB \| NPU
	\| recognizer \| QNN_DLC \| float \| Qualcomm® SA8775P \| 25.78 ms \| 0 - 703 MB \| NPU
	\| recognizer \| QNN_DLC \| float \| Qualcomm® SA8650P \| 25.78 ms \| 0 - 703 MB \| NPU
	\| recognizer \| QNN_DLC \| float \| Qualcomm® SA8255P \| 25.78 ms \| 0 - 703 MB \| NPU
	\| recognizer \| QNN_DLC \| float \| Qualcomm® QCS8450 \| 28.841 ms \| 0 - 411 MB \| NPU
	\| recognizer \| QNN_DLC \| float \| Qualcomm® Dragonwing™ IQ-9075 \| 24.868 ms \| 2 - 4 MB \| NPU
	\| recognizer \| QNN_DLC \| float \| Qualcomm® Dragonwing™ IQ-X7181 \| 20.763 ms \| 0 - 0 MB \| NPU
	\| recognizer \| QNN_DLC \| float \| Qualcomm® Dragonwing™ Q-8750 \| 12.095 ms \| 0 - 705 MB \| NPU
	\| recognizer \| QNN_DLC \| float \| Qualcomm® SA7255P \| 57.668 ms \| 0 - 696 MB \| NPU
	\| recognizer \| QNN_DLC \| float \| Qualcomm® SA8295P \| 31.789 ms \| 0 - 340 MB \| NPU
	\| recognizer \| QNN_DLC \| float \| Snapdragon® 8 Elite Mobile \| 12.095 ms \| 0 - 705 MB \| NPU
	\| recognizer \| QNN_DLC \| float \| Snapdragon® 8 Elite Gen 5 Mobile \| 11.432 ms \| 0 - 727 MB \| NPU
	\| recognizer \| TFLITE \| float \| Snapdragon® 8 Gen 3 Mobile \| 55.202 ms \| 7 - 15 MB \| CPU
	\| recognizer \| TFLITE \| float \| Snapdragon® 8 Gen 1 Mobile \| 87.592 ms \| 7 - 21 MB \| CPU
	\| recognizer \| TFLITE \| float \| Qualcomm® Dragonwing™ IQ-8275 \| 339.33 ms \| 5 - 34 MB \| CPU
	\| recognizer \| TFLITE \| float \| Qualcomm® Dragonwing™ IQ-8275 \| 174.222 ms \| 6 - 16 MB \| CPU
	\| recognizer \| TFLITE \| float \| Qualcomm® Dragonwing™ QCS8550 (Proxy) \| 77.577 ms \| 3 - 45 MB \| CPU
	\| recognizer \| TFLITE \| float \| Qualcomm® SA8775P \| 99.618 ms \| 8 - 14 MB \| CPU
	\| recognizer \| TFLITE \| float \| Qualcomm® SA8650P \| 99.618 ms \| 8 - 14 MB \| CPU
	\| recognizer \| TFLITE \| float \| Qualcomm® SA8255P \| 99.618 ms \| 8 - 14 MB \| CPU
	\| recognizer \| TFLITE \| float \| Qualcomm® QCS8450 \| 87.592 ms \| 7 - 21 MB \| CPU
	\| recognizer \| TFLITE \| float \| Qualcomm® Dragonwing™ IQ-9075 \| 132.194 ms \| 4 - 33 MB \| CPU
	\| recognizer \| TFLITE \| float \| Qualcomm® Dragonwing™ Q-8750 \| 45.439 ms \| 7 - 17 MB \| CPU
	\| recognizer \| TFLITE \| float \| Qualcomm® SA7255P \| 174.222 ms \| 6 - 16 MB \| CPU
	\| recognizer \| TFLITE \| float \| Qualcomm® SA8295P \| 69.518 ms \| 6 - 11 MB \| CPU
	\| recognizer \| TFLITE \| float \| Snapdragon® 8 Elite Mobile \| 45.439 ms \| 7 - 17 MB \| CPU
	\| recognizer \| TFLITE \| float \| Snapdragon® 8 Elite Gen 5 Mobile \| 44.156 ms \| 9 - 19 MB \| CPU
	\| recognizer \| TFLITE \| w8a8 \| Snapdragon® 8 Gen 3 Mobile \| 30.789 ms \| 5 - 14 MB \| CPU
	\| recognizer \| TFLITE \| w8a8 \| Snapdragon® 8 Gen 1 Mobile \| 56.134 ms \| 0 - 12 MB \| CPU
	\| recognizer \| TFLITE \| w8a8 \| Qualcomm® Dragonwing™ QCS6490 \| 141.75 ms \| 3 - 22 MB \| CPU
	\| recognizer \| TFLITE \| w8a8 \| Qualcomm® Dragonwing™ IQ-8275 \| 280.375 ms \| 3 - 21 MB \| CPU
	\| recognizer \| TFLITE \| w8a8 \| Qualcomm® Dragonwing™ IQ-8275 \| 140.387 ms \| 0 - 8 MB \| CPU
	\| recognizer \| TFLITE \| w8a8 \| Qualcomm® Dragonwing™ QCS8550 (Proxy) \| 37.889 ms \| 5 - 28 MB \| CPU
	\| recognizer \| TFLITE \| w8a8 \| Qualcomm® SA8775P \| 70.59 ms \| 8 - 14 MB \| CPU
	\| recognizer \| TFLITE \| w8a8 \| Qualcomm® SA8650P \| 70.59 ms \| 8 - 14 MB \| CPU
	\| recognizer \| TFLITE \| w8a8 \| Qualcomm® SA8255P \| 70.59 ms \| 8 - 14 MB \| CPU
	\| recognizer \| TFLITE \| w8a8 \| Qualcomm® QCS8450 \| 56.134 ms \| 0 - 12 MB \| CPU
	\| recognizer \| TFLITE \| w8a8 \| Qualcomm® Dragonwing™ IQ-9075 \| 95.825 ms \| 3 - 22 MB \| CPU
	\| recognizer \| TFLITE \| w8a8 \| Qualcomm® Dragonwing™ Q-6690 \| 76.452 ms \| 6 - 12 MB \| CPU
	\| recognizer \| TFLITE \| w8a8 \| Qualcomm® Dragonwing™ Q-7790 \| 57.837 ms \| 8 - 14 MB \| CPU
	\| recognizer \| TFLITE \| w8a8 \| Qualcomm® Dragonwing™ Q-8750 \| 31.312 ms \| 7 - 16 MB \| CPU
	\| recognizer \| TFLITE \| w8a8 \| Qualcomm® SA7255P \| 140.387 ms \| 0 - 8 MB \| CPU
	\| recognizer \| TFLITE \| w8a8 \| Qualcomm® SA8295P \| 50.224 ms \| 5 - 11 MB \| CPU
	\| recognizer \| TFLITE \| w8a8 \| Snapdragon® 8 Elite Mobile \| 31.312 ms \| 7 - 16 MB \| CPU
	\| recognizer \| TFLITE \| w8a8 \| Snapdragon® 8 Elite Gen 5 Mobile \| 40.178 ms \| 6 - 14 MB \| CPU
	\| recognizer \| TFLITE \| w8a8 \| Snapdragon® 7 Gen 4 Mobile \| 57.837 ms \| 8 - 14 MB \| CPU

	## License
	* The license for the original implementation of EasyOCR can be found
	[here](https://github.com/JaidedAI/EasyOCR/blob/master/LICENSE).

	## References
	* [Source Model Implementation](https://github.com/JaidedAI/EasyOCR)

	## Community
	* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
	* For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).