---
title: EasyOCR
canonical_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/EasyOCR"
md_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/EasyOCR.md"
repository: Qualcomm-AI-Hub/EasyOCR
last_updated: 2026-10-16
license: apache-2.0
downloads: 0
stars: 0
tags:
  - android
---

# EasyOCR

> EasyOCR - Qualcomm-AI-Hub 在 ModelScope 开源的模型。EasyOCR: Optimized for Qualcomm Devices

Qualcomm-AI-Hub/EasyOCR 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可。

- **Repository**: Qualcomm-AI-Hub/EasyOCR
- **License**: apache-2.0
- **Tags**: android
- **Downloads**: 0
- **Stars**: 0
- **Last updated**: 2026-10-16

Source: https://www.modelscope.cn/models/Qualcomm-AI-Hub/EasyOCR

---

![](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/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-cn/blob/main/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.cn) 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://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/easyocr/releases/v0.62.1/easyocr-onnx-float.zip)
| ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/easyocr/releases/v0.62.1/easyocr-onnx-w8a8.zip)
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/easyocr/releases/v0.62.1/easyocr-qnn_dlc-float.zip)
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/easyocr/releases/v0.62.1/easyocr-tflite-float.zip)
| TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/easyocr/releases/v0.62.1/easyocr-tflite-w8a8.zip)

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


### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models-cn/blob/main/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-cn/blob/main/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 | 20.046 ms | 9 - 9 MB | NPU
| detector | ONNX | float | Snapdragon® X Elite | 38.129 ms | 36 - 36 MB | NPU
| detector | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 27.754 ms | 1 - 230 MB | NPU
| detector | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 76.012 ms | 1 - 237 MB | NPU
| detector | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 78.292 ms | 6 - 15 MB | NPU
| detector | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 36.858 ms | 0 - 354 MB | NPU
| detector | ONNX | float | Qualcomm® QCS8450 | 76.012 ms | 1 - 237 MB | NPU
| detector | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 68.496 ms | 5 - 14 MB | NPU
| detector | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 38.129 ms | 36 - 36 MB | NPU
| detector | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 22.297 ms | 2 - 165 MB | NPU
| detector | ONNX | float | Snapdragon® 8 Elite Mobile | 22.297 ms | 2 - 165 MB | NPU
| detector | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 16.322 ms | 3 - 170 MB | NPU
| detector | ONNX | w8a8 | Snapdragon® X2 Elite | 6.731 ms | 1 - 1 MB | NPU
| detector | ONNX | w8a8 | Snapdragon® X Elite | 13.45 ms | 19 - 19 MB | NPU
| detector | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 9.708 ms | 2 - 219 MB | NPU
| detector | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 20.009 ms | 2 - 216 MB | NPU
| detector | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 15.275 ms | 1 - 5 MB | NPU
| detector | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 13.047 ms | 0 - 25 MB | NPU
| detector | ONNX | w8a8 | Qualcomm® QCS8450 | 20.009 ms | 2 - 216 MB | NPU
| detector | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 13.459 ms | 1 - 4 MB | NPU
| detector | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 13.45 ms | 19 - 19 MB | NPU
| detector | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 7.842 ms | 1 - 163 MB | NPU
| detector | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 7.842 ms | 1 - 163 MB | NPU
| detector | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 5.474 ms | 0 - 166 MB | NPU
| detector | QNN_DLC | float | Snapdragon® X2 Elite | 20.746 ms | 6 - 6 MB | NPU
| detector | QNN_DLC | float | Snapdragon® X Elite | 39.471 ms | 6 - 6 MB | NPU
| detector | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 28.034 ms | 6 - 235 MB | NPU
| detector | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 80.316 ms | 6 - 258 MB | NPU
| detector | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 76.745 ms | 6 - 14 MB | NPU
| detector | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 37.979 ms | 6 - 8 MB | NPU
| detector | QNN_DLC | float | Qualcomm® SA8775P | 67.978 ms | 0 - 171 MB | NPU
| detector | QNN_DLC | float | Qualcomm® SA8650P | 67.978 ms | 0 - 171 MB | NPU
| detector | QNN_DLC | float | Qualcomm® SA8255P | 67.978 ms | 0 - 171 MB | NPU
| detector | QNN_DLC | float | Qualcomm® QCS8450 | 80.316 ms | 6 - 258 MB | NPU
| detector | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 67.934 ms | 6 - 14 MB | NPU
| detector | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 39.471 ms | 6 - 6 MB | NPU
| detector | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 21.863 ms | 6 - 169 MB | NPU
| detector | QNN_DLC | float | Qualcomm® SA7255P | 269.293 ms | 0 - 170 MB | NPU
| detector | QNN_DLC | float | Qualcomm® SA8295P | 77.661 ms | 0 - 185 MB | NPU
| detector | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 21.863 ms | 6 - 169 MB | NPU
| detector | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 16.848 ms | 6 - 183 MB | NPU
| detector | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 28.26 ms | 1 - 260 MB | NPU
| detector | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 80.52 ms | 1 - 283 MB | NPU
| detector | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 76.586 ms | 0 - 49 MB | NPU
| detector | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 37.892 ms | 1 - 3 MB | NPU
| detector | TFLITE | float | Qualcomm® SA8775P | 67.999 ms | 1 - 175 MB | NPU
| detector | TFLITE | float | Qualcomm® SA8650P | 67.999 ms | 1 - 175 MB | NPU
| detector | TFLITE | float | Qualcomm® SA8255P | 67.999 ms | 1 - 175 MB | NPU
| detector | TFLITE | float | Qualcomm® QCS8450 | 80.52 ms | 1 - 283 MB | NPU
| detector | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 67.968 ms | 0 - 49 MB | NPU
| detector | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 21.871 ms | 1 - 171 MB | NPU
| detector | TFLITE | float | Qualcomm® SA7255P | 269.421 ms | 1 - 175 MB | NPU
| detector | TFLITE | float | Qualcomm® SA8295P | 73.865 ms | 1 - 186 MB | NPU
| detector | TFLITE | float | Snapdragon® 8 Elite Mobile | 21.871 ms | 1 - 171 MB | NPU
| detector | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 16.568 ms | 1 - 182 MB | NPU
| detector | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 7.158 ms | 0 - 209 MB | NPU
| detector | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 14.654 ms | 0 - 211 MB | NPU
| detector | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 61.979 ms | 0 - 24 MB | NPU
| detector | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 11.173 ms | 0 - 25 MB | NPU
| detector | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 9.459 ms | 0 - 3 MB | NPU
| detector | TFLITE | w8a8 | Qualcomm® SA8775P | 10.061 ms | 0 - 158 MB | NPU
| detector | TFLITE | w8a8 | Qualcomm® SA8650P | 10.061 ms | 0 - 158 MB | NPU
| detector | TFLITE | w8a8 | Qualcomm® SA8255P | 10.061 ms | 0 - 158 MB | NPU
| detector | TFLITE | w8a8 | Qualcomm® QCS8450 | 14.654 ms | 0 - 211 MB | NPU
| detector | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 9.802 ms | 0 - 24 MB | NPU
| detector | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 226.215 ms | 0 - 206 MB | NPU
| detector | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 18.605 ms | 0 - 177 MB | NPU
| detector | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 5.748 ms | 0 - 157 MB | NPU
| detector | TFLITE | w8a8 | Qualcomm® SA7255P | 35.806 ms | 0 - 154 MB | NPU
| detector | TFLITE | w8a8 | Qualcomm® SA8295P | 19.001 ms | 0 - 153 MB | NPU
| detector | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 5.748 ms | 0 - 157 MB | NPU
| detector | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 4.539 ms | 0 - 161 MB | NPU
| detector | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 18.605 ms | 0 - 177 MB | NPU
| recognizer | ONNX | float | Snapdragon® X2 Elite | 12.881 ms | 1 - 1 MB | NPU
| recognizer | ONNX | float | Snapdragon® X Elite | 20.081 ms | 11 - 11 MB | NPU
| recognizer | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 16.698 ms | 0 - 781 MB | NPU
| recognizer | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 27.787 ms | 1 - 346 MB | NPU
| recognizer | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 23.304 ms | 0 - 4 MB | NPU
| recognizer | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 21.73 ms | 0 - 50 MB | NPU
| recognizer | ONNX | float | Qualcomm® QCS8450 | 27.787 ms | 1 - 346 MB | NPU
| recognizer | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 24.428 ms | 0 - 3 MB | NPU
| recognizer | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 20.081 ms | 11 - 11 MB | NPU
| recognizer | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 11.882 ms | 0 - 655 MB | NPU
| recognizer | ONNX | float | Snapdragon® 8 Elite Mobile | 11.882 ms | 0 - 655 MB | NPU
| recognizer | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 11.651 ms | 0 - 789 MB | NPU
| recognizer | ONNX | w8a8 | Snapdragon® X2 Elite | 9.114 ms | 1 - 1 MB | NPU
| recognizer | ONNX | w8a8 | Snapdragon® X Elite | 10.525 ms | 10 - 10 MB | NPU
| recognizer | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 7.975 ms | 0 - 801 MB | NPU
| recognizer | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 15.709 ms | 0 - 355 MB | NPU
| recognizer | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 11.992 ms | 0 - 4 MB | NPU
| recognizer | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.554 ms | 0 - 14 MB | NPU
| recognizer | ONNX | w8a8 | Qualcomm® QCS8450 | 15.709 ms | 0 - 355 MB | NPU
| recognizer | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 11.268 ms | 0 - 3 MB | NPU
| recognizer | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 10.525 ms | 10 - 10 MB | NPU
| recognizer | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 7.642 ms | 0 - 666 MB | NPU
| recognizer | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 7.642 ms | 0 - 666 MB | NPU
| recognizer | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 8.162 ms | 0 - 810 MB | NPU
| recognizer | QNN_DLC | float | Snapdragon® X2 Elite | 12.996 ms | 0 - 0 MB | NPU
| recognizer | QNN_DLC | float | Snapdragon® X Elite | 20.666 ms | 0 - 0 MB | NPU
| recognizer | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 16.767 ms | 0 - 862 MB | NPU
| recognizer | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 28.652 ms | 0 - 411 MB | NPU
| recognizer | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 23.665 ms | 0 - 3 MB | NPU
| recognizer | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 21.714 ms | 0 - 299 MB | NPU
| recognizer | QNN_DLC | float | Qualcomm® SA8775P | 25.844 ms | 0 - 703 MB | NPU
| recognizer | QNN_DLC | float | Qualcomm® SA8650P | 25.844 ms | 0 - 703 MB | NPU
| recognizer | QNN_DLC | float | Qualcomm® SA8255P | 25.844 ms | 0 - 703 MB | NPU
| recognizer | QNN_DLC | float | Qualcomm® QCS8450 | 28.652 ms | 0 - 411 MB | NPU
| recognizer | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 24.472 ms | 0 - 2 MB | NPU
| recognizer | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 20.666 ms | 0 - 0 MB | NPU
| recognizer | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 12.201 ms | 0 - 701 MB | NPU
| recognizer | QNN_DLC | float | Qualcomm® SA7255P | 57.674 ms | 0 - 696 MB | NPU
| recognizer | QNN_DLC | float | Qualcomm® SA8295P | 31.833 ms | 0 - 340 MB | NPU
| recognizer | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 12.201 ms | 0 - 701 MB | NPU
| recognizer | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 11.437 ms | 0 - 729 MB | NPU
| recognizer | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 51.173 ms | 6 - 14 MB | CPU
| recognizer | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 72.286 ms | 4 - 15 MB | CPU
| recognizer | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 331.768 ms | 5 - 34 MB | CPU
| recognizer | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 58.925 ms | 3 - 43 MB | CPU
| recognizer | TFLITE | float | Qualcomm® SA8775P | 99.132 ms | 7 - 13 MB | CPU
| recognizer | TFLITE | float | Qualcomm® SA8650P | 99.132 ms | 7 - 13 MB | CPU
| recognizer | TFLITE | float | Qualcomm® SA8255P | 99.132 ms | 7 - 13 MB | CPU
| recognizer | TFLITE | float | Qualcomm® QCS8450 | 72.286 ms | 4 - 15 MB | CPU
| recognizer | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 125.365 ms | 4 - 33 MB | CPU
| recognizer | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 43.51 ms | 8 - 20 MB | CPU
| recognizer | TFLITE | float | Qualcomm® SA7255P | 173.037 ms | 8 - 18 MB | CPU
| recognizer | TFLITE | float | Qualcomm® SA8295P | 69.746 ms | 8 - 13 MB | CPU
| recognizer | TFLITE | float | Snapdragon® 8 Elite Mobile | 43.51 ms | 8 - 20 MB | CPU
| recognizer | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 43.162 ms | 9 - 18 MB | CPU
| recognizer | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 31.05 ms | 5 - 13 MB | CPU
| recognizer | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 41.151 ms | 0 - 11 MB | CPU
| recognizer | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 166.812 ms | 3 - 22 MB | CPU
| recognizer | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 282.613 ms | 3 - 22 MB | CPU
| recognizer | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 36.69 ms | 2 - 29 MB | CPU
| recognizer | TFLITE | w8a8 | Qualcomm® SA8775P | 69.203 ms | 8 - 13 MB | CPU
| recognizer | TFLITE | w8a8 | Qualcomm® SA8650P | 69.203 ms | 8 - 13 MB | CPU
| recognizer | TFLITE | w8a8 | Qualcomm® SA8255P | 69.203 ms | 8 - 13 MB | CPU
| recognizer | TFLITE | w8a8 | Qualcomm® QCS8450 | 41.151 ms | 0 - 11 MB | CPU
| recognizer | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 94.786 ms | 3 - 22 MB | CPU
| recognizer | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 77.796 ms | 7 - 13 MB | CPU
| recognizer | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 57.201 ms | 15 - 21 MB | CPU
| recognizer | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 28.269 ms | 7 - 16 MB | CPU
| recognizer | TFLITE | w8a8 | Qualcomm® SA7255P | 142.671 ms | 8 - 16 MB | CPU
| recognizer | TFLITE | w8a8 | Qualcomm® SA8295P | 50.206 ms | 5 - 11 MB | CPU
| recognizer | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 28.269 ms | 7 - 16 MB | CPU
| recognizer | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 39.539 ms | 6 - 14 MB | CPU
| recognizer | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 57.201 ms | 15 - 21 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
* For questions or feedback, chat with our engineers in [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.cn).