Hugging Face's logo

qualcomm
/
EasyOCR

Image-to-Text
PyTorch
android
Model card Files
xet
 Community
3

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. 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 w8a8 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
TFLITE w8a8 Universal QAIRT 2.45 Download

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

Model Details

Model Type: Model_use_case.image_to_text

Model Stats:

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

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
detector ONNX float Snapdragon® 8 Elite Gen 5 Mobile 16.267 ms 7 - 179 MB NPU
detector ONNX float Snapdragon® X2 Elite 19.925 ms 36 - 36 MB NPU
detector ONNX float Snapdragon® X Elite 38.194 ms 35 - 35 MB NPU
detector ONNX float Snapdragon® 8 Gen 3 Mobile 27.361 ms 8 - 246 MB NPU
detector ONNX float Qualcomm® QCS8550 (Proxy) 36.993 ms 6 - 29 MB NPU
detector ONNX float Qualcomm® QCS9075 69.986 ms 6 - 14 MB NPU
detector ONNX float Snapdragon® 8 Elite For Galaxy Mobile 21.97 ms 3 - 171 MB NPU
detector ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 5.362 ms 0 - 162 MB NPU
detector ONNX w8a8 Snapdragon® X2 Elite 6.712 ms 20 - 20 MB NPU
detector ONNX w8a8 Snapdragon® X Elite 13.661 ms 19 - 19 MB NPU
detector ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 9.744 ms 2 - 218 MB NPU
detector ONNX w8a8 Qualcomm® QCS6490 947.215 ms 224 - 243 MB CPU
detector ONNX w8a8 Qualcomm® QCS8550 (Proxy) 13.055 ms 1 - 217 MB NPU
detector ONNX w8a8 Qualcomm® QCS9075 13.331 ms 1 - 4 MB NPU
detector ONNX w8a8 Qualcomm® QCM6690 929.664 ms 197 - 205 MB CPU
detector ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 7.744 ms 2 - 160 MB NPU
detector ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 917.263 ms 233 - 240 MB CPU
detector QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 16.532 ms 6 - 184 MB NPU
detector QNN_DLC float Snapdragon® X2 Elite 20.72 ms 6 - 6 MB NPU
detector QNN_DLC float Snapdragon® X Elite 39.442 ms 6 - 6 MB NPU
detector QNN_DLC float Snapdragon® 8 Gen 3 Mobile 27.94 ms 6 - 235 MB NPU
detector QNN_DLC float Qualcomm® QCS8275 (Proxy) 269.326 ms 2 - 171 MB NPU
detector QNN_DLC float Qualcomm® QCS8550 (Proxy) 37.756 ms 6 - 111 MB NPU
detector QNN_DLC float Qualcomm® SA8775P 67.981 ms 2 - 171 MB NPU
detector QNN_DLC float Qualcomm® QCS9075 75.57 ms 8 - 16 MB NPU
detector QNN_DLC float Qualcomm® QCS8450 (Proxy) 80.627 ms 6 - 259 MB NPU
detector QNN_DLC float Qualcomm® SA7255P 269.326 ms 2 - 171 MB NPU
detector QNN_DLC float Qualcomm® SA8295P 77.679 ms 2 - 186 MB NPU
detector QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 21.874 ms 0 - 167 MB NPU
detector TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 16.513 ms 1 - 181 MB NPU
detector TFLITE float Snapdragon® 8 Gen 3 Mobile 28.11 ms 1 - 261 MB NPU
detector TFLITE float Qualcomm® QCS8275 (Proxy) 269.441 ms 1 - 174 MB NPU
detector TFLITE float Qualcomm® QCS8550 (Proxy) 38.13 ms 1 - 3 MB NPU
detector TFLITE float Qualcomm® SA8775P 67.993 ms 1 - 175 MB NPU
detector TFLITE float Qualcomm® QCS9075 75.386 ms 0 - 49 MB NPU
detector TFLITE float Qualcomm® QCS8450 (Proxy) 81.164 ms 0 - 284 MB NPU
detector TFLITE float Qualcomm® SA7255P 269.441 ms 1 - 174 MB NPU
detector TFLITE float Qualcomm® SA8295P 73.86 ms 1 - 185 MB NPU
detector TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 21.86 ms 1 - 169 MB NPU
detector TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 4.46 ms 0 - 160 MB NPU
detector TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 7.172 ms 0 - 211 MB NPU
detector TFLITE w8a8 Qualcomm® QCS6490 51.228 ms 0 - 24 MB NPU
detector TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 35.804 ms 0 - 154 MB NPU
detector TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 9.493 ms 0 - 2 MB NPU
detector TFLITE w8a8 Qualcomm® SA8775P 10.093 ms 0 - 158 MB NPU
detector TFLITE w8a8 Qualcomm® QCS9075 11.892 ms 0 - 24 MB NPU
detector TFLITE w8a8 Qualcomm® QCM6690 218.248 ms 0 - 209 MB NPU
detector TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 14.682 ms 0 - 209 MB NPU
detector TFLITE w8a8 Qualcomm® SA7255P 35.804 ms 0 - 154 MB NPU
detector TFLITE w8a8 Qualcomm® SA8295P 18.989 ms 0 - 153 MB NPU
detector TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 5.748 ms 0 - 158 MB NPU
detector TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 18.784 ms 0 - 176 MB NPU
recognizer ONNX float Snapdragon® 8 Elite Gen 5 Mobile 10.493 ms 0 - 790 MB NPU
recognizer ONNX float Snapdragon® X2 Elite 12.001 ms 13 - 13 MB NPU
recognizer ONNX float Snapdragon® X Elite 16.161 ms 11 - 11 MB NPU
recognizer ONNX float Snapdragon® 8 Gen 3 Mobile 12.274 ms 0 - 773 MB NPU
recognizer ONNX float Qualcomm® QCS8550 (Proxy) 16.232 ms 0 - 21 MB NPU
recognizer ONNX float Qualcomm® QCS9075 18.504 ms 0 - 3 MB NPU
recognizer ONNX float Snapdragon® 8 Elite For Galaxy Mobile 10.199 ms 0 - 640 MB NPU
recognizer ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 9.266 ms 1 - 873 MB NPU
recognizer ONNX w8a8 Snapdragon® X2 Elite 10.762 ms 14 - 14 MB NPU
recognizer ONNX w8a8 Snapdragon® X Elite 12.276 ms 10 - 10 MB NPU
recognizer ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 8.906 ms 2 - 866 MB NPU
recognizer ONNX w8a8 Qualcomm® QCS6490 121.646 ms 20 - 24 MB CPU
recognizer ONNX w8a8 Qualcomm® QCS8550 (Proxy) 11.951 ms 0 - 16 MB NPU
recognizer ONNX w8a8 Qualcomm® QCS9075 13.945 ms 2 - 5 MB NPU
recognizer ONNX w8a8 Qualcomm® QCM6690 55.077 ms 17 - 24 MB CPU
recognizer ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 8.302 ms 2 - 701 MB NPU
recognizer ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 40.881 ms 19 - 26 MB CPU
recognizer QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 10.419 ms 0 - 735 MB NPU
recognizer QNN_DLC float Snapdragon® X2 Elite 12.168 ms 0 - 0 MB NPU
recognizer QNN_DLC float Snapdragon® X Elite 16.153 ms 0 - 0 MB NPU
recognizer QNN_DLC float Snapdragon® 8 Gen 3 Mobile 12.472 ms 0 - 832 MB NPU
recognizer QNN_DLC float Qualcomm® QCS8275 (Proxy) 47.542 ms 0 - 691 MB NPU
recognizer QNN_DLC float Qualcomm® QCS8550 (Proxy) 16.682 ms 0 - 3 MB NPU
recognizer QNN_DLC float Qualcomm® SA8775P 20.334 ms 0 - 700 MB NPU
recognizer QNN_DLC float Qualcomm® QCS9075 19.2 ms 0 - 2 MB NPU
recognizer QNN_DLC float Qualcomm® QCS8450 (Proxy) 22.24 ms 0 - 402 MB NPU
recognizer QNN_DLC float Qualcomm® SA7255P 47.542 ms 0 - 691 MB NPU
recognizer QNN_DLC float Qualcomm® SA8295P 24.802 ms 0 - 337 MB NPU
recognizer QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 10.274 ms 0 - 696 MB NPU
recognizer TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 40.954 ms 10 - 20 MB CPU
recognizer TFLITE float Snapdragon® 8 Gen 3 Mobile 53.437 ms 2 - 10 MB CPU
recognizer TFLITE float Qualcomm® QCS8275 (Proxy) 175.498 ms 8 - 16 MB CPU
recognizer TFLITE float Qualcomm® QCS8550 (Proxy) 59.374 ms 5 - 8 MB CPU
recognizer TFLITE float Qualcomm® SA8775P 98.424 ms 8 - 13 MB CPU
recognizer TFLITE float Qualcomm® QCS9075 132.374 ms 4 - 33 MB CPU
recognizer TFLITE float Qualcomm® QCS8450 (Proxy) 70.415 ms 7 - 18 MB CPU
recognizer TFLITE float Qualcomm® SA7255P 175.498 ms 8 - 16 MB CPU
recognizer TFLITE float Qualcomm® SA8295P 71.147 ms 8 - 13 MB CPU
recognizer TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 42.927 ms 8 - 16 MB CPU
recognizer TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 26.99 ms 9 - 19 MB CPU
recognizer TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 32.418 ms 5 - 15 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCS6490 192.194 ms 3 - 22 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 141.017 ms 5 - 13 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 35.69 ms 5 - 7 MB CPU
recognizer TFLITE w8a8 Qualcomm® SA8775P 69.472 ms 10 - 15 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCS9075 98.699 ms 3 - 21 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCM6690 73.06 ms 8 - 14 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 42.4 ms 6 - 17 MB CPU
recognizer TFLITE w8a8 Qualcomm® SA7255P 141.017 ms 5 - 13 MB CPU
recognizer TFLITE w8a8 Qualcomm® SA8295P 49.746 ms 6 - 11 MB CPU
recognizer TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 28.172 ms 7 - 19 MB CPU
recognizer TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 57.238 ms 8 - 15 MB CPU

License

  • The license for the original implementation of EasyOCR can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Image-to-Text
This model isn't deployed by any Inference Provider. 🙋 3 Ask for provider support

Model tree for qualcomm/EasyOCR

Finetunes
1 model

Space using qualcomm/EasyOCR 1