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 1.25.0 Download
ONNX w8a8 Universal QAIRT 2.42, ONNX Runtime 1.25.0 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 16.155 ms 7 - 178 MB NPU
detector ONNX float Snapdragon® X Elite 37.935 ms 143 - 143 MB NPU
detector ONNX float Snapdragon® 8 Gen 3 Mobile 27.155 ms 7 - 246 MB NPU
detector ONNX float Qualcomm® QCS8550 (Proxy) 37.015 ms 0 - 48 MB NPU
detector ONNX float Snapdragon® 8 Elite For Galaxy Mobile 21.904 ms 3 - 170 MB NPU
detector ONNX float Qualcomm® QCS9075 69.949 ms 6 - 51 MB NPU
detector ONNX float Qualcomm® QCS8750 21.904 ms 3 - 170 MB NPU
detector ONNX float Qualcomm® QCS7181 37.935 ms 143 - 143 MB NPU
detector ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 5.361 ms 2 - 165 MB NPU
detector ONNX w8a8 Snapdragon® X2 Elite 6.725 ms 211 - 211 MB NPU
detector ONNX w8a8 Snapdragon® X Elite 13.515 ms 180 - 180 MB NPU
detector ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 9.718 ms 2 - 218 MB NPU
detector ONNX w8a8 Qualcomm® QCS6490 951.763 ms 222 - 241 MB CPU
detector ONNX w8a8 Qualcomm® QCS8550 (Proxy) 13.053 ms 0 - 45 MB NPU
detector ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 919.288 ms 231 - 238 MB CPU
detector ONNX w8a8 Qualcomm® QCM6690 930.44 ms 233 - 241 MB CPU
detector ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 7.75 ms 1 - 162 MB NPU
detector ONNX w8a8 Qualcomm® QCS9075 13.53 ms 1 - 47 MB NPU
detector ONNX w8a8 Qualcomm® QCS7790 919.288 ms 231 - 238 MB CPU
detector ONNX w8a8 Qualcomm® QCS8750 7.75 ms 1 - 162 MB NPU
detector ONNX w8a8 Qualcomm® QCS7181 13.515 ms 180 - 180 MB NPU
detector TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 16.536 ms 1 - 182 MB NPU
detector TFLITE float Snapdragon® 8 Gen 3 Mobile 28.074 ms 0 - 259 MB NPU
detector TFLITE float Qualcomm® QCS8275 269.41 ms 1 - 175 MB NPU
detector TFLITE float Qualcomm® QCS8550 (Proxy) 37.992 ms 1 - 3 MB NPU
detector TFLITE float Qualcomm® SA8775P 67.998 ms 1 - 175 MB NPU
detector TFLITE float Qualcomm® SA8650P 67.998 ms 1 - 175 MB NPU
detector TFLITE float Qualcomm® SA8255P 67.998 ms 1 - 175 MB NPU
detector TFLITE float Qualcomm® QCS8450 (Proxy) 80.47 ms 0 - 282 MB NPU
detector TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 21.918 ms 1 - 168 MB NPU
detector TFLITE float Qualcomm® QCS9075 75.504 ms 0 - 49 MB NPU
detector TFLITE float Qualcomm® SA7255P 269.41 ms 1 - 175 MB NPU
detector TFLITE float Qualcomm® SA8295P 73.886 ms 1 - 186 MB NPU
detector TFLITE float Qualcomm® QCS8750 21.918 ms 1 - 168 MB NPU
detector TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 4.455 ms 0 - 159 MB NPU
detector TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 7.162 ms 0 - 208 MB NPU
detector TFLITE w8a8 Qualcomm® QCS6490 51.34 ms 0 - 24 MB NPU
detector TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 9.472 ms 0 - 2 MB NPU
detector TFLITE w8a8 Qualcomm® SA8775P 10.08 ms 0 - 158 MB NPU
detector TFLITE w8a8 Qualcomm® SA8650P 10.08 ms 0 - 158 MB NPU
detector TFLITE w8a8 Qualcomm® SA8255P 10.08 ms 0 - 158 MB NPU
detector TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 18.879 ms 0 - 176 MB NPU
detector TFLITE w8a8 Qualcomm® QCM6690 251.395 ms 0 - 208 MB NPU
detector TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 5.765 ms 0 - 156 MB NPU
detector TFLITE w8a8 Qualcomm® QCS9075 11.86 ms 0 - 24 MB NPU
detector TFLITE w8a8 Qualcomm® SA8295P 18.978 ms 0 - 152 MB NPU
detector TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 14.699 ms 0 - 210 MB NPU
detector TFLITE w8a8 Qualcomm® QCS7790 18.879 ms 0 - 176 MB NPU
detector TFLITE w8a8 Qualcomm® QCS8750 5.765 ms 0 - 156 MB NPU
recognizer ONNX float Snapdragon® 8 Elite Gen 5 Mobile 10.473 ms 0 - 769 MB NPU
recognizer ONNX float Snapdragon® X Elite 16.531 ms 151 - 151 MB NPU
recognizer ONNX float Snapdragon® 8 Gen 3 Mobile 12.032 ms 0 - 747 MB NPU
recognizer ONNX float Qualcomm® QCS8550 (Proxy) 16.502 ms 0 - 31 MB NPU
recognizer ONNX float Snapdragon® 8 Elite For Galaxy Mobile 10.198 ms 0 - 638 MB NPU
recognizer ONNX float Qualcomm® QCS9075 19.206 ms 0 - 45 MB NPU
recognizer ONNX float Qualcomm® QCS8750 10.198 ms 0 - 638 MB NPU
recognizer ONNX float Qualcomm® QCS7181 16.531 ms 151 - 151 MB NPU
recognizer ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 8.14 ms 0 - 804 MB NPU
recognizer ONNX w8a8 Snapdragon® X2 Elite 9.41 ms 212 - 212 MB NPU
recognizer ONNX w8a8 Snapdragon® X Elite 10.347 ms 181 - 181 MB NPU
recognizer ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 7.731 ms 0 - 748 MB NPU
recognizer ONNX w8a8 Qualcomm® QCS6490 121.882 ms 22 - 26 MB CPU
recognizer ONNX w8a8 Qualcomm® QCS8550 (Proxy) 10.944 ms 0 - 7 MB NPU
recognizer ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 39.641 ms 19 - 26 MB CPU
recognizer ONNX w8a8 Qualcomm® QCM6690 53.375 ms 18 - 25 MB CPU
recognizer ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 7.554 ms 0 - 648 MB NPU
recognizer ONNX w8a8 Qualcomm® QCS9075 11.836 ms 0 - 45 MB NPU
recognizer ONNX w8a8 Qualcomm® QCS7790 39.641 ms 19 - 26 MB CPU
recognizer ONNX w8a8 Qualcomm® QCS8750 7.554 ms 0 - 648 MB NPU
recognizer ONNX w8a8 Qualcomm® QCS7181 10.347 ms 181 - 181 MB NPU
recognizer TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 43.206 ms 10 - 21 MB CPU
recognizer TFLITE float Snapdragon® 8 Gen 3 Mobile 51.716 ms 6 - 14 MB CPU
recognizer TFLITE float Qualcomm® QCS8275 172.478 ms 8 - 16 MB CPU
recognizer TFLITE float Qualcomm® QCS8550 (Proxy) 60.195 ms 6 - 8 MB CPU
recognizer TFLITE float Qualcomm® SA8775P 99.795 ms 8 - 13 MB CPU
recognizer TFLITE float Qualcomm® SA8650P 99.795 ms 8 - 13 MB CPU
recognizer TFLITE float Qualcomm® SA8255P 99.795 ms 8 - 13 MB CPU
recognizer TFLITE float Qualcomm® QCS8450 (Proxy) 66.907 ms 6 - 17 MB CPU
recognizer TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 43.188 ms 8 - 21 MB CPU
recognizer TFLITE float Qualcomm® QCS9075 127.336 ms 4 - 33 MB CPU
recognizer TFLITE float Qualcomm® SA7255P 172.478 ms 8 - 16 MB CPU
recognizer TFLITE float Qualcomm® SA8295P 70.866 ms 6 - 11 MB CPU
recognizer TFLITE float Qualcomm® QCS8750 43.188 ms 8 - 21 MB CPU
recognizer TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 38.993 ms 8 - 19 MB CPU
recognizer TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 32.315 ms 5 - 15 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCS6490 140.003 ms 3 - 22 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 35.485 ms 5 - 7 MB CPU
recognizer TFLITE w8a8 Qualcomm® SA8775P 70.313 ms 7 - 13 MB CPU
recognizer TFLITE w8a8 Qualcomm® SA8650P 70.313 ms 7 - 13 MB CPU
recognizer TFLITE w8a8 Qualcomm® SA8255P 70.313 ms 7 - 13 MB CPU
recognizer TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 56.7 ms 8 - 14 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCM6690 75.277 ms 8 - 14 MB CPU
recognizer TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 28.471 ms 8 - 20 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCS9075 97.71 ms 3 - 22 MB CPU
recognizer TFLITE w8a8 Qualcomm® SA8295P 51.579 ms 5 - 10 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 42.36 ms 5 - 17 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCS7790 56.7 ms 8 - 14 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCS8750 28.471 ms 8 - 20 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