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 2.45, ONNX Runtime 1.25.0 Download
ONNX w8a8 Universal QAIRT 2.45, ONNX Runtime 1.25.0 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® X2 Elite 19.974 ms 207 - 207 MB NPU
detector ONNX float Snapdragon® X Elite 38.18 ms 143 - 143 MB NPU
detector ONNX float Snapdragon® 8 Gen 3 Mobile 28.016 ms 1 - 220 MB NPU
detector ONNX float Snapdragon® 8 Gen 1 Mobile 76.924 ms 7 - 235 MB NPU
detector ONNX float Qualcomm® QCS8550 (Proxy) 36.992 ms 0 - 45 MB NPU
detector ONNX float Qualcomm® QCS8450 76.924 ms 7 - 235 MB NPU
detector ONNX float Snapdragon® 8 Elite Mobile 22.287 ms 3 - 166 MB NPU
detector ONNX float Snapdragon® 8 Elite Gen 5 Mobile 16.015 ms 3 - 168 MB NPU
detector ONNX float Qualcomm® QCS9075 70.753 ms 6 - 51 MB NPU
detector ONNX float Qualcomm® QCS8750 22.287 ms 3 - 166 MB NPU
detector ONNX float Qualcomm® QCS7181 38.18 ms 143 - 143 MB NPU
detector ONNX w8a8 Snapdragon® X2 Elite 6.737 ms 180 - 180 MB NPU
detector ONNX w8a8 Snapdragon® X Elite 13.547 ms 180 - 180 MB NPU
detector ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 9.701 ms 2 - 208 MB NPU
detector ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 19.893 ms 2 - 208 MB NPU
detector ONNX w8a8 Qualcomm® QCS8550 (Proxy) 13.128 ms 0 - 27 MB NPU
detector ONNX w8a8 Qualcomm® QCS8450 19.893 ms 2 - 208 MB NPU
detector ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 5.344 ms 2 - 160 MB NPU
detector ONNX w8a8 Qualcomm® QCS9075 13.515 ms 1 - 47 MB NPU
detector ONNX w8a8 Snapdragon® 8 Elite Mobile 7.834 ms 2 - 162 MB NPU
detector ONNX w8a8 Qualcomm® QCS8750 7.834 ms 2 - 162 MB NPU
detector ONNX w8a8 Qualcomm® QCS7181 13.547 ms 180 - 180 MB NPU
detector QNN_DLC float Snapdragon® X2 Elite 20.739 ms 6 - 6 MB NPU
detector QNN_DLC float Snapdragon® X Elite 39.517 ms 6 - 6 MB NPU
detector QNN_DLC float Snapdragon® 8 Gen 3 Mobile 27.998 ms 0 - 230 MB NPU
detector QNN_DLC float Snapdragon® 8 Gen 1 Mobile 80.542 ms 6 - 258 MB NPU
detector QNN_DLC float Qualcomm® QCS8275 269.318 ms 0 - 170 MB NPU
detector QNN_DLC float Qualcomm® QCS8550 (Proxy) 38.327 ms 6 - 33 MB NPU
detector QNN_DLC float Qualcomm® QCS8450 80.542 ms 6 - 258 MB NPU
detector QNN_DLC float Snapdragon® 8 Elite Mobile 21.941 ms 0 - 165 MB NPU
detector QNN_DLC float Qualcomm® SA8295P 77.662 ms 0 - 184 MB NPU
detector QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 16.543 ms 6 - 184 MB NPU
detector QNN_DLC float Qualcomm® SA7255P 269.318 ms 0 - 170 MB NPU
detector QNN_DLC float Qualcomm® QCS9075 76.218 ms 6 - 14 MB NPU
detector QNN_DLC float Qualcomm® QCS8750 21.941 ms 0 - 165 MB NPU
detector QNN_DLC float Qualcomm® QCS7181 39.517 ms 6 - 6 MB NPU
detector TFLITE float Snapdragon® 8 Gen 3 Mobile 28.006 ms 0 - 258 MB NPU
detector TFLITE float Snapdragon® 8 Gen 1 Mobile 81.65 ms 1 - 285 MB NPU
detector TFLITE float Qualcomm® QCS8275 269.479 ms 1 - 175 MB NPU
detector TFLITE float Qualcomm® QCS8550 (Proxy) 38.139 ms 1 - 3 MB NPU
detector TFLITE float Qualcomm® SA8775P 453.767 ms 0 - 19 MB GPU
detector TFLITE float Qualcomm® SA8650P 453.767 ms 0 - 19 MB GPU
detector TFLITE float Qualcomm® SA8255P 453.767 ms 0 - 19 MB GPU
detector TFLITE float Qualcomm® QCS8450 81.65 ms 1 - 285 MB NPU
detector TFLITE float Snapdragon® 8 Elite Mobile 21.901 ms 1 - 170 MB NPU
detector TFLITE float Qualcomm® SA8295P 73.836 ms 1 - 186 MB NPU
detector TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 16.591 ms 1 - 183 MB NPU
detector TFLITE float Qualcomm® SA7255P 269.479 ms 1 - 175 MB NPU
detector TFLITE float Qualcomm® QCS9075 75.417 ms 0 - 49 MB NPU
detector TFLITE float Qualcomm® QCS8750 21.901 ms 1 - 170 MB NPU
detector TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 7.167 ms 0 - 209 MB NPU
detector TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 14.626 ms 0 - 210 MB NPU
detector TFLITE w8a8 Qualcomm® QCS6490 51.273 ms 0 - 24 MB NPU
detector TFLITE w8a8 Qualcomm® QCS8275 35.829 ms 0 - 154 MB NPU
detector TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 9.479 ms 0 - 174 MB NPU
detector TFLITE w8a8 Qualcomm® SA8775P 450.107 ms 7 - 25 MB GPU
detector TFLITE w8a8 Qualcomm® SA8650P 450.107 ms 7 - 25 MB GPU
detector TFLITE w8a8 Qualcomm® SA8255P 450.107 ms 7 - 25 MB GPU
detector TFLITE w8a8 Qualcomm® QCS8450 14.626 ms 0 - 210 MB NPU
detector TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 4.47 ms 0 - 160 MB NPU
detector TFLITE w8a8 Qualcomm® QCS9075 11.703 ms 0 - 24 MB NPU
detector TFLITE w8a8 Qualcomm® SA7255P 35.829 ms 0 - 154 MB NPU
detector TFLITE w8a8 Qualcomm® QCM6690 224.707 ms 0 - 208 MB NPU
detector TFLITE w8a8 Snapdragon® 8 Elite Mobile 5.756 ms 0 - 157 MB NPU
detector TFLITE w8a8 Qualcomm® SA8295P 18.987 ms 0 - 152 MB NPU
detector TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 18.84 ms 0 - 177 MB NPU
detector TFLITE w8a8 Qualcomm® QCS7790 18.84 ms 0 - 177 MB NPU
detector TFLITE w8a8 Qualcomm® QCS8750 5.756 ms 0 - 157 MB NPU
recognizer ONNX float Snapdragon® X2 Elite 12.904 ms 212 - 212 MB NPU
recognizer ONNX float Snapdragon® X Elite 20.442 ms 181 - 181 MB NPU
recognizer ONNX float Snapdragon® 8 Gen 3 Mobile 16.507 ms 0 - 775 MB NPU
recognizer ONNX float Snapdragon® 8 Gen 1 Mobile 27.979 ms 2 - 341 MB NPU
recognizer ONNX float Qualcomm® QCS8550 (Proxy) 21.69 ms 0 - 22 MB NPU
recognizer ONNX float Qualcomm® QCS8450 27.979 ms 2 - 341 MB NPU
recognizer ONNX float Snapdragon® 8 Elite Mobile 11.895 ms 0 - 659 MB NPU
recognizer ONNX float Snapdragon® 8 Elite Gen 5 Mobile 11.613 ms 0 - 786 MB NPU
recognizer ONNX float Qualcomm® QCS9075 24.141 ms 0 - 45 MB NPU
recognizer ONNX float Qualcomm® QCS8750 11.895 ms 0 - 659 MB NPU
recognizer ONNX float Qualcomm® QCS7181 20.442 ms 181 - 181 MB NPU
recognizer ONNX w8a8 Snapdragon® X2 Elite 9.142 ms 182 - 182 MB NPU
recognizer ONNX w8a8 Snapdragon® X Elite 10.498 ms 152 - 152 MB NPU
recognizer ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 8.04 ms 0 - 794 MB NPU
recognizer ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 15.62 ms 0 - 343 MB NPU
recognizer ONNX w8a8 Qualcomm® QCS8550 (Proxy) 11.077 ms 0 - 21 MB NPU
recognizer ONNX w8a8 Qualcomm® QCS8450 15.62 ms 0 - 343 MB NPU
recognizer ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 8.151 ms 0 - 804 MB NPU
recognizer ONNX w8a8 Qualcomm® QCS9075 11.768 ms 0 - 45 MB NPU
recognizer ONNX w8a8 Snapdragon® 8 Elite Mobile 7.901 ms 0 - 668 MB NPU
recognizer ONNX w8a8 Qualcomm® QCS8750 7.901 ms 0 - 668 MB NPU
recognizer ONNX w8a8 Qualcomm® QCS7181 10.498 ms 152 - 152 MB NPU
recognizer QNN_DLC float Snapdragon® X2 Elite 12.925 ms 0 - 0 MB NPU
recognizer QNN_DLC float Snapdragon® X Elite 20.67 ms 0 - 0 MB NPU
recognizer QNN_DLC float Snapdragon® 8 Gen 3 Mobile 16.98 ms 0 - 868 MB NPU
recognizer QNN_DLC float Snapdragon® 8 Gen 1 Mobile 28.684 ms 0 - 423 MB NPU
recognizer QNN_DLC float Qualcomm® QCS8275 57.667 ms 0 - 706 MB NPU
recognizer QNN_DLC float Qualcomm® QCS8550 (Proxy) 23.049 ms 0 - 3 MB NPU
recognizer QNN_DLC float Qualcomm® QCS8450 28.684 ms 0 - 423 MB NPU
recognizer QNN_DLC float Snapdragon® 8 Elite Mobile 12.15 ms 0 - 718 MB NPU
recognizer QNN_DLC float Qualcomm® SA8295P 31.519 ms 0 - 349 MB NPU
recognizer QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 11.405 ms 0 - 737 MB NPU
recognizer QNN_DLC float Qualcomm® SA7255P 57.667 ms 0 - 706 MB NPU
recognizer QNN_DLC float Qualcomm® QCS9075 24.964 ms 0 - 2 MB NPU
recognizer QNN_DLC float Qualcomm® QCS8750 12.15 ms 0 - 718 MB NPU
recognizer QNN_DLC float Qualcomm® QCS7181 20.67 ms 0 - 0 MB NPU
recognizer TFLITE float Snapdragon® 8 Gen 3 Mobile 51.065 ms 6 - 15 MB CPU
recognizer TFLITE float Snapdragon® 8 Gen 1 Mobile 77.872 ms 11 - 27 MB CPU
recognizer TFLITE float Qualcomm® QCS8275 174.494 ms 8 - 18 MB CPU
recognizer TFLITE float Qualcomm® QCS8550 (Proxy) 65.754 ms 6 - 41 MB CPU
recognizer TFLITE float Qualcomm® SA8775P 98.746 ms 7 - 13 MB CPU
recognizer TFLITE float Qualcomm® SA8650P 98.746 ms 7 - 13 MB CPU
recognizer TFLITE float Qualcomm® SA8255P 98.746 ms 7 - 13 MB CPU
recognizer TFLITE float Qualcomm® QCS8450 77.872 ms 11 - 27 MB CPU
recognizer TFLITE float Snapdragon® 8 Elite Mobile 43.944 ms 8 - 21 MB CPU
recognizer TFLITE float Qualcomm® SA8295P 71.092 ms 6 - 12 MB CPU
recognizer TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 40.191 ms 8 - 17 MB CPU
recognizer TFLITE float Qualcomm® SA7255P 174.494 ms 8 - 18 MB CPU
recognizer TFLITE float Qualcomm® QCS9075 131.955 ms 4 - 33 MB CPU
recognizer TFLITE float Qualcomm® QCS8750 43.944 ms 8 - 21 MB CPU
recognizer TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 32.258 ms 5 - 14 MB CPU
recognizer TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 52.1 ms 6 - 21 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCS6490 165.23 ms 3 - 22 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCS8275 141.87 ms 0 - 9 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 36.23 ms 5 - 7 MB CPU
recognizer TFLITE w8a8 Qualcomm® SA8775P 70.169 ms 8 - 14 MB CPU
recognizer TFLITE w8a8 Qualcomm® SA8650P 70.169 ms 8 - 14 MB CPU
recognizer TFLITE w8a8 Qualcomm® SA8255P 70.169 ms 8 - 14 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCS8450 52.1 ms 6 - 21 MB CPU
recognizer TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 39.948 ms 6 - 14 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCS9075 99.333 ms 3 - 22 MB CPU
recognizer TFLITE w8a8 Qualcomm® SA7255P 141.87 ms 0 - 9 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCM6690 75.674 ms 8 - 14 MB CPU
recognizer TFLITE w8a8 Snapdragon® 8 Elite Mobile 29.372 ms 8 - 15 MB CPU
recognizer TFLITE w8a8 Qualcomm® SA8295P 51.519 ms 5 - 11 MB CPU
recognizer TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 57.977 ms 15 - 21 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCS7790 57.977 ms 15 - 21 MB CPU
recognizer TFLITE w8a8 Qualcomm® QCS8750 29.372 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