Hugging Face's logo

qualcomm
/
EasyOCR

Image-to-Text
PyTorch
LiteRT
ONNX
android
Model card Files Community

EasyOCR: Optimized for Mobile Deployment

Ready-to-use OCR with 80+ supported languages and all popular writing scripts

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

This model is an implementation of EasyOCR found here.

This repository provides scripts to run EasyOCR on Qualcomm® devices. More details on model performance across various devices, can be found here.

Model Details

  • Model Type: Image to text
  • Model Stats:
    • Model checkpoint: easyocr-small-stage1
    • Input resolution: 384x384
    • Number of parameters (EasyOCRDetector): 20.8M
    • Model size (EasyOCRDetector): 79.2 MB
    • Number of parameters (EasyOCRRecognizer): 3.84M
    • Model size (EasyOCRRecognizer): 14.7 MB
Model Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Precision Primary Compute Unit Target Model
EasyOCRDetector Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 41.176 ms 10 - 204 MB FP16 NPU EasyOCR.tflite
EasyOCRDetector Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 40.762 ms 6 - 27 MB FP16 NPU EasyOCR.so
EasyOCRDetector Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 38.179 ms 27 - 118 MB FP16 NPU EasyOCR.onnx
EasyOCRDetector Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 30.08 ms 15 - 73 MB FP16 NPU EasyOCR.tflite
EasyOCRDetector Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 30.011 ms 6 - 34 MB FP16 NPU EasyOCR.so
EasyOCRDetector Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 28.298 ms 11 - 48 MB FP16 NPU EasyOCR.onnx
EasyOCRDetector Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 29.212 ms 16 - 50 MB FP16 NPU EasyOCR.tflite
EasyOCRDetector Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 29.536 ms 6 - 33 MB FP16 NPU Use Export Script
EasyOCRDetector Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 29.382 ms 37 - 72 MB FP16 NPU EasyOCR.onnx
EasyOCRDetector SA7255P ADP SA7255P TFLITE 2113.846 ms 12 - 41 MB FP16 NPU EasyOCR.tflite
EasyOCRDetector SA7255P ADP SA7255P QNN 2109.747 ms 0 - 10 MB FP16 NPU Use Export Script
EasyOCRDetector SA8255 (Proxy) SA8255P Proxy TFLITE 41.614 ms 11 - 148 MB FP16 NPU EasyOCR.tflite
EasyOCRDetector SA8255 (Proxy) SA8255P Proxy QNN 38.355 ms 6 - 8 MB FP16 NPU Use Export Script
EasyOCRDetector SA8295P ADP SA8295P TFLITE 78.417 ms 16 - 48 MB FP16 NPU EasyOCR.tflite
EasyOCRDetector SA8295P ADP SA8295P QNN 74.968 ms 0 - 18 MB FP16 NPU Use Export Script
EasyOCRDetector SA8650 (Proxy) SA8650P Proxy TFLITE 40.593 ms 12 - 141 MB FP16 NPU EasyOCR.tflite
EasyOCRDetector SA8650 (Proxy) SA8650P Proxy QNN 39.059 ms 6 - 8 MB FP16 NPU Use Export Script
EasyOCRDetector SA8775P ADP SA8775P TFLITE 88.523 ms 16 - 45 MB FP16 NPU EasyOCR.tflite
EasyOCRDetector SA8775P ADP SA8775P QNN 84.948 ms 1 - 11 MB FP16 NPU Use Export Script
EasyOCRDetector QCS8275 (Proxy) QCS8275 Proxy TFLITE 2113.846 ms 12 - 41 MB FP16 NPU EasyOCR.tflite
EasyOCRDetector QCS8275 (Proxy) QCS8275 Proxy QNN 2109.747 ms 0 - 10 MB FP16 NPU Use Export Script
EasyOCRDetector QCS8550 (Proxy) QCS8550 Proxy TFLITE 41.383 ms 10 - 144 MB FP16 NPU EasyOCR.tflite
EasyOCRDetector QCS8550 (Proxy) QCS8550 Proxy QNN 38.101 ms 6 - 8 MB FP16 NPU Use Export Script
EasyOCRDetector QCS9075 (Proxy) QCS9075 Proxy TFLITE 88.523 ms 16 - 45 MB FP16 NPU EasyOCR.tflite
EasyOCRDetector QCS9075 (Proxy) QCS9075 Proxy QNN 84.948 ms 1 - 11 MB FP16 NPU Use Export Script
EasyOCRDetector QCS8450 (Proxy) QCS8450 Proxy TFLITE 74.593 ms 16 - 76 MB FP16 NPU EasyOCR.tflite
EasyOCRDetector QCS8450 (Proxy) QCS8450 Proxy QNN 70.247 ms 6 - 36 MB FP16 NPU Use Export Script
EasyOCRDetector Snapdragon X Elite CRD Snapdragon® X Elite QNN 38.767 ms 6 - 6 MB FP16 NPU Use Export Script
EasyOCRDetector Snapdragon X Elite CRD Snapdragon® X Elite ONNX 40.377 ms 66 - 66 MB FP16 NPU EasyOCR.onnx
EasyOCRRecognizer Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 118.317 ms 8 - 11 MB FP32 CPU EasyOCR.tflite
EasyOCRRecognizer Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 23.77 ms 0 - 104 MB FP16 NPU EasyOCR.so
EasyOCRRecognizer Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 23.218 ms 0 - 25 MB FP16 NPU EasyOCR.onnx
EasyOCRRecognizer Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 112.593 ms 4 - 25 MB FP32 CPU EasyOCR.tflite
EasyOCRRecognizer Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 17.437 ms 0 - 433 MB FP16 NPU EasyOCR.so
EasyOCRRecognizer Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 15.887 ms 0 - 19 MB FP16 NPU EasyOCR.onnx
EasyOCRRecognizer Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 104.512 ms 20 - 35 MB FP32 CPU EasyOCR.tflite
EasyOCRRecognizer Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 18.72 ms 0 - 427 MB FP16 NPU Use Export Script
EasyOCRRecognizer Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 14.137 ms 0 - 12 MB FP16 NPU EasyOCR.onnx
EasyOCRRecognizer SA7255P ADP SA7255P TFLITE 551.941 ms 9 - 19 MB FP32 CPU EasyOCR.tflite
EasyOCRRecognizer SA7255P ADP SA7255P QNN 282.107 ms 0 - 9 MB FP16 NPU Use Export Script
EasyOCRRecognizer SA8255 (Proxy) SA8255P Proxy TFLITE 133.823 ms 8 - 12 MB FP32 CPU EasyOCR.tflite
EasyOCRRecognizer SA8255 (Proxy) SA8255P Proxy QNN 23.269 ms 0 - 2 MB FP16 NPU Use Export Script
EasyOCRRecognizer SA8295P ADP SA8295P TFLITE 219.098 ms 7 - 25 MB FP32 CPU EasyOCR.tflite
EasyOCRRecognizer SA8295P ADP SA8295P QNN 39.202 ms 0 - 18 MB FP16 NPU Use Export Script
EasyOCRRecognizer SA8650 (Proxy) SA8650P Proxy TFLITE 133.828 ms 1 - 4 MB FP32 CPU EasyOCR.tflite
EasyOCRRecognizer SA8650 (Proxy) SA8650P Proxy QNN 23.263 ms 0 - 2 MB FP16 NPU Use Export Script
EasyOCRRecognizer SA8775P ADP SA8775P TFLITE 409.932 ms 8 - 18 MB FP32 CPU EasyOCR.tflite
EasyOCRRecognizer SA8775P ADP SA8775P QNN 31.338 ms 0 - 10 MB FP16 NPU Use Export Script
EasyOCRRecognizer QCS8275 (Proxy) QCS8275 Proxy TFLITE 551.941 ms 9 - 19 MB FP32 CPU EasyOCR.tflite
EasyOCRRecognizer QCS8275 (Proxy) QCS8275 Proxy QNN 282.107 ms 0 - 9 MB FP16 NPU Use Export Script
EasyOCRRecognizer QCS8550 (Proxy) QCS8550 Proxy TFLITE 128.382 ms 8 - 10 MB FP32 CPU EasyOCR.tflite
EasyOCRRecognizer QCS8550 (Proxy) QCS8550 Proxy QNN 23.512 ms 0 - 3 MB FP16 NPU Use Export Script
EasyOCRRecognizer QCS9075 (Proxy) QCS9075 Proxy TFLITE 409.932 ms 8 - 18 MB FP32 CPU EasyOCR.tflite
EasyOCRRecognizer QCS9075 (Proxy) QCS9075 Proxy QNN 31.338 ms 0 - 10 MB FP16 NPU Use Export Script
EasyOCRRecognizer QCS8450 (Proxy) QCS8450 Proxy TFLITE 148.637 ms 2 - 20 MB FP32 CPU EasyOCR.tflite
EasyOCRRecognizer QCS8450 (Proxy) QCS8450 Proxy QNN 36.268 ms 0 - 171 MB FP16 NPU Use Export Script
EasyOCRRecognizer Snapdragon X Elite CRD Snapdragon® X Elite QNN 24.574 ms 0 - 0 MB FP16 NPU Use Export Script
EasyOCRRecognizer Snapdragon X Elite CRD Snapdragon® X Elite ONNX 19.464 ms 0 - 0 MB FP16 NPU EasyOCR.onnx

Installation

Install the package via pip:

pip install "qai-hub-models[easyocr]"

Configure Qualcomm® AI Hub to run this model on a cloud-hosted device

Sign-in to Qualcomm® AI Hub with your Qualcomm® ID. Once signed in navigate to Account -> Settings -> API Token.

With this API token, you can configure your client to run models on the cloud hosted devices.

qai-hub configure --api_token API_TOKEN

Navigate to docs for more information.

Demo off target

The package contains a simple end-to-end demo that downloads pre-trained weights and runs this model on a sample input.

python -m qai_hub_models.models.easyocr.demo

The above demo runs a reference implementation of pre-processing, model inference, and post processing.

NOTE: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above).

%run -m qai_hub_models.models.easyocr.demo

Run model on a cloud-hosted device

In addition to the demo, you can also run the model on a cloud-hosted Qualcomm® device. This script does the following:

  • Performance check on-device on a cloud-hosted device
  • Downloads compiled assets that can be deployed on-device for Android.
  • Accuracy check between PyTorch and on-device outputs.
python -m qai_hub_models.models.easyocr.export

Profiling Results
------------------------------------------------------------
EasyOCRDetector
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 41.2                   
Estimated peak memory usage (MB): [10, 204]              
Total # Ops                     : 42                     
Compute Unit(s)                 : NPU (42 ops)           

------------------------------------------------------------
EasyOCRRecognizer
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 118.3                  
Estimated peak memory usage (MB): [8, 11]                
Total # Ops                     : 136                    
Compute Unit(s)                 : CPU (136 ops)

How does this work?

This export script leverages Qualcomm® AI Hub to optimize, validate, and deploy this model on-device. Lets go through each step below in detail:

Step 1: Compile model for on-device deployment

To compile a PyTorch model for on-device deployment, we first trace the model in memory using the jit.trace and then call the submit_compile_job API.

import torch

import qai_hub as hub
from qai_hub_models.models.easyocr import Model

# Load the model
torch_model = Model.from_pretrained()

# Device
device = hub.Device("Samsung Galaxy S24")

# Trace model
input_shape = torch_model.get_input_spec()
sample_inputs = torch_model.sample_inputs()

pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])

# Compile model on a specific device
compile_job = hub.submit_compile_job(
    model=pt_model,
    device=device,
    input_specs=torch_model.get_input_spec(),
)

# Get target model to run on-device
target_model = compile_job.get_target_model()

Step 2: Performance profiling on cloud-hosted device

After compiling models from step 1. Models can be profiled model on-device using the target_model. Note that this scripts runs the model on a device automatically provisioned in the cloud. Once the job is submitted, you can navigate to a provided job URL to view a variety of on-device performance metrics.

profile_job = hub.submit_profile_job(
    model=target_model,
    device=device,
)

Step 3: Verify on-device accuracy

To verify the accuracy of the model on-device, you can run on-device inference on sample input data on the same cloud hosted device.

input_data = torch_model.sample_inputs()
inference_job = hub.submit_inference_job(
    model=target_model,
    device=device,
    inputs=input_data,
)
    on_device_output = inference_job.download_output_data()

With the output of the model, you can compute like PSNR, relative errors or spot check the output with expected output.

Note: This on-device profiling and inference requires access to Qualcomm® AI Hub. Sign up for access.

Deploying compiled model to Android

The models can be deployed using multiple runtimes:

  • TensorFlow Lite (.tflite export): This tutorial provides a guide to deploy the .tflite model in an Android application.

  • QNN (.so export ): This sample app provides instructions on how to use the .so shared library in an Android application.

View on Qualcomm® AI Hub

Get more details on EasyOCR's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of EasyOCR can be found here.
  • The license for the compiled assets for on-device deployment 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. 🙋 Ask for provider support