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: Model_use_case.image_to_text
• Model Stats:
  • Model checkpoint: easyocr-small-stage1
  • Input resolution: 608x800
  • Number of parameters (EasyOCRDetector): 20.8M
  • Model size (EasyOCRDetector) (float): 79.2 MB
  • Number of parameters (EasyOCRRecognizer): 3.84M
  • Model size (EasyOCRRecognizer) (float): 14.7 MB

Model	Precision	Device	Chipset	Target Runtime	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit	Target Model
EasyOCRDetector	float	QCS8275 (Proxy)	Qualcomm® QCS8275 (Proxy)	TFLITE	268.568 ms	1 - 149 MB	NPU	EasyOCR.tflite
EasyOCRDetector	float	QCS8275 (Proxy)	Qualcomm® QCS8275 (Proxy)	QNN_DLC	271.624 ms	5 - 143 MB	NPU	EasyOCR.dlc
EasyOCRDetector	float	QCS8450 (Proxy)	Qualcomm® QCS8450 (Proxy)	TFLITE	76.961 ms	0 - 228 MB	NPU	EasyOCR.tflite
EasyOCRDetector	float	QCS8450 (Proxy)	Qualcomm® QCS8450 (Proxy)	QNN_DLC	80.046 ms	6 - 240 MB	NPU	EasyOCR.dlc
EasyOCRDetector	float	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	TFLITE	36.884 ms	1 - 4 MB	NPU	EasyOCR.tflite
EasyOCRDetector	float	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	QNN_DLC	39.479 ms	6 - 8 MB	NPU	EasyOCR.dlc
EasyOCRDetector	float	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	ONNX	37.137 ms	0 - 45 MB	NPU	EasyOCR.onnx.zip
EasyOCRDetector	float	QCS9075 (Proxy)	Qualcomm® QCS9075 (Proxy)	TFLITE	67.922 ms	1 - 149 MB	NPU	EasyOCR.tflite
EasyOCRDetector	float	QCS9075 (Proxy)	Qualcomm® QCS9075 (Proxy)	QNN_DLC	324.119 ms	1 - 140 MB	NPU	EasyOCR.dlc
EasyOCRDetector	float	SA7255P ADP	Qualcomm® SA7255P	TFLITE	268.568 ms	1 - 149 MB	NPU	EasyOCR.tflite
EasyOCRDetector	float	SA7255P ADP	Qualcomm® SA7255P	QNN_DLC	271.624 ms	5 - 143 MB	NPU	EasyOCR.dlc
EasyOCRDetector	float	SA8255 (Proxy)	Qualcomm® SA8255P (Proxy)	TFLITE	36.724 ms	1 - 4 MB	NPU	EasyOCR.tflite
EasyOCRDetector	float	SA8255 (Proxy)	Qualcomm® SA8255P (Proxy)	QNN_DLC	39.333 ms	6 - 8 MB	NPU	EasyOCR.dlc
EasyOCRDetector	float	SA8295P ADP	Qualcomm® SA8295P	TFLITE	74.923 ms	1 - 156 MB	NPU	EasyOCR.tflite
EasyOCRDetector	float	SA8295P ADP	Qualcomm® SA8295P	QNN_DLC	77.451 ms	0 - 157 MB	NPU	EasyOCR.dlc
EasyOCRDetector	float	SA8650 (Proxy)	Qualcomm® SA8650P (Proxy)	TFLITE	37.318 ms	1 - 3 MB	NPU	EasyOCR.tflite
EasyOCRDetector	float	SA8650 (Proxy)	Qualcomm® SA8650P (Proxy)	QNN_DLC	39.471 ms	6 - 8 MB	NPU	EasyOCR.dlc
EasyOCRDetector	float	SA8775P ADP	Qualcomm® SA8775P	TFLITE	67.922 ms	1 - 149 MB	NPU	EasyOCR.tflite
EasyOCRDetector	float	SA8775P ADP	Qualcomm® SA8775P	QNN_DLC	324.119 ms	1 - 140 MB	NPU	EasyOCR.dlc
EasyOCRDetector	float	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	TFLITE	26.908 ms	0 - 225 MB	NPU	EasyOCR.tflite
EasyOCRDetector	float	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	QNN_DLC	28.022 ms	6 - 221 MB	NPU	EasyOCR.dlc
EasyOCRDetector	float	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	ONNX	27.23 ms	7 - 194 MB	NPU	EasyOCR.onnx.zip
EasyOCRDetector	float	Samsung Galaxy S25	Snapdragon® 8 Elite For Galaxy Mobile	TFLITE	21.616 ms	1 - 152 MB	NPU	EasyOCR.tflite
EasyOCRDetector	float	Samsung Galaxy S25	Snapdragon® 8 Elite For Galaxy Mobile	QNN_DLC	22.706 ms	6 - 143 MB	NPU	EasyOCR.dlc
EasyOCRDetector	float	Samsung Galaxy S25	Snapdragon® 8 Elite For Galaxy Mobile	ONNX	21.874 ms	3 - 117 MB	NPU	EasyOCR.onnx.zip
EasyOCRDetector	float	Snapdragon 8 Elite Gen 5 QRD	Snapdragon® 8 Elite Gen5 Mobile	TFLITE	17.112 ms	1 - 152 MB	NPU	EasyOCR.tflite
EasyOCRDetector	float	Snapdragon 8 Elite Gen 5 QRD	Snapdragon® 8 Elite Gen5 Mobile	QNN_DLC	19.421 ms	6 - 150 MB	NPU	EasyOCR.dlc
EasyOCRDetector	float	Snapdragon 8 Elite Gen 5 QRD	Snapdragon® 8 Elite Gen5 Mobile	ONNX	16.504 ms	7 - 126 MB	NPU	EasyOCR.onnx.zip
EasyOCRDetector	float	Snapdragon X Elite CRD	Snapdragon® X Elite	QNN_DLC	40.807 ms	6 - 6 MB	NPU	EasyOCR.dlc
EasyOCRDetector	float	Snapdragon X Elite CRD	Snapdragon® X Elite	ONNX	38.421 ms	35 - 35 MB	NPU	EasyOCR.onnx.zip
EasyOCRRecognizer	float	QCS8275 (Proxy)	Qualcomm® QCS8275 (Proxy)	TFLITE	481.451 ms	8 - 17 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	float	QCS8275 (Proxy)	Qualcomm® QCS8275 (Proxy)	QNN_DLC	63.957 ms	0 - 739 MB	NPU	EasyOCR.dlc
EasyOCRRecognizer	float	QCS8450 (Proxy)	Qualcomm® QCS8450 (Proxy)	TFLITE	124.592 ms	9 - 31 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	float	QCS8450 (Proxy)	Qualcomm® QCS8450 (Proxy)	QNN_DLC	38.136 ms	0 - 434 MB	NPU	EasyOCR.dlc
EasyOCRRecognizer	float	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	TFLITE	98.988 ms	8 - 11 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	float	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	QNN_DLC	25.01 ms	0 - 3 MB	NPU	EasyOCR.dlc
EasyOCRRecognizer	float	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	ONNX	35.1 ms	0 - 19 MB	NPU	EasyOCR.onnx.zip
EasyOCRRecognizer	float	QCS9075 (Proxy)	Qualcomm® QCS9075 (Proxy)	TFLITE	379.045 ms	8 - 18 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	float	QCS9075 (Proxy)	Qualcomm® QCS9075 (Proxy)	QNN_DLC	29.013 ms	0 - 739 MB	NPU	EasyOCR.dlc
EasyOCRRecognizer	float	SA7255P ADP	Qualcomm® SA7255P	TFLITE	481.451 ms	8 - 17 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	float	SA7255P ADP	Qualcomm® SA7255P	QNN_DLC	63.957 ms	0 - 739 MB	NPU	EasyOCR.dlc
EasyOCRRecognizer	float	SA8255 (Proxy)	Qualcomm® SA8255P (Proxy)	TFLITE	99.248 ms	8 - 11 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	float	SA8255 (Proxy)	Qualcomm® SA8255P (Proxy)	QNN_DLC	25.118 ms	0 - 3 MB	NPU	EasyOCR.dlc
EasyOCRRecognizer	float	SA8295P ADP	Qualcomm® SA8295P	TFLITE	224.461 ms	7 - 24 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	float	SA8295P ADP	Qualcomm® SA8295P	QNN_DLC	40.877 ms	0 - 385 MB	NPU	EasyOCR.dlc
EasyOCRRecognizer	float	SA8650 (Proxy)	Qualcomm® SA8650P (Proxy)	TFLITE	105.965 ms	7 - 10 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	float	SA8650 (Proxy)	Qualcomm® SA8650P (Proxy)	QNN_DLC	24.739 ms	0 - 3 MB	NPU	EasyOCR.dlc
EasyOCRRecognizer	float	SA8775P ADP	Qualcomm® SA8775P	TFLITE	379.045 ms	8 - 18 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	float	SA8775P ADP	Qualcomm® SA8775P	QNN_DLC	29.013 ms	0 - 739 MB	NPU	EasyOCR.dlc
EasyOCRRecognizer	float	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	TFLITE	95.776 ms	9 - 29 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	float	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	QNN_DLC	18.798 ms	0 - 871 MB	NPU	EasyOCR.dlc
EasyOCRRecognizer	float	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	ONNX	26.128 ms	1 - 516 MB	NPU	EasyOCR.onnx.zip
EasyOCRRecognizer	float	Samsung Galaxy S25	Snapdragon® 8 Elite For Galaxy Mobile	TFLITE	118.983 ms	10 - 26 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	float	Samsung Galaxy S25	Snapdragon® 8 Elite For Galaxy Mobile	QNN_DLC	16.278 ms	0 - 742 MB	NPU	EasyOCR.dlc
EasyOCRRecognizer	float	Samsung Galaxy S25	Snapdragon® 8 Elite For Galaxy Mobile	ONNX	21.306 ms	1 - 451 MB	NPU	EasyOCR.onnx.zip
EasyOCRRecognizer	float	Snapdragon 8 Elite Gen 5 QRD	Snapdragon® 8 Elite Gen5 Mobile	TFLITE	69.568 ms	17 - 29 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	float	Snapdragon 8 Elite Gen 5 QRD	Snapdragon® 8 Elite Gen5 Mobile	QNN_DLC	17.179 ms	0 - 802 MB	NPU	EasyOCR.dlc
EasyOCRRecognizer	float	Snapdragon 8 Elite Gen 5 QRD	Snapdragon® 8 Elite Gen5 Mobile	ONNX	19.862 ms	0 - 478 MB	NPU	EasyOCR.onnx.zip
EasyOCRRecognizer	float	Snapdragon X Elite CRD	Snapdragon® X Elite	QNN_DLC	24.76 ms	0 - 0 MB	NPU	EasyOCR.dlc
EasyOCRRecognizer	float	Snapdragon X Elite CRD	Snapdragon® X Elite	ONNX	35.96 ms	12 - 12 MB	NPU	EasyOCR.onnx.zip
EasyOCRDetector	w8a8	Dragonwing Q-6690 MTP	Qualcomm® Qcm6690	TFLITE	240.483 ms	0 - 190 MB	NPU	EasyOCR.tflite
EasyOCRDetector	w8a8	Dragonwing RB3 Gen 2 Vision Kit	Qualcomm® QCS6490	TFLITE	47.487 ms	0 - 24 MB	NPU	EasyOCR.tflite
EasyOCRDetector	w8a8	QCS8275 (Proxy)	Qualcomm® QCS8275 (Proxy)	TFLITE	36.011 ms	0 - 136 MB	NPU	EasyOCR.tflite
EasyOCRDetector	w8a8	QCS8450 (Proxy)	Qualcomm® QCS8450 (Proxy)	TFLITE	14.851 ms	0 - 193 MB	NPU	EasyOCR.tflite
EasyOCRDetector	w8a8	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	TFLITE	9.663 ms	0 - 2 MB	NPU	EasyOCR.tflite
EasyOCRDetector	w8a8	QCS9075 (Proxy)	Qualcomm® QCS9075 (Proxy)	TFLITE	10.193 ms	0 - 137 MB	NPU	EasyOCR.tflite
EasyOCRDetector	w8a8	SA7255P ADP	Qualcomm® SA7255P	TFLITE	36.011 ms	0 - 136 MB	NPU	EasyOCR.tflite
EasyOCRDetector	w8a8	SA8255 (Proxy)	Qualcomm® SA8255P (Proxy)	TFLITE	9.675 ms	2 - 4 MB	NPU	EasyOCR.tflite
EasyOCRDetector	w8a8	SA8295P ADP	Qualcomm® SA8295P	TFLITE	19.18 ms	0 - 144 MB	NPU	EasyOCR.tflite
EasyOCRDetector	w8a8	SA8650 (Proxy)	Qualcomm® SA8650P (Proxy)	TFLITE	9.669 ms	0 - 3 MB	NPU	EasyOCR.tflite
EasyOCRDetector	w8a8	SA8775P ADP	Qualcomm® SA8775P	TFLITE	10.193 ms	0 - 137 MB	NPU	EasyOCR.tflite
EasyOCRDetector	w8a8	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	TFLITE	7.179 ms	0 - 194 MB	NPU	EasyOCR.tflite
EasyOCRDetector	w8a8	Samsung Galaxy S25	Snapdragon® 8 Elite For Galaxy Mobile	TFLITE	5.748 ms	0 - 137 MB	NPU	EasyOCR.tflite
EasyOCRDetector	w8a8	Snapdragon 7 Gen 4 QRD	Snapdragon® 7 Gen 4 Mobile	TFLITE	18.556 ms	0 - 158 MB	NPU	EasyOCR.tflite
EasyOCRDetector	w8a8	Snapdragon 8 Elite Gen 5 QRD	Snapdragon® 8 Elite Gen5 Mobile	TFLITE	4.279 ms	0 - 138 MB	NPU	EasyOCR.tflite
EasyOCRRecognizer	w8a8	Dragonwing Q-6690 MTP	Qualcomm® Qcm6690	TFLITE	210.388 ms	10 - 24 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	w8a8	Dragonwing RB3 Gen 2 Vision Kit	Qualcomm® QCS6490	TFLITE	226.879 ms	4 - 25 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	w8a8	QCS8275 (Proxy)	Qualcomm® QCS8275 (Proxy)	TFLITE	439.764 ms	8 - 17 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	w8a8	QCS8450 (Proxy)	Qualcomm® QCS8450 (Proxy)	TFLITE	86.814 ms	7 - 29 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	w8a8	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	TFLITE	73.994 ms	6 - 9 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	w8a8	QCS9075 (Proxy)	Qualcomm® QCS9075 (Proxy)	TFLITE	337.174 ms	9 - 19 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	w8a8	SA7255P ADP	Qualcomm® SA7255P	TFLITE	439.764 ms	8 - 17 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	w8a8	SA8255 (Proxy)	Qualcomm® SA8255P (Proxy)	TFLITE	75.985 ms	6 - 16 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	w8a8	SA8295P ADP	Qualcomm® SA8295P	TFLITE	189.089 ms	10 - 27 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	w8a8	SA8650 (Proxy)	Qualcomm® SA8650P (Proxy)	TFLITE	73.048 ms	6 - 9 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	w8a8	SA8775P ADP	Qualcomm® SA8775P	TFLITE	337.174 ms	9 - 19 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	w8a8	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	TFLITE	67.923 ms	7 - 27 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	w8a8	Samsung Galaxy S25	Snapdragon® 8 Elite For Galaxy Mobile	TFLITE	93.259 ms	6 - 21 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	w8a8	Snapdragon 7 Gen 4 QRD	Snapdragon® 7 Gen 4 Mobile	TFLITE	124.982 ms	14 - 30 MB	CPU	EasyOCR.tflite
EasyOCRRecognizer	w8a8	Snapdragon 8 Elite Gen 5 QRD	Snapdragon® 8 Elite Gen5 Mobile	TFLITE	53.799 ms	15 - 27 MB	CPU	EasyOCR.tflite

Installation

Install the package via pip:

# NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported.
pip install "qai-hub-models[easyocr]"

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

Sign-in to Qualcomm® AI Hub Workbench 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

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 S25")

# 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 Workbench. 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.

References

• Source Model Implementation

Community

• Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
• For questions or feedback please reach out to us.