qualcomm
/

EasyOCR

+---
+library_name: pytorch
+license: apache-2.0
+tags:
+- android
+pipeline_tag: image-to-text
+---
+![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/easyocr/web-assets/model_demo.png)
+# 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](https://github.com/JaidedAI/EasyOCR).
+This repository provides scripts to run EasyOCR on Qualcomm® devices.
+More details on model performance across various devices, can be found
+[here](https://aihub.qualcomm.com/models/easyocr).
+### 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 | 41.189 ms | 0 - 136 MB | FP16 | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRDetector.tflite) |
+| EasyOCRDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 39.017 ms | 6 - 9 MB | FP16 | NPU | [EasyOCR.so](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRDetector.so) |
+| EasyOCRDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 40.015 ms | 34 - 181 MB | FP16 | NPU | [EasyOCR.onnx](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRDetector.onnx) |
+| EasyOCRDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 30.181 ms | 14 - 45 MB | FP16 | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRDetector.tflite) |
+| EasyOCRDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 29.323 ms | 6 - 25 MB | FP16 | NPU | [EasyOCR.so](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRDetector.so) |
+| EasyOCRDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 29.584 ms | 38 - 75 MB | FP16 | NPU | [EasyOCR.onnx](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRDetector.onnx) |
+| EasyOCRDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 28.753 ms | 15 - 45 MB | FP16 | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRDetector.tflite) |
+| EasyOCRDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 24.26 ms | 6 - 36 MB | FP16 | NPU | Use Export Script |
+| EasyOCRDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 28.097 ms | 43 - 78 MB | FP16 | NPU | [EasyOCR.onnx](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRDetector.onnx) |
+| EasyOCRDetector | SA7255P ADP | SA7255P | TFLITE | 2113.678 ms | 3 - 28 MB | FP16 | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRDetector.tflite) |
+| EasyOCRDetector | SA7255P ADP | SA7255P | QNN | 2111.684 ms | 0 - 8 MB | FP16 | NPU | Use Export Script |
+| EasyOCRDetector | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 41.731 ms | 0 - 97 MB | FP16 | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRDetector.tflite) |
+| EasyOCRDetector | SA8255 (Proxy) | SA8255P Proxy | QNN | 38.998 ms | 6 - 8 MB | FP16 | NPU | Use Export Script |
+| EasyOCRDetector | SA8295P ADP | SA8295P | TFLITE | 78.45 ms | 16 - 42 MB | FP16 | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRDetector.tflite) |
+| EasyOCRDetector | SA8295P ADP | SA8295P | QNN | 76.549 ms | 0 - 11 MB | FP16 | NPU | Use Export Script |
+| EasyOCRDetector | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 42.824 ms | 0 - 145 MB | FP16 | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRDetector.tflite) |
+| EasyOCRDetector | SA8650 (Proxy) | SA8650P Proxy | QNN | 40.764 ms | 6 - 8 MB | FP16 | NPU | Use Export Script |
+| EasyOCRDetector | SA8775P ADP | SA8775P | TFLITE | 88.536 ms | 16 - 41 MB | FP16 | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRDetector.tflite) |
+| EasyOCRDetector | SA8775P ADP | SA8775P | QNN | 86.522 ms | 1 - 9 MB | FP16 | NPU | Use Export Script |
+| EasyOCRDetector | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 2113.678 ms | 3 - 28 MB | FP16 | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRDetector.tflite) |
+| EasyOCRDetector | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 2111.684 ms | 0 - 8 MB | FP16 | NPU | Use Export Script |
+| EasyOCRDetector | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 41.678 ms | 0 - 126 MB | FP16 | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRDetector.tflite) |
+| EasyOCRDetector | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 39.278 ms | 6 - 8 MB | FP16 | NPU | Use Export Script |
+| EasyOCRDetector | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 88.536 ms | 16 - 41 MB | FP16 | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRDetector.tflite) |
+| EasyOCRDetector | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 86.522 ms | 1 - 9 MB | FP16 | NPU | Use Export Script |
+| EasyOCRDetector | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 80.295 ms | 16 - 48 MB | FP16 | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRDetector.tflite) |
+| EasyOCRDetector | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 69.9 ms | 6 - 37 MB | FP16 | NPU | Use Export Script |
+| EasyOCRDetector | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 39.87 ms | 6 - 6 MB | FP16 | NPU | Use Export Script |
+| EasyOCRDetector | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 41.319 ms | 66 - 66 MB | FP16 | NPU | [EasyOCR.onnx](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRDetector.onnx) |
+| EasyOCRRecognizer | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 109.812 ms | 6 - 8 MB | FP32 | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRRecognizer.tflite) |
+| EasyOCRRecognizer | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 20.483 ms | 0 - 3 MB | FP16 | NPU | [EasyOCR.so](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRRecognizer.so) |
+| EasyOCRRecognizer | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 21.731 ms | 0 - 24 MB | FP16 | NPU | [EasyOCR.onnx](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRRecognizer.onnx) |
+| EasyOCRRecognizer | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 108.852 ms | 2 - 20 MB | FP32 | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRRecognizer.tflite) |
+| EasyOCRRecognizer | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 14.237 ms | 0 - 16 MB | FP16 | NPU | [EasyOCR.so](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRRecognizer.so) |
+| EasyOCRRecognizer | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 16.212 ms | 1 - 24 MB | FP16 | NPU | [EasyOCR.onnx](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRRecognizer.onnx) |
+| EasyOCRRecognizer | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 107.149 ms | 14 - 30 MB | FP32 | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRRecognizer.tflite) |
+| EasyOCRRecognizer | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 20.63 ms | 0 - 346 MB | FP16 | NPU | Use Export Script |
+| EasyOCRRecognizer | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 17.677 ms | 0 - 18 MB | FP16 | NPU | [EasyOCR.onnx](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRRecognizer.onnx) |
+| EasyOCRRecognizer | SA7255P ADP | SA7255P | TFLITE | 565.404 ms | 9 - 17 MB | FP32 | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRRecognizer.tflite) |
+| EasyOCRRecognizer | SA7255P ADP | SA7255P | QNN | 285.155 ms | 0 - 8 MB | FP16 | NPU | Use Export Script |
+| EasyOCRRecognizer | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 124.344 ms | 9 - 11 MB | FP32 | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRRecognizer.tflite) |
+| EasyOCRRecognizer | SA8255 (Proxy) | SA8255P Proxy | QNN | 20.321 ms | 0 - 3 MB | FP16 | NPU | Use Export Script |
+| EasyOCRRecognizer | SA8295P ADP | SA8295P | TFLITE | 214.709 ms | 8 - 18 MB | FP32 | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRRecognizer.tflite) |
+| EasyOCRRecognizer | SA8295P ADP | SA8295P | QNN | 30.834 ms | 0 - 12 MB | FP16 | NPU | Use Export Script |
+| EasyOCRRecognizer | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 101.784 ms | 7 - 11 MB | FP32 | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRRecognizer.tflite) |
+| EasyOCRRecognizer | SA8650 (Proxy) | SA8650P Proxy | QNN | 20.407 ms | 0 - 3 MB | FP16 | NPU | Use Export Script |
+| EasyOCRRecognizer | SA8775P ADP | SA8775P | TFLITE | 415.153 ms | 6 - 14 MB | FP32 | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRRecognizer.tflite) |
+| EasyOCRRecognizer | SA8775P ADP | SA8775P | QNN | 29.021 ms | 0 - 7 MB | FP16 | NPU | Use Export Script |
+| EasyOCRRecognizer | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 565.404 ms | 9 - 17 MB | FP32 | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRRecognizer.tflite) |
+| EasyOCRRecognizer | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 285.155 ms | 0 - 8 MB | FP16 | NPU | Use Export Script |
+| EasyOCRRecognizer | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 108.193 ms | 7 - 10 MB | FP32 | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRRecognizer.tflite) |
+| EasyOCRRecognizer | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 20.315 ms | 0 - 3 MB | FP16 | NPU | Use Export Script |
+| EasyOCRRecognizer | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 415.153 ms | 6 - 14 MB | FP32 | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRRecognizer.tflite) |
+| EasyOCRRecognizer | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 29.021 ms | 0 - 7 MB | FP16 | NPU | Use Export Script |
+| EasyOCRRecognizer | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 210.333 ms | 9 - 25 MB | FP32 | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRRecognizer.tflite) |
+| EasyOCRRecognizer | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 34.309 ms | 0 - 151 MB | FP16 | NPU | Use Export Script |
+| EasyOCRRecognizer | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 21.364 ms | 0 - 0 MB | FP16 | NPU | Use Export Script |
+| EasyOCRRecognizer | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 19.37 ms | 0 - 0 MB | FP16 | NPU | [EasyOCR.onnx](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCRRecognizer.onnx) |
+## Installation
+Install the package via pip:
+```bash
+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](https://app.aihub.qualcomm.com/) 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.
+```bash
+qai-hub configure --api_token API_TOKEN
+```
+Navigate to [docs](https://app.aihub.qualcomm.com/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.
+```bash
+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.
+```bash
+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): [0, 136]
+Total # Ops                     : 42
+Compute Unit(s)                 : NPU (42 ops)
+------------------------------------------------------------
+EasyOCRRecognizer
+Device                          : Samsung Galaxy S23 (13)
+Runtime                         : TFLITE
+Estimated inference time (ms)   : 109.8
+Estimated peak memory usage (MB): [6, 8]
+Total # Ops                     : 136
+Compute Unit(s)                 : CPU (136 ops)
+```
+## How does this work?
+This [export script](https://aihub.qualcomm.com/models/easyocr/qai_hub_models/models/EasyOCR/export.py)
+leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) 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.
+```python
+import torch
+import qai_hub as hub
+from qai_hub_models.models.easyocr import Model
+# Load the model
+model = Model.from_pretrained()
+detector_model = model.detector
+recognizer_model = model.recognizer
+# Device
+device = hub.Device("Samsung Galaxy S23")
+# Trace model
+detector_input_shape = detector_model.get_input_spec()
+detector_sample_inputs = detector_model.sample_inputs()
+traced_detector_model = torch.jit.trace(detector_model, [torch.tensor(data[0]) for _, data in detector_sample_inputs.items()])
+# Compile model on a specific device
+detector_compile_job = hub.submit_compile_job(
+    model=traced_detector_model ,
+    device=device,
+    input_specs=detector_model.get_input_spec(),
+)
+# Get target model to run on-device
+detector_target_model = detector_compile_job.get_target_model()
+# Trace model
+recognizer_input_shape = recognizer_model.get_input_spec()
+recognizer_sample_inputs = recognizer_model.sample_inputs()
+traced_recognizer_model = torch.jit.trace(recognizer_model, [torch.tensor(data[0]) for _, data in recognizer_sample_inputs.items()])
+# Compile model on a specific device
+recognizer_compile_job = hub.submit_compile_job(
+    model=traced_recognizer_model ,
+    device=device,
+    input_specs=recognizer_model.get_input_spec(),
+)
+# Get target model to run on-device
+recognizer_target_model = recognizer_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.
+```python
+detector_profile_job = hub.submit_profile_job(
+    model=detector_target_model,
+    device=device,
+)
+recognizer_profile_job = hub.submit_profile_job(
+    model=recognizer_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.
+```python
+detector_input_data = detector_model.sample_inputs()
+detector_inference_job = hub.submit_inference_job(
+    model=detector_target_model,
+    device=device,
+    inputs=detector_input_data,
+)
+detector_inference_job.download_output_data()
+recognizer_input_data = recognizer_model.sample_inputs()
+recognizer_inference_job = hub.submit_inference_job(
+    model=recognizer_target_model,
+    device=device,
+    inputs=recognizer_input_data,
+)
+recognizer_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](https://myaccount.qualcomm.com/signup).
+## Deploying compiled model to Android
+The models can be deployed using multiple runtimes:
+- TensorFlow Lite (`.tflite` export): [This
+  tutorial](https://www.tensorflow.org/lite/android/quickstart) provides a
+  guide to deploy the .tflite model in an Android application.
+- QNN (`.so` export ): This [sample
+  app](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/sample_app.html)
+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](https://aihub.qualcomm.com/models/easyocr).
+Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
+## License
+* The license for the original implementation of EasyOCR can be found
+  [here](https://github.com/JaidedAI/EasyOCR/blob/master/LICENSE).
+* The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
+## References
+* [None](None)
+* [Source Model Implementation](https://github.com/JaidedAI/EasyOCR)
+## Community
+* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
+* For questions or feedback please [reach out to us](mailto:[email protected]).