🚀 devanagari_PP-OCRv3_mobile_rec
devanagari_PP-OCRv3_mobile_rec is a text line recognition model within the PP-OCRv3_rec series, developed by the PaddleOCR team. It's an Devanagari-specific model trained based on PP-OCRv3_mobile_rec, supporting Devanagari recognition.
🚀 Quick Start
📦 Installation
- PaddlePaddle
Please refer to the following commands to install PaddlePaddle using pip:
python -m pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/
python -m pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
python -m pip install paddlepaddle==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/
For details about PaddlePaddle installation, please refer to the PaddlePaddle official website.
- PaddleOCR
Install the latest version of the PaddleOCR inference package from PyPI:
python -m pip install paddleocr
💻 Usage Examples
Basic Usage
You can quickly experience the functionality with a single command:
paddleocr text_recognition \
--model_name devanagari_PP-OCRv3_mobile_rec \
-i https://cdn-uploads.huggingface.co/production/uploads/681c1ecd9539bdde5ae1733c/lpNu16sSBMXoRDt_DmUm6.png
You can also integrate the model inference of the text recognition module into your project. Before running the following code, please download the sample image to your local machine.
from paddleocr import TextRecognition
model = TextRecognition(model_name="devanagari_PP-OCRv3_mobile_rec")
output = model.predict(input="lpNu16sSBMXoRDt_DmUm6.png", batch_size=1)
for res in output:
res.print()
res.save_to_img(save_path="./output/")
res.save_to_json(save_path="./output/res.json")
After running, the obtained result is as follows:
{'res': {'input_path': '/root/.paddlex/predict_input/lpNu16sSBMXoRDt_DmUm6.png', 'page_index': None, 'rec_text': 'बहुपङिकतपाठपरीआापकर', 'rec_score': 0.9564684629440308}}
For details about usage command and descriptions of parameters, please refer to the Document.
Advanced Usage
The ability of a single model is limited. But the pipeline consists of several models can provide more capacity to resolve difficult problems in real-world scenarios.
PP-OCRv3
The general OCR pipeline is used to solve text recognition tasks by extracting text information from images and outputting it in string format. And there are 5 modules in the pipeline:
- Document Image Orientation Classification Module (Optional)
- Text Image Unwarping Module (Optional)
- Text Line Orientation Classification Module (Optional)
- Text Detection Module
- Text Recognition Module
Run a single command to quickly experience the OCR pipeline:
paddleocr ocr -i https://cdn-uploads.huggingface.co/production/uploads/681c1ecd9539bdde5ae1733c/_5b764by68-a295JP4y1q.png \
--text_recognition_model_name devanagari_PP-OCRv3_mobile_rec \
--use_doc_orientation_classify False \
--use_doc_unwarping False \
--use_textline_orientation True \
--save_path ./output \
--device gpu:0
Results are printed to the terminal:
{'res': {'input_path': '/root/.paddlex/predict_input/_5b764by68-a295JP4y1q.png', 'page_index': None, 'model_settings': {'use_doc_preprocessor': True, 'use_textline_orientation': True}, 'doc_preprocessor_res': {'input_path': None, 'page_index': None, 'model_settings': {'use_doc_orientation_classify': False, 'use_doc_unwarping': False}, 'angle': -1}, 'dt_polys': array([[[ 11, 8],
...,
[ 11, 42]],
...,
[[ 9, 88],
...,
[ 9, 120]]], dtype=int16), 'text_det_params': {'limit_side_len': 64, 'limit_type': 'min', 'thresh': 0.3, 'max_side_limit': 4000, 'box_thresh': 0.6, 'unclip_ratio': 1.5}, 'text_type': 'general', 'textline_orientation_angles': array([0, ..., 1]), 'text_rec_score_thresh': 0.0, 'rec_texts': ['िसिरिलक', 'IBlhhh?', 'H॰'], 'rec_scores': array([0.98613745, ..., 0.5240429 ]), 'rec_polys': array([[[ 11, 8],
...,
[ 11, 42]],
...,
[[ 9, 88],
...,
[ 9, 120]]], dtype=int16), 'rec_boxes': array([[ 11, ..., 42],
...,
[ 9, ..., 120]], dtype=int16)}}
The command-line method is for quick experience. For project integration, also only a few codes are needed as well:
from paddleocr import PaddleOCR
ocr = PaddleOCR(
text_recognition_model_name="devanagari_PP-OCRv3_mobile_rec",
use_doc_orientation_classify=False,
use_doc_unwarping=False,
use_textline_orientation=True,
device="gpu:0",
)
result = ocr.predict("https://cdn-uploads.huggingface.co/production/uploads/681c1ecd9539bdde5ae1733c/c3hSldnYVQXp48T5V0Ze4.png")
for res in result:
res.print()
res.save_to_img("output")
res.save_to_json("output")
The default model used in pipeline is PP-OCRv5_server_rec
, so it is needed that specifing to devanagari_PP-OCRv3_mobile_rec
by argument text_recognition_model_name
. And you can also use the local model file by argument text_recognition_model_dir
. For details about usage command and descriptions of parameters, please refer to the Document.
✨ Features
The key accuracy metrics are as follow:
Property |
Details |
Model |
devanagari_PP-OCRv3_mobile_rec |
Recognition Avg Accuracy(%) |
96.44 |
Model Storage Size (M) |
7.9 M |
Introduction |
An ultra-lightweight Devanagari alphabet recognition model trained based on the PP-OCRv3 recognition model, supporting Devanagari alphabet and numeric character recognition. |
Note: If any character (including punctuation) in a line was incorrect, the entire line was marked as wrong. This ensures higher accuracy in practical applications.
📄 License
This project is licensed under the Apache-2.0 license.
📚 Documentation