Model reference · open weights
devanagari_PP-OCRv5_mobile_rec is an open-weight language model from PaddlePaddle. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | Baidu |
|---|---|
| Published under | PaddlePaddle |
| Type | Language models |
| Task | Image→text |
| Runs with | PaddleOCR |
| Released | 2025-10-16 |
| Popularity | 1k downloads / month |
| Licence | Open weights |
About
devanagari_PP-OCRv5_mobile_rec is one of the PP-OCRv5_rec that are the latest generation text line recognition models developed by PaddleOCR team. It aims to efficiently and accurately support the recognition of Devanagari. The key accuracy metrics are as follow:
| Model | Accuracy (%) |
|---|---|
| devanagari_PP-OCRv5_mobile_rec | 84.96 |
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.
Please refer to the following commands to install PaddlePaddle using pip:
# for CUDA11.8
python -m pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/
# for CUDA12.6
python -m pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
# for CPU
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.
Install the latest version of the PaddleOCR inference package from PyPI:
python -m pip install paddleocr
You can quickly experience the functionality with a single command:
paddleocr text_recognition \
--model_name devanagari_PP-OCRv5_mobile_rec \
-i https://cdn-uploads.huggingface.co/production/uploads/684ad4f6eb7d8ee8f6a92a3a/dtgfI1BdDM7c9BB0X3-xE.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-OCRv5_mobile_rec")
output = model.predict(input="dtgfI1BdDM7c9BB0X3-xE.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/dtgfI1BdDM7c9BB0X3-xE.png', 'page_index': None, 'rec_text': 'कख ग घड', 'rec_score': 0.8845340013504028}}
The visualized image is as follows:
For details about usage command and descriptions of parameters, please refer to the Document.
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.
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:
Run a single command to quickly experience the OCR pipeline:
paddleocr ocr -i https://cdn-uploads.huggingface.co/production/uploads/684ad4f6eb7d8ee8f6a92a3a/4565zt8fsAJ2JCVyP2OEa.png \
--text_recognition_model_name devanagari_PP-OCRv5_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/4565zt8fsAJ2JCVyP2OEa.png', 'page_index': None, 'model_settings': {'use_doc_preprocessor': True, 'use_textline_orientation': False}, '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([[[ 172, 201],
...,
[ 172, 290]],
...,
[[ 795, 2010],
...,
[ 795, 2055]]], shape=(42, 4, 2), 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([-1, ..., -1], shape=(42,)), 'text_rec_score_thresh': 0.0, 'return_word_box': False, 'rec_texts': ['विषय-सूची', 'क्र.सं.', 'विवरण', 'पृष्ठ सं.', '1', 'आरईसी लिमिटेड और आरईसीआईपीएमटी के बारे में', '2-3', '2', 'विदयुत क्षत्र के अधिकारियों के लिए राष्टीय नियमित प्रशिक्षण कार्यक्रम', '4-10', '3', 'विदयुत क्षत्र के अधिकारियों के लिए आरईसी द्वारा प्रायोजित प्रशिक्षण कार्यक्रम', '11-14', 'आरईसीआईपीएमटी/ऑफ-कैंपस में आरईसी के कर्मचारियों के लिए इन-हाउस', '4', 'प्रशिक्षण कार्यक्रम', '15-16', '5', 'अनुकूलित प्रशिकषण कैंपस', '17-18', '6', 'आरईसीआईपीएमटी कैंपस', '19-21', '7', 'अंतरिक फैकल्टी के सदस्य', '22', '8', 'बाहरी फैकल्टी के सदस्य', '23', 'संस्थानों और यूटिलिटीज के साथ समझौता ज़ापन', '9', '24', 'मिशन', 'अपने अनुभव, विशेषज्ञता को साझञा करने और बिजली', 'यूटिलिटिज के प्रबंधकीय कर्मियों को प्रबुद्ध करने के लिए', 'बिजली क्षेत्र के मानव संसाधन विकास के लिए वैश्िक', 'उत्कृष्टता की एक संस्था का निर्माण करना।', 'विज़न', 'बिजली इंजीनियरों/्रबंधकों तक पहुंचना, शिक्षित करना,', 'प्रित करना, पोषण करना, प्रबुद करना और सक्रय करना', 'और उच्च उत्पादकता प्रस्त करने के लिए मानव संसाधनों', 'में गुणवता सुधार के लिए प्रयास करना।'], 'rec_scores': array([0.96054012, ..., 0.96115613], shape=(42,)), 'rec_polys': array([[[ 172, 201],
...,
[ 172, 290]],
...,
[[ 795, 2010],
...,
[ 795, 2055]]], shape=(42, 4, 2), dtype=int16), 'rec_boxes': array([[ 172, ..., 290],
...,
[ 795, ..., 2061]], shape=(42, 4), dtype=int16)}}
If save_path is specified, the visualization results will be saved under save_path. The visualization output is shown below:
The command-line method is for qu
From the published model card. Full card on the HuggingFace links in the sidebar.
How it works
Using it via the API
Once AxForge deploys devanagari-pp-ocrv5-mobile-rec for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (devanagari-pp-ocrv5-mobile-rec below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"devanagari-pp-ocrv5-mobile-rec","messages":[{"role":"user","content":"Hello"}]}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.