paddleocr-onnx

PP-OCR ONNX Models

Multilingual OCR models from PaddleOCR, converted to ONNX format for production deployment.

Use as a complete pipeline: Integrate with monkt.com for end-to-end document processing.

Source: PaddlePaddle PP-OCRv5 Collection
Format: ONNX (optimized for inference)
License: Apache 2.0

---

Overview

16 models covering 48+ languages:

• 11 PP-OCRv5 models (latest, highest accuracy)
• 5 PP-OCRv3 models (legacy, additional language support)

---

Quick Start

Download from HuggingFace

pip install huggingface_hub rapidocr-onnxruntime

<details> <summary><b>Download specific language models</b></summary>

from huggingface_hub import hf_hub_download

# Download English models
det_path = hf_hub_download("monkt/paddleocr-onnx", "detection/v5/det.onnx")
rec_path = hf_hub_download("monkt/paddleocr-onnx", "languages/english/rec.onnx")
dict_path = hf_hub_download("monkt/paddleocr-onnx", "languages/english/dict.txt")

# Use with RapidOCR
from rapidocr_onnxruntime import RapidOCR
ocr = RapidOCR(det_model_path=det_path, rec_model_path=rec_path, rec_keys_path=dict_path)
result, elapsed = ocr("document.jpg")

</details> <details> <summary><b>Download entire language folder</b></summary>

from huggingface_hub import snapshot_download

# Download all French/German/Spanish (Latin) models
snapshot_download("monkt/paddleocr-onnx", allow_patterns=["detection/v5/*", "languages/latin/*"])

# Download Arabic models (v3)
snapshot_download("monkt/paddleocr-onnx", allow_patterns=["detection/v3/*", "languages/arabic/*"])

</details> <details> <summary><b>Clone entire repository</b></summary>

git clone https://huggingface.co/monkt/paddleocr-onnx
cd paddleocr-onnx

</details>

Basic Usage

from rapidocr_onnxruntime import RapidOCR

ocr = RapidOCR(
    det_model_path="detection/v5/det.onnx",
    rec_model_path="languages/english/rec.onnx",
    rec_keys_path="languages/english/dict.txt"
)

result, elapsed = ocr("document.jpg")
for line in result:
    print(line[1][0])  # Extracted text

---

Available Models

PP-OCRv5 Recognition Models

PP-OCRv3 Recognition Models (Legacy)

Detection Models

Note: Use v5 detection with v5 recognition models. Use v3 detection with v3 recognition models.

Preprocessing Models (Optional)

---

Language Support

PP-OCRv5 Languages (40+)

Latin Script (32 languages): English, French, German, Spanish, Italian, Portuguese, Dutch, Polish, Czech, Slovak, Croatian, Bosnian, Serbian, Slovenian, Danish, Norwegian, Swedish, Icelandic, Estonian, Lithuanian, Hungarian, Albanian, Welsh, Irish, Turkish, Indonesian, Malay, Afrikaans, Swahili, Tagalog, Uzbek, Latin

Cyrillic: Russian, Bulgarian, Ukrainian, Belarusian

East Asian: Chinese (Simplified, Traditional), Japanese (Hiragana, Katakana, Kanji), Korean

Southeast Asian: Thai

Other: Greek

PP-OCRv3 Languages (8)

South Asian: Hindi, Marathi, Nepali, Sanskrit, Tamil, Telugu

Middle Eastern: Arabic, Urdu, Persian/Farsi

---

Usage Examples

<details> <summary><b>PP-OCRv5 Models (English, Latin, East Asian, etc.)</b></summary>

from rapidocr_onnxruntime import RapidOCR

# English
ocr = RapidOCR(
    det_model_path="detection/v5/det.onnx",
    rec_model_path="languages/english/rec.onnx",
    rec_keys_path="languages/english/dict.txt"
)

# French, German, Spanish, etc. (32 languages)
ocr = RapidOCR(
    det_model_path="detection/v5/det.onnx",
    rec_model_path="languages/latin/rec.onnx",
    rec_keys_path="languages/latin/dict.txt"
)

# Russian, Bulgarian, Ukrainian, Belarusian
ocr = RapidOCR(
    det_model_path="detection/v5/det.onnx",
    rec_model_path="languages/eslav/rec.onnx",
    rec_keys_path="languages/eslav/dict.txt"
)

# Korean
ocr = RapidOCR(
    det_model_path="detection/v5/det.onnx",
    rec_model_path="languages/korean/rec.onnx",
    rec_keys_path="languages/korean/dict.txt"
)

# Chinese/Japanese
ocr = RapidOCR(
    det_model_path="detection/v5/det.onnx",
    rec_model_path="languages/chinese/rec.onnx",
    rec_keys_path="languages/chinese/dict.txt"
)

# Thai
ocr = RapidOCR(
    det_model_path="detection/v5/det.onnx",
    rec_model_path="languages/thai/rec.onnx",
    rec_keys_path="languages/thai/dict.txt"
)

# Greek
ocr = RapidOCR(
    det_model_path="detection/v5/det.onnx",
    rec_model_path="languages/greek/rec.onnx",
    rec_keys_path="languages/greek/dict.txt"
)

</details> <details> <summary><b>PP-OCRv3 Models (Hindi, Arabic, Tamil, Telugu)</b></summary>

from rapidocr_onnxruntime import RapidOCR

# Hindi, Marathi, Nepali, Sanskrit
ocr = RapidOCR(
    det_model_path="detection/v3/det.onnx",
    rec_model_path="languages/hindi/rec.onnx",
    rec_keys_path="languages/hindi/dict.txt"
)

# Arabic, Urdu, Persian/Farsi
ocr = RapidOCR(
    det_model_path="detection/v3/det.onnx",
    rec_model_path="languages/arabic/rec.onnx",
    rec_keys_path="languages/arabic/dict.txt"
)

# Tamil
ocr = RapidOCR(
    det_model_path="detection/v3/det.onnx",
    rec_model_path="languages/tamil/rec.onnx",
    rec_keys_path="languages/tamil/dict.txt"
)

# Telugu
ocr = RapidOCR(
    det_model_path="detection/v3/det.onnx",
    rec_model_path="languages/telugu/rec.onnx",
    rec_keys_path="languages/telugu/dict.txt"
)

</details>

---

Full Pipeline with Preprocessing

<details> <summary><b>Optional preprocessing for rotated/distorted documents</b></summary>

Preprocessing models improve accuracy on rotated or distorted documents:

from rapidocr_onnxruntime import RapidOCR

# Complete pipeline with preprocessing
ocr = RapidOCR(
    det_model_path="detection/v5/det.onnx",
    rec_model_path="languages/english/rec.onnx",
    rec_keys_path="languages/english/dict.txt",
    # Optional preprocessing
    use_angle_cls=True,
    angle_cls_model_path="preprocessing/textline-orientation/PP-LCNet_x1_0_textline_ori.onnx"
)

result, elapsed = ocr("rotated_document.jpg")

When to use preprocessing:

• Document Orientation (doc-orientation/): Scanned documents with unknown rotation (0°/90°/180°/270°)
• Text Line Orientation (textline-orientation/): Upside-down text lines (0°/180°)
• Document Unwarping (doc-unwarping/): Curved pages, warped documents, camera photos

Performance impact: +10-30% accuracy on distorted images, minimal speed overhead.

</details>

---

Repository Structure

.
├── detection/
│   ├── v5/
│   │   ├── det.onnx             # 84 MB - PP-OCRv5 detection
│   │   └── config.json
│   └── v3/
│       ├── det.onnx             # 2.3 MB - PP-OCRv3 detection
│       └── config.json
│
├── languages/
│   ├── english/
│   │   ├── rec.onnx             # 7.5 MB
│   │   ├── dict.txt
│   │   └── config.json
│   ├── latin/                   # 32 languages
│   ├── eslav/                   # Russian, Bulgarian, Ukrainian, Belarusian
│   ├── korean/
│   ├── chinese/                 # Chinese, Japanese
│   ├── thai/
│   ├── greek/
│   ├── hindi/                   # Hindi, Marathi, Nepali, Sanskrit (v3)
│   ├── arabic/                  # Arabic, Urdu, Persian (v3)
│   ├── tamil/                   # Tamil (v3)
│   └── telugu/                  # Telugu (v3)
│
└── preprocessing/
    ├── doc-orientation/
    ├── textline-orientation/
    └── doc-unwarping/

---

Model Selection

---

Technical Specifications

• Framework: PaddleOCR → ONNX
• ONNX Opset: 11
• Precision: FP32
• Input Format: RGB images (dynamic size)
• Inference: CPU/GPU via onnxruntime

Detection Model

• Input: (batch, 3, height, width) - dynamic
• Output: Text bounding boxes

Recognition Model

• Input: (batch, 3, 32, width) - height fixed at 32px
• Output: CTC logits → decoded with dictionary

---

Performance

Accuracy (PP-OCRv5)

---

FAQ

Q: Which version should I use?
A: Use PP-OCRv5 models for best accuracy. Use PP-OCRv3 only for South Asian languages not available in v5.

Q: Can I mix v5 and v3 models?
A: No. Use detection/v5/det.onnx with v5 recognition models, and detection/v3/det.onnx with v3 recognition models.

Q: GPU acceleration?
A: Install onnxruntime-gpu instead of onnxruntime for 10x faster inference.

Q: Commercial use?
A: Yes. Apache 2.0 license allows commercial use.

---

Credits

• Original Models: PaddlePaddle Team
• Conversion: paddle2onnx
• Source: PP-OCRv5 Collection

---

Links

• PaddleOCR GitHub
• PaddleOCR Documentation
• ONNX Runtime
• monkt.com - Document processing pipeline

---

License: Apache 2.0