https://github.com/Byaidu/PDFMathTranslate

PDF scientific paper translation and bilingual comparison - 完整保留排版的 PDF 文档全文双语翻译
https://github.com/Byaidu/PDFMathTranslate

chinese english japanese korean latex pdf translation

Last synced: about 2 months ago
JSON representation

PDF scientific paper translation and bilingual comparison - 完整保留排版的 PDF 文档全文双语翻译

• Host: GitHub
• URL: https://github.com/Byaidu/PDFMathTranslate
• Owner: Byaidu
• License: agpl-3.0
• Created: 2024-09-06T06:56:03.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2024-10-28T06:58:34.000Z (about 2 months ago)
• Last Synced: 2024-10-29T22:56:24.488Z (about 2 months ago)
• Topics: chinese, english, japanese, korean, latex, pdf, translation
• Language: Python
• Homepage:
• Size: 40.6 MB
• Stars: 78
• Watchers: 3
• Forks: 12
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• StarryDivineSky - Byaidu/PDFMathTranslate - YOLO 等开源项目。 (A01_文本生成_文本对话 / 其他_文本生成_文本对话)
• AiTreasureBox - Byaidu/PDFMathTranslate - 12-14_5799_738](https://img.shields.io/github/stars/Byaidu/PDFMathTranslate.svg)|PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/Docker| (Repos)
• awesome - Byaidu/PDFMathTranslate - PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/Docker (Python)

README

        
# PDFMathTranslate



  

  

    

  

  

  

    

  



PDF scientific paper translation and bilingual comparison based on font rules and deep learning, preserving formula and figure layout.

![image](https://github.com/user-attachments/assets/57e1cde6-c647-4af8-8f8f-587a40050dde)

![image](https://github.com/user-attachments/assets/0e6d7e44-18cd-443a-8a84-db99edf2c268)

## Installation

```bash

pip install pdf2zh

```

## Usage

Execute the translation command in the command line to generate the translated document `example-zh.pdf` and the bilingual document `example-dual.pdf` in the current directory.

### Translate the entire document

```bash

pdf2zh example.pdf

```

### Translate part of the document

```bash

pdf2zh example.pdf -p 1-3,5

```

### Translate with the specified language

```bash

pdf2zh example.pdf -li en -lo ja

```

### Use regex to specify formula fonts and characters that need to be preserved

Hint: Starting from `\ufb00` is English style ligature.

```bash

pdf2zh BDA3.pdf -f "(CM[^RT].*|MS.*|XY.*|MT.*|BL.*|.*0700|.*0500|.*Italic)" -c "(\(|\||\)|\+|=|\d|[\u0080-\ufaff])"

```

## Acknowledgement

Document merging: [PyMuPDF](https://github.com/pymupdf/PyMuPDF)

Document parsing: [Pdfminer.six](https://github.com/pdfminer/pdfminer.six)

Document extraction: [MinerU](https://github.com/opendatalab/MinerU)

Multi-threaded translation: [MathTranslate](https://github.com/SUSYUSTC/MathTranslate)

Layout parsing: [DocLayout-YOLO](https://github.com/opendatalab/DocLayout-YOLO)

## Star History