PDF Translate

A simple yet powerful tool to translate English PDFs into fluent Chinese using the ChatGLM (GLM-4.5-Air) model.

Features

• High-Quality Translation: Uses ZhipuAI's GLM-4.5-Air model for idiomatic translations.
• Context Preservation: Maintains the original paragraph structure.
• Bilingual Output: Generates a Markdown file with both original English text and Chinese translation side-by-side.
• Batch Processing: Optimizes API calls by batching text chunks for faster processing.

Prerequisites

• Python 3.8 or higher
• A ZhipuAI API Key (Get one at open.bigmodel.cn)

Installation

1. Clone the repository (or download the files):

   git clone <your-repo-url>
   cd PDF-Translate

2. Create and activate a virtual environment (recommended):

   python -m venv venv
   # Windows
   .\venv\Scripts\activate
   # Linux/Mac
   source venv/bin/activate

3. Install dependencies:

   pip install pymupdf zhipuai python-dotenv

4. Configure Environment: Create a .env file in the root directory and add your API key:

   API_KEY=your_zhipuai_api_key_here
   MODEL_NAME=GLM-4.5-Air

Usage

Run the script with the path to your PDF file:

python translate_pdf.py "path/to/your/document.pdf"

Example

python translate_pdf.py "sample-data/paper.pdf"

Output

The tool will generate a Markdown file in the same directory as the input PDF, with _translated.md appended to the filename.

Example Output (paper_translated.md):

# Translation of paper.pdf

## Page 1

### Original
This is the abstract of the paper.

### Translation
这是论文的摘要。

---

License

Apache-2.0 license