What is an MCP Server?

MCP (Model Context Protocol) Server acts as a bridge, allowing AI models to access and interact with external data sources and tools. In the context of PDF translation, it enhances the translation process by providing AI models with contextual information, resulting in more accurate and nuanced translations while preserving the original formatting.

What translation services are supported?

The solution supports a wide range of translation services, including Google Translate, DeepL, Ollama, and OpenAI.

What file formats are supported?

The primary focus is on PDF documents. While efforts are being made to support non-PDF/A compliant files, PDF remains the core supported format.

How do I install and use the PDF translation tool?

There are multiple installation and usage methods available, including UV install, Windows executable, graphic user interface (GUI), Docker container, Zotero plugin, and command-line interface (CLI). Choose the method that best suits your technical expertise and environment.

Can I translate specific pages or sections of a PDF document?

Yes, the `-p` option allows you to specify the page numbers you want to translate.

How can I improve the accuracy of translations for technical or scientific documents?

You can use the `--prompt` option to provide custom prompts that guide the AI model to use specific terminology or context relevant to your document.

How do I handle PDF documents that are not PDF/A compliant?

Use the `-cp` or `--compatible` option to enable compatibility mode, which attempts to handle non-PDF/A documents.

Is there a way to speed up the translation process?

Yes, the `-t` option allows you to use multi-threading to parallelize the translation process.

Can I use this tool for commercial purposes?

Yes, the tool can be used for commercial purposes. However, ensure that you comply with the terms of service of the translation services you are using.

Where can I find more information and support?

Refer to the project's GitHub repository for detailed documentation, FAQs, and issue tracking. You can also join the Telegram group for community support.

I'm having trouble downloading the AI model. What should I do?

If you encounter issues downloading the AI model due to network problems, try setting the `HF_ENDPOINT` environment variable to a mirror site, such as `https://hf-mirror.com`.

PDFMathTranslate – README

English | 简体中文 | 繁體中文 | 日本語 | 한국어

PDFMathTranslate

PDF scientific paper translation and bilingual comparison.

📊 Preserve formulas, charts, table of contents, and annotations (preview).
🌐 Support multiple languages, and diverse translation services.
🤖 Provides commandline tool, interactive user interface, and Docker

Feel free to provide feedback in GitHub Issues or Telegram Group.

For details on how to contribute, please consult the Contribution Guide.

Updates

[Mar. 3, 2025] Experimental support for the new backend BabelDOC WebUI added as an experimental option (by @awwaawwa)
[Feb. 22 2025] Better release CI and well-packaged windows-amd64 exe (by @awwaawwa)
[Dec. 24 2024] The translator now supports local models on Xinference (by @imClumsyPanda)
[Dec. 19 2024] Non-PDF/A documents are now supported using -cp (by @reycn)
[Dec. 13 2024] Additional support for backend by (by @YadominJinta)
[Dec. 10 2024] The translator now supports OpenAI models on Azure (by @yidasanqian)

Preview

Online Service 🌟

You can try our application out using either of the following demos:

Public free service online without installation (recommended).
Immersive Translate - BabelDOC 1000 free pages per month. (recommended)
Demo hosted on HuggingFace
Demo hosted on ModelScope without installation.

Note that the computing resources of the demo are limited, so please avoid abusing them.

Installation and Usage

Methods

For different use cases, we provide distinct methods to use our program:

1. UV install

Python installed (3.10 <= version <= 3.12)

Install our package:

pip install uv
uv tool install --python 3.12 pdf2zh

Execute translation, files generated in current working directory:
```
pdf2zh document.pdf
```

2. Windows exe

Download pdf2zh-version-win64.zip from release page
Unzip and double-click pdf2zh.exe to run.

3. Graphic user interface

1. Python installed (3.10 <= version <= 3.12) 2. Install our package:

pip install pdf2zh

Start using in browser:
```
pdf2zh -i
```
If your browswer has not been started automatically, goto
```
http://localhost:7860/
```

See documentation for GUI for more details.

4. Docker

Pull and run:

docker pull byaidu/pdf2zh
docker run -d -p 7860:7860 byaidu/pdf2zh

Open in browser:
```
http://localhost:7860/
```

For docker deployment on cloud service:

5. Zotero Plugin

See Zotero PDF2zh for more details.

6. Commandline

Python installed (3.10 <= version <= 3.12)
Install our package:
```
pip install pdf2zh
```
Execute translation, files generated in current working directory:
```
pdf2zh document.pdf
```

[!TIP]

If you’re using Windows and cannot open the file after downloading, please install vc_redist.x64.exe and try again.

If you cannot access Docker Hub, please try the image on GitHub Container Registry.
docker pull ghcr.io/byaidu/pdfmathtranslate
docker run -d -p 7860:7860 ghcr.io/byaidu/pdfmathtranslate

Unable to install?

The present program needs an AI model(wybxc/DocLayout-YOLO-DocStructBench-onnx) before working and some users are not able to download due to network issues. If you have a problem with downloading this model, we provide a workaround using the following environment variable:

set HF_ENDPOINT=https://hf-mirror.com

For PowerShell user:

$env:HF_ENDPOINT = https://hf-mirror.com

If the solution does not work to you / you encountered other issues, please refer to frequently asked questions.

Advanced Options

Execute the translation command in the command line to generate the translated document example-mono.pdf and the bilingual document example-dual.pdf in the current working directory. Use Google as the default translation service. More support translation services can find HERE.

In the following table, we list all advanced options for reference:

Option	Function	Example
files	Local files	`pdf2zh ~/local.pdf`
links	Online files	`pdf2zh http://arxiv.org/paper.pdf`
`-i`	Enter GUI	`pdf2zh -i`
`-p`	Partial document translation	`pdf2zh example.pdf -p 1`
`-li`	Source language	`pdf2zh example.pdf -li en`
`-lo`	Target language	`pdf2zh example.pdf -lo zh`
`-s`	Translation service	`pdf2zh example.pdf -s deepl`
`-t`	Multi-threads	`pdf2zh example.pdf -t 1`
`-o`	Output dir	`pdf2zh example.pdf -o output`
`-f`, `-c`	Exceptions	`pdf2zh example.pdf -f "(MS.*)"`
`-cp`	Compatibility Mode	`pdf2zh example.pdf --compatible`
`--skip-subset-fonts`	Skip font subset	`pdf2zh example.pdf --skip-subset-fonts`
`--ignore-cache`	Ignore translate cache	`pdf2zh example.pdf --ignore-cache`
`--share`	Public link	`pdf2zh -i --share`
`--authorized`	Authorization	`pdf2zh -i --authorized users.txt [auth.html]`
`--prompt`	Custom Prompt	`pdf2zh --prompt [prompt.txt]`
`--onnx`	[Use Custom DocLayout-YOLO ONNX model]	`pdf2zh --onnx [onnx/model/path]`
`--serverport`	[Use Custom WebUI port]	`pdf2zh --serverport 7860`
`--dir`	[batch translate]	`pdf2zh --dir /path/to/translate/`
`--config`	configuration file	`pdf2zh --config /path/to/config/config.json`
`--serverport`	[custom gradio server port]	`pdf2zh --serverport 7860`
`--babeldoc`	Use Experimental backend BabelDOC to translate	`pdf2zh --babeldoc` -s openai example.pdf

For detailed explanations, please refer to our document about Advanced Usage for a full list of each option.

Secondary Development (APIs)

The current pdf2zh API is temporarily deprecated. The API will be provided again after pdf2zh 2.0 is released. For users who need programmatic access, please use the babeldoc.high_level.async_translate function of BabelDOC.

This API being temporarily deprecated means: the relevant code will not be removed for now, but no technical support will be provided, and no bug fixes will be made.

TODOs

[ ] Parse layout with DocLayNet based models, PaddleX, PaperMage, SAM2
[ ] Fix page rotation, table of contents, format of lists
[ ] Fix pixel formula in old papers
[ ] Async retry except KeyboardInterrupt
[ ] Knuth–Plass algorithm for western languages
[ ] Support non-PDF/A files
[ ] Plugins of Zotero and Obsidian

Acknowledgements

Immersive Translation sponsors monthly Pro membership redemption codes for active contributors to this project, see details at: CONTRIBUTOR_REWARD.md
New backend: BabelDOC
Document merging: PyMuPDF
Document parsing: Pdfminer.six
Document extraction: MinerU
Document Preview: Gradio PDF
Multi-threaded translation: MathTranslate
Layout parsing: DocLayout-YOLO
Document standard: PDF Explained, PDF Cheat Sheets
Multilingual Font: Go Noto Universal

Contributors

Alt

PDFMathTranslate

Updates

Preview

Online Service 🌟

Installation and Usage

Methods

Unable to install?

Advanced Options

Secondary Development (APIs)

TODOs

Acknowledgements

Contributors

Star History

PDFMathTranslate

Resources

Project Details

Recomended MCP Servers

Featured Templates

Image Generation with Stable Diffusion

AI Voice Assistant (Voice-Text-Voice)

AI-Powered Product List Manager

Unified Authorization Template

Sarcastic AI Chat Bot

AI Video Generator

Start your free trial

PDFMathTranslate

Updates

Preview

Online Service 🌟

Installation and Usage

Methods

Unable to install?

Advanced Options

Secondary Development (APIs)

TODOs

Acknowledgements

Contributors

Star History

PDFMathTranslate

Resources

Project Details

Recomended MCP Servers

Featured Templates

Image Generation with Stable Diffusion

AI Voice Assistant (Voice-Text-Voice)

AI-Powered Product List Manager

Unified Authorization Template

Sarcastic AI Chat Bot

AI Video Generator

Start your free trial

Sign In

Register

Reset Password