PDFMathTranslate – PDFMathTranslate

<div align="center">
<a href="https://go.warp.dev/PDFMathTranslate" target="_blank">
^{Special thanks to:}
<br>
<img alt="Warp sponsorship" width="400" src="https://github.com/warpdotdev/brand-assets/blob/main/Github/Sponsor/Warp-Github-LG-02.png">
<br>
<h>Warp, built for coding with multiple AI agents</b>
<br>
^{Available for macOS, Linux and Windows}
</a>
</div>

<br>

<div align="center">

English | 简体中文 | 繁體中文 | 日本語 | 한국어

<img src="./docs/images/banner.png" width="320px" alt="PDF2ZH"/>

<h2 id="title">PDFMathTranslate</h2>

<p>
<!-- PyPI -->
<a href="https://pypi.org/project/pdf2zh/">
<img src="https://img.shields.io/pypi/v/pdf2zh"></a>
<a href="https://pepy.tech/projects/pdf2zh">
<img src="https://static.pepy.tech/badge/pdf2zh"></a>
<a href="https://hub.docker.com/r/byaidu/pdf2zh">
<img src="https://img.shields.io/docker/pulls/byaidu/pdf2zh"></a>
<a href="https://hellogithub.com/repository/8ec2cfd3ef744762bf531232fa32bc47" target="_blank"><img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=8ec2cfd3ef744762bf531232fa32bc47&claim_uid=JQ0yfeBNjaTuqDU&theme=small" alt="Featured｜HelloGitHub" /></a>
<a href="https://gitcode.com/Byaidu/PDFMathTranslate/overview">
<img src="https://gitcode.com/Byaidu/PDFMathTranslate/star/badge.svg"></a>
<a href="https://huggingface.co/spaces/reycn/PDFMathTranslate-Docker">
<img src="https://img.shields.io/badge/%F0%9F%A4%97-Online%20Demo-FF9E0D"></a>
<a href="https://www.modelscope.cn/studios/AI-ModelScope/PDFMathTranslate">
<img src="https://img.shields.io/badge/ModelScope-Demo-blue"></a>
<a href="https://github.com/Byaidu/PDFMathTranslate/pulls">
<img src="https://img.shields.io/badge/contributions-welcome-green"></a>
<a href="https://t.me/+Z9_SgnxmsmA5NzBl">
<img src="https://img.shields.io/badge/Telegram-2CA5E0?style=flat-squeare&logo=telegram&logoColor=white"></a>
<!-- License -->
<a href="./LICENSE">
<img src="https://img.shields.io/github/license/Byaidu/PDFMathTranslate"></a>
</p>

<a href="https://trendshift.io/repositories/19816" target="_blank"><img src="https://trendshift.io/api/badge/repositories/19816" alt="PDFMathTranslate%2FPDFMathTranslate | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>

</div>

<h2 id="updates">1. What does this do?</h2>

Scientific PDF document translation preserving layouts.

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

<div align="center">
<img src="./docs/images/preview.gif" width="80%"/>
</div>

<h2 id="updates">2. Recent Updates</h2>

• [March 23, 2026] Experimental support for v2.0 translation kernel using isolated environment (--mode precise). (by @reycn)
• [March 22, 2026] Supporting MiniMax (PR by @octo-patch)
• [March 22, 2026] Fixing OpenAI-related issues (PR by @samqin123)
• [March 22, 2026] Fixing HTTP-related issues (PR by @soukouki)
• [March 22, 2026] Faster model loading on mac and OONX platforms, GUI starting-up, version printing, and continuous integration.(by @reycn)
• [May 9, 2025] pdf2zh 2.0 Preview Version #586: The Windows ZIP file and Docker image are now available.

> [!NOTE]
>
> 2.0 Moved to a new repository under the organization: PDFMathTranslate/PDFMathTranslate-next
>
> Version 2.0 official release has been published.

<h2 id="use-section">3. Use 🌟</h2>
<h3 id="demo">3.1 Online Service 🌟</h3>

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

• Public free service online without installation _(recommended)_.
• Immersive Translate - BabelDOC Free usage quota is available; please refer to the FAQ section on the page for details. _(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.

<h3 id="install">3.2 Local Installation</h3>

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

<details open>
<summary>3.2.1 Python: Install using uv</summary>

1. Python installed (3.11 <= version <= 3.12)

1. Install our package:

   pip install uv
   uv tool install --python 3.12 pdf2zh

1. Execute translation, files generated in current working directory:

   pdf2zh document.pdf

</details>
<details>
<summary>3.2.2 Python: Install using pip</summary>

1. Python installed (3.11 <= version <= 3.12)
2. Install our package:

   pip install pdf2zh

1. Execute translation, files generated in current working directory:

   pdf2zh document.pdf

</details>
<details>
<summary>3.3.3 Python: Graphic user interface</summary>

1. Python installed (3.11 <= version <= 3.12)

1. Install our package:

  pip install pdf2zh

1. Start using in browser:

   pdf2zh -i

1. If your browser has not been started automatically, goto

   http://localhost:7860/

<img src="./docs/images/gui.gif" width="500"/>

See documentation for GUI for more details.

</details>

<details>
<summary>3.2.4 Application: On Windows</summary>

1. Download pdf2zh-version-win64.zip from release page

1. Unzip and double-click pdf2zh.exe to run.

> [!TIP]
>
> - If you're using Windows and cannot open the file after downloading, please install vc_redist.x64.exe and try again.
>
</details>

<details>

<summary>3.2.5 Reference manager: Zotero Plugin</summary>

See Zotero PDF2zh for more details.

</details>

<details>
<summary>3.2.6 Docker: Containerized Deployment</summary>

1. Pull and run:

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

1. Open in browser:

   http://localhost:7860/

For docker deployment on cloud service:

<div>
<a href="https://www.heroku.com/deploy?template=https://github.com/Byaidu/PDFMathTranslate">
<img src="https://www.herokucdn.com/deploy/button.svg" alt="Deploy" height="26"></a>
<a href="https://render.com/deploy">
<img src="https://render.com/images/deploy-to-render-button.svg" alt="Deploy to Koyeb" height="26"></a>
<a href="https://zeabur.com/templates/5FQIGX?referralCode=reycn">
<img src="https://zeabur.com/button.svg" alt="Deploy on Zeabur" height="26"></a>
<a href="https://template.sealos.io/deploy?templateName=pdf2zh">
<img src="https://sealos.io/Deploy-on-Sealos.svg" alt="Deploy on Sealos" height="26"></a>
<a href="https://app.koyeb.com/deploy?type=git&builder=buildpack&repository=github.com/Byaidu/PDFMathTranslate&branch=main&name=pdf-math-translate">
<img src="https://www.koyeb.com/static/images/deploy/button.svg" alt="Deploy to Koyeb" height="26"></a>
</div>

> [!TIP]
>
> - 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
>

<details>
<summary>3.2.* Solutions for network issues in installation</summary>

Users in specific regions may encounter network difficulties when loading the AI model. The current program relies on the AI model (wybxc/DocLayout-YOLO-DocStructBench-onnx), and some users are unable to download it due to these network issues.

To address issues with downloading this model, use the following environment variable as a workaround:

  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.
</details>

<h2 id="usage">4. Technical Details</h2>

4.1 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.

<img src="./docs/images/cmd.explained.png" width="580px" alt="cmd"/>

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

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

<h3 id="downstream">4.2 Downstream Development</h3>
For downstream applications, please refer to our document about API Details for further information about:

• Python API, how to use the program in other Python programs
• HTTP API, how to communicate with a server with the program installed

<h3 id="downstream">4.3 Differences between two major forks</h3>

• Byaidu/PDFMathTranslate: The present and the original project for stable release.

• PDFMathTranslate/PDFMathTranslate-next: A fork with web-ui and additional features. This fork handles a large number of marginal cases, improves PDF compatibility, and optimizes cross-column and cross-page semantic consistency, dynamic scaling, and dynamic scaling consistency, among many other translation quality improvements. However, this fork is intended solely for development and does not address compatibility issues and is not designed for community-contributions.

<h2 id="information">5. Project Information</h2>
<h3 id="citation">5.1 Citation</h3>

This work has been accepted by the Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP 2025).

Citation:

@inproceedings{ouyang-etal-2025-pdfmathtranslate,
	    title = "{PDFM}ath{T}ranslate: Scientific Document Translation Preserving Layouts",
	    author = "Ouyang, Rongxin  and
	      Chu, Chang  and
	      Xin, Zhikuang  and
	      Ma, Xiangyao",
	    editor = {Habernal, Ivan  and
	      Schulam, Peter  and
	      Tiedemann, J{"o}rg},
	    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
	    month = nov,
	    year = "2025",
	    address = "Suzhou, China",
	    publisher = "Association for Computational Linguistics",
	    url = "https://aclanthology.org/2025.emnlp-demos.71/",
	    pages = "918--924",
	    ISBN = "979-8-89176-334-0",
	    abstract = "Language barriers in scientific documents hinder the diffusion and development of science and technologies. However, prior efforts in translating such documents largely overlooked the information in layouts. To bridge the gap, we introduce PDFMathTranslate, the world{'}s first open-source software for translating scientific documents while preserving layouts. Leveraging the most recent advances in large language models and precise layout detection, we contribute to the community with key improvements in precision, flexibility, and efficiency. The work is open-sourced at https://github.com/byaidu/pdfmathtranslate with more than 222k downloads."
	}

• 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

<h3 id="contrib">5.3 Contributors</h3>

<a href="https://github.com/Byaidu/PDFMathTranslate/graphs/contributors">
<img src="https://opencollective.com/PDFMathTranslate/contributors.svg?width=890&button=false" />
</a>


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

<h3 id="star_hist">5.4 Star History</h3>
<!-- star-history:start -->
<picture>
<source media="(prefers-color-scheme: dark)" srcset="assets/star-history/star-history-dark.svg">
<img alt="Star history" src="assets/star-history/star-history-light.svg">
</picture>
<!-- star-history:end -->