# CBIhalsen/PolyglotPDF

(eBook，PDFs Translation) A multilingual eBook processing tool supporting all eBook formats. Features online and offline translation while preserving original layouts. Compatible with both scanned and digital PDFs. Elegant user interface. The world's highest-performing open-source layout-preserving eBook translator.

Repository: https://github.com/CBIhalsen/PolyglotPDF
Canonical: https://ross.abutalabs.com/products/polyglotpdf
Homepage: https://github.com/CBIhalsen/PolyglotPDF
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: formulas, latex, math, pdf, pymupdf, translation, deepseek, openai-api, ebook
Last push: 2025-09-28T05:14:31+00:00

## Health v2 (maintenance only)
Score: 42/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 44, release rhythm 28, longevity 63
- inputs: {"age_days": 886, "days_push": 339, "days_rel": 465, "gap_med": 38.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1315, forks 198 (observed 2026-08-28T04:04:20.619161+00:00)

## What it is
PolyglotPDF is a Python-based multilingual eBook and PDF translation tool that preserves original layouts while translating, supporting both digital and scanned PDFs via OCR. It offers a web UI, online and offline translation via LLM APIs (DeepSeek, GPT-4o-mini, Qwen, Doubao) and traditional services (DeepL, Bing, YouDao), and handles math formulas and tables.

## Use cases
- translate a pdf document to another language while keeping the original layout
- translate scanned pdfs with ocr
- translate ebooks in any format preserving formatting
- translate academic papers with math formulas and latex
- batch translate large pdf reports with tables
- self-host a pdf translation web service
- translate pdfs offline without cloud services

## When to choose
- you need layout-preserving pdf translation rather than plain text extraction
- you work with scanned pdfs or complex layouts like tables and formulas
- you want a self-hosted tool with a choice of translation backends including LLMs
- you need to translate ebooks in multiple formats beyond pdf

## When to avoid
- you only need raw text extraction from pdfs without translation
- you need pixel-perfect handling of complex vector math formulas inside tables
- you require a fully mature, bug-free tool for heavily styled or bold/colored mixed text
- you want a lightweight cli-only one-liner translation utility

## Facets
- artifact type: application
- maturity: active
- function: pdf, ocr, nlp, machine-learning, llm-inference, gui, web-framework
- domain: pdf, files, artificial-intelligence
- platform: python, cross-platform, self-hosted
- tags: pdf-translation, ebook-translator, layout-preserving, pymupdf, scanned-pdf, latex-formulas, deepseek, openai, ebook-formats, natural-language-processing, localization, web-server, docker

## Member repositories
- CBIhalsen/PolyglotPDF (main) score 42

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:20.619161+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:48:39.766541+00:00, confidence not recorded.
  - readme: https://github.com/CBIhalsen/PolyglotPDF (fetched 2026-08-28T04:04:20.619161+00:00, sha ef7d8d0778dd)
  - homepage: https://github.com/CBIhalsen/PolyglotPDF (fetched 2026-08-29T12:07:06.449504+00:00, sha 426b482a5140)
- Data as of 2026-08-30T08:39:29.467469+00:00.