Vibe Coding DiscoverBabelDOC
View on GitHubYet Another Document Translator
LLM-powered document translation library that turns PDFs (especially scientific papers) into bilingual or translated PDFs. Uses OpenAI-compatible models plus ONNX layout analysis, OCR and glossaries; ships a CLI and Python API.
Use Cases
Translate English scientific PDF papers into ChineseGenerate side-by-side or alternating bilingual PDFsBatch translate multiple PDF filesTerm-consistent translation using auto-extracted glossariesTranslate scanned PDFs via OCR workaroundEmbed PDF translation into other Python programsUse in Zotero via plugins for paper readingPreserve tables and formulas while translating
Built With
- Language
- Python
- Frameworks
- OpenAI Python SDK · ONNX Runtime · Hugging Face Hub · PyMuPDF · scikit-image · OpenCV · pydantic · tiktoken · peewee · xsdata · rich · scikit-learn · uv
Tags
pdf-translation · document-translation · bilingual-pdf · layout-analysis · ocr · glossary · scientific-papers · openai · onnx · cli · python-api · self-hosted · zotero · batch-processing · formula-preservation · pdf