Dolphin
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
About
Dolphin-v2 is an enhanced universal document parsing model that substantially improves upon the original Dolphin. It seamlessly handles any document type—whether digital-born or photographed—through a document-type-aware two-stage architecture with scalable anchor prompting.
Open Source Health
- Stars
- 9,046
- Forks
- 775
- License
- Not stated
- Last commit
- 7 months ago
Related Categories
Vendor
ByteDance
Quick Links
Open Source
More by ByteDance
Related Products
OCRmyPDF
OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
Top category match
ZenlessZoneZero-Auto
绝区零 | ZenlessZoneZero | 零号空洞 | 自动战斗 | 自动化 | 图片分类 | OCR识别
Top category match
PaddleOCR2Pytorch
PaddleOCR inference in PyTorch. Converted from [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
Top category match
MinerU
A practical document parsing tool for converting PDF, images, DOCX, PPTX, and XLSX into Markdown and JSON
Top category match
Deepseek OCR App
A quick vibe coded app for deepseek OCR
Top category match