marker

工具介绍

用高精度快速将 PDF 转换为下标 + JSON

核心特点

• •Converts PDF, image, PPTX, DOCX, XLSX, HTML, EPUB files in all languages
• •Formats tables, forms, equations, inline math, links, references, and code blocks
• •Extracts and saves images
• •Removes headers/footers/other artifacts
• •Extensible with your own formatting and logic
• •Optionally boost accuracy with LLMs (and your own prompt)
• •Works on GPU, CPU, or MPS
• •NVIDIA GPU: Docker plus the NVIDIA Container Toolkit.
• •CPU / Apple Silicon: the llama-server binary from llama.cpp:
• •Mode (--mode balanced|fast; defaults by device — balanced on GPU, fast on CPU/MPS):