---
title: MiniCPM-OCR
emoji: 📄
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 6.31.0
python_version: 3.12
app_file: app.py
pinned: false
short_description: Document parsing with MiniCPM-OCR on ZeroGPU
models:
  - openbmb/MiniCPM-OCR-1.0
  - PaddlePaddle/PP-DocLayoutV3_safetensors
  - PaddlePaddle/PP-LCNet_x1_0_doc_ori_safetensors
---

# MiniCPM-OCR on ZeroGPU

Upload one page image. Optional upright correction uses
`PaddlePaddle/PP-LCNet_x1_0_doc_ori_safetensors`, layout detection uses
`PaddlePaddle/PP-DocLayoutV3_safetensors`, and each region is read by
`openbmb/MiniCPM-OCR-1.0`. Seal and chart regions can be skipped.