Spaces:

openbmb
/

MiniCPM-OCR

Running on Zero

App Files Files Community

MiniCPM-OCR / README.md

HwwwH

Remove PDF upload and keep image parsing only

ed48dac verified 4 days ago

preview code

Raw History Blame Contribute Delete

640 Bytes

metadata

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.