---
title: OvisOCR2
canonical_url: "https://www.modelscope.ai/studios/ATH-MaaS/OvisOCR2"
md_url: "https://www.modelscope.ai/studios/ATH-MaaS/OvisOCR2.md"
repository: ATH-MaaS/OvisOCR2
chinese_name: "OvisOCR2 Document Parsing"
last_updated: 2026-07-30
sdk_type: gradio
sdk_version: 6.17.3
downloads: 0
stars: 3
---

# OvisOCR2

> OvisOCR2 - An interactive demo by ATH-MaaS on ModelScope. OvisOCR2 — Document OCR Demo

ATH-MaaS/OvisOCR2 is an interactive demo (Studio) on ModelScope. built with gradio 6.17.3. also known as 「OvisOCR2 Document Parsing」.

- **Repository**: ATH-MaaS/OvisOCR2
- **SDK**: gradio
- **SDK version**: 6.17.3
- **Downloads**: 0
- **Stars**: 3
- **Last updated**: 2026-07-30

Source: https://www.modelscope.ai/studios/ATH-MaaS/OvisOCR2

---

# OvisOCR2 — Document OCR Demo

OvisOCR2 is a compact 0.8B end-to-end model for page-level document parsing.
This Studio accepts images and PDFs and streams structured Markdown containing
text, LaTeX formulas, HTML tables, and cropped visual regions.

PDF pages are rasterized and inferred independently in Base mode. Up to four
pages share one xGPU request by default, reducing repeated scheduling overhead
while preserving per-page results and navigation in the browser.

Model: [ATH-MaaS/OvisOCR2](https://modelscope.cn/models/ATH-MaaS/OvisOCR2)

## Runtime

- Gradio 6.17.3
- Ada xGPU with 48 GB VRAM
- ModelScope model cache under `/mnt/workspace/modelscope-cache`
- `app.py` serves the pre-built frontend in `dist/`; Node.js is not required at runtime

## Configuration

- `OVISOCR_MODEL_PROVIDER=modelscope`
- `MODELSCOPE_CACHE=/mnt/workspace/modelscope-cache`
- `OVISOCR_MAX_NEW_TOKENS=16384`
- `OVISOCR_MAX_PDF_PAGES=50`
- `OVISOCR_PAGES_PER_GPU_REQUEST=4`