uv-scripts/ocr

13 OCR models from 0.9B to 8B parameters. Pick a model, point at your dataset, get markdown — no setup required.

🚀 Quick Start

Run OCR on any dataset without needing your own GPU:

# Quick test with 10 samples

hf jobs uv run --flavor l4x1 \

--secrets HF_TOKEN \

https://huggingface.co/datasets/uv-scripts/ocr/raw/main/glm-ocr.py \

your-input-dataset your-output-dataset \

--max-samples 10