HF Jobs OCR script zoo: 28 models, one command, 7 pages for 7 cents
vanstriendaniel · x · 2026-09-16
The author updated the uv-scripts OCR collection on Hugging Face: self-contained scripts that run on HF Jobs with a single command on a GPU, adding a Markdown column to any image dataset.
- First-run example: 7 scanned NASA pages to Markdown in 4 min for 7 cents
- 28 OCR models to pick from; works on your own images or folders of PDFs
- Companion recipes for structured extraction (image/text → JSON), layout-region detection (bboxes for text/title/table/figure), and a cross-model judge script
- Includes troubleshooting for the nvcc/nvrtc crash when vLLM scripts start
More from coding & agent
- Community app runs Grok, Codex & Claude Code without terminal or IDE — PawelHuryn · 2026-09-16
- Agent-installed skill/CLI survives a VM temp files wipe — MurrLincoln · 2026-09-16
- ComfyUI MCP + Claude diagnosis cuts video gen workflow from 22 to 9 minutes — CanadianDocWild · 2026-09-16
- A senior Google AI engineer's 482-page doc on agentic design patterns — mdancho84 · 2026-09-16
- Developer adds reusable saved tasks to a browser agent, prompts now work across repos — Silly_Entertainer92 · 2026-09-16
- Jev nails raw bank-data payee cleanup 95% of the way on first try — Vjeux · 2026-09-16