OCR scanned or image-only corpora with vision-language models, in three phases. Use `evaluate` to compare candidate OCR systems against stratified human ground truth and pick one on measured CER/WER, `run` to build the production pipeline (model selection, image handling, prompts, architecture, batching, accuracy evaluation, reproducibility), and `clean` to correct raw OCR text with LLM and rule-based passes, quality diagnostics, multilingual handling, and span-level provenance. Not for born-dig
mdr add scdenney/open-science-skills/vlm-ocr@git:20260902.da5a263mdr add scdenney/open-science-skills/vlm-ocr@sha256:26c0b8595f4f3cfd[](https://markdownregistry.com/a/art_zsnnj5kn4i67xp4d)
0 badge views in 30 days
scdenney/open-science-skills · 54 stars · license NOASSERTION · pushed 2026-09-05 · branch main
GET https://markdownregistry.com/api/v1/artifacts/art_zsnnj5kn4i67xp4d GET https://markdownregistry.com/api/v1/resolve?ref=scdenney/open-science-skills/vlm-ocr GET https://markdownregistry.com/api/v1/blob/26c0b8595f4f3cfdd62cca64519bfb3a736963dbdf9ffc3fd08a50578a837a65