|
Download ocr-tech/CLAUDE.md from prosperious/ocr-projects-archive: direct link, hf CLI and curl.
- Browser
- Download file 2 kB
-
https://huggingface.co/prosperious/ocr-projects-archive/resolve/main/ocr-tech/CLAUDE.md
- Command line
-
hf download hf://prosperious/ocr-projects-archive/ocr-tech/CLAUDE.md
-
curl -L -o CLAUDE.md https://huggingface.co/prosperious/ocr-projects-archive/resolve/main/ocr-tech/CLAUDE.md
2 kB
ocr-tech — agent instructions
Drive documents
RESEARCH.mdis the research state and drive document. Read it first every session; keep it current when results land.- End goal: OCR covering the whole Nepal language pack, Limbu first, Newar (Nepal Bhasa) second (steer 2026-07-04).
Model delegation policy (steer 2026-07-04)
- Fable (lead session model): orchestration, the hardest reasoning, design decisions, and final verification of all delegated work. Best model available — do not delegate judgment calls.
- Codex: treat as a peer, not a subordinate. It has good independent ways of figuring things out. Hand it substantial, well-scoped build/diagnosis/research tasks (new tools, refactors, root-cause hunts) with verified file paths and acceptance criteria; always verify its output independently (run its tests, spot-check its data).
- Opus: near-par with the lead model but slightly weaker; usable for hard tasks and second opinions when a peer-level check is wanted.
- Sonnet: tasks that require no big thought — mechanical edits, bulk file wrangling, running known command recipes, simple searches and summaries.
Working rules
- Never assume file paths, schemas, or endpoint behavior — verify on disk / live before coding against them (this repo's history has multiple wrong-assumption scars; see RESEARCH.md "Mistakes To Avoid").
- Real CER comes from
tools/eval_metrics.py(micro CER, codepoint + grapheme). Never report Paddlenorm_edit_disas CER. - Silver labels are machine-converted; they are training/diagnostic substrate, not claim-grade ground truth. Claim-grade numbers need frozen, human-reviewed eval packs.
- Long downloads/runs: launch detached (
nohup), not under tool timeouts; watch with polling loops.ocrtech audit-gorkhapatra-language-pageshas no resume. - Python runtime for Paddle work is 3.11 (
uv run --python 3.11); silver tooling needs--with pymupdf --with npttf2utf.