int8 .focrq weights for franken ocr's second model, Baidu Unlimited-OCR-2 (MIT). Recipe unlimited-ocr-2-ffn-int8-attn-bf16-lmhead-bf16-v1 , converted from HF baidu/Unlimi

PaddleOCR ONNX models (monkt/paddleocr-onnx, Apache-2.0), fetched at runtime by hygg's ocr feature and cached locally. Provenance + pinned SHA256s: packages/cli-pdf-to-te

What's Changed Add tutorial for fine-tuning OCR models by @ankandrew in https://github.com/ankandrew/fast-plate-ocr/pull/51 Migrate to UV by @ankandrew in https://github.

…andrew in https://github.com/ankandrew/fast-plate-ocr/pull/50 Full Changelog : https://github.com/ankandrew/fast-plate-ocr/compare/v1.0.0...v1.0.1

…andrew in https://github.com/ankandrew/fast-plate-ocr/pull/25 Add more CLI train options by @ankandrew in https://github.com/ankandrew/fast-plate-ocr/pull/27 New Global m

LaTeX-OCR models (from https://github.com/RapidAI/RapidLatexOCR)