https://pinboard.in/u:jonty/public/ recent bookmarks from jonty 2024-09-04T12:31:59+00:00 https://x.com/dylfreed/status/1831075759747723709 jontyThe new Qwen2-VL-7B Instruct model gets *100%* accuracy extracting text from this handwritten document. This is the first open weights model (Apache 2.0) that I've seen OCR this accurately. (Thank you @fdaudens for the tip!) https://t.co/AB9r3bKDF0]]> extraction text ai recognition image writing transcription ocr https://pinboard.in/u:jonty/b:ad6c7e7db9da/ 2024-08-10T12:15:16+00:00 https://github.com/Dicklesworthstone/llm_aided_ocr jontyEnhance Tesseract OCR output for scanned PDFs by applying Large Language Model (LLM) corrections. - Dicklesworthstone/llm_aided_ocr]]> ocr text scanning recognition llm model corrections https://pinboard.in/u:jonty/b:591d15829c59/ 2010-12-22T13:45:07+00:00 http://documentcloud.github.com/docsplit/ jonty ruby pdf document parsing ocr documents data processing split https://pinboard.in/u:jonty/b:eb51e92dfec7/