# Financial document processing

A vision-language model specifically designed to extract structured financial information from cheque images and generate JSON-formatted output containing key information such as cheque number, payee, amount, and issue date.

OCR model optimized for printed digits and timestamp-like numerical values, achieving CER=0 recognition accuracy on single-line image test sets

This model is a fine-tuned version of the Impira model, specifically designed for visual question answering tasks on Czech invoices.

An experimental model fine-tuned based on Donut architecture, specifically designed for converting invoice or receipt images into XML or JSON data structures without traditional OCR engines.

A large language model based on the Donut architecture, designed for converting invoice and receipt images into structured data

An OCR model specifically designed for transcribing e13b MICR codes, fine-tuned based on Microsoft's TrOCR-large-stage1.

Document understanding model based on Donut architecture, specifically fine-tuned for payslip image processing