S

Sk Invoice Receipts

Developed by selvakumarcts
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.
Downloads 201
Release Time : 10/20/2023

Model Overview

This model directly processes image-to-structured data conversion through LLM, simplifying workflows and improving performance, suitable for bill processing in finance, retail and other fields.

Model Features

No OCR dependency
Achieves end-to-end conversion directly through vision-language models, reducing intermediate steps and error accumulation of traditional OCR
Structured output
Supports JSON/XML dual-format output, automatically extracting key bill fields (e.g. invoice number, amount, tax rate, etc.)
Multi-item processing
Accurately identifies multiple product items and their associated attributes (quantity, unit price, tax amount, etc.) in bills

Model Capabilities

Image-to-text conversion
Key bill information extraction
Multi-format structured output
Complex layout analysis

Use Cases

Financial automation
E-invoice processing
Automatically parses header information and product details of scanned invoices
Example shows successful extraction of 6 product items with complete tax information
Retail management
Receipt digitization
Converts paper receipts into structured data for ERP system integration
Can process complex receipts with variable-length product descriptions
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase