Extract Matic
Sparrow is a document data extraction model fine-tuned on invoice data based on the Donut ML foundation model, designed to validate Donut's performance on enterprise documents.
Downloads 17
Release Time : 6/3/2024
Model Overview
This model is specifically designed to extract text data from enterprise documents such as invoices, with high-accuracy document understanding capabilities.
Model Features
High-Accuracy Invoice Processing
Achieves an average accuracy of 0.96 on the test set, reliably extracting key information from invoices.
Enterprise Document Optimization
Fine-tuned specifically for enterprise documents (e.g., invoices), optimizing performance in business scenarios.
Based on Donut Architecture
Leverages the powerful vision-language understanding capabilities of the Donut model for end-to-end document comprehension.
Model Capabilities
Invoice text extraction
Document image understanding
Structured data output
Use Cases
Financial Automation
Invoice Information Extraction
Automatically extracts key information such as vendor, amount, and date from invoice images.
Test accuracy 0.96
Document Digitization
Enterprise Document Processing
Converts paper invoices and other business documents into structured digital data.
Featured Recommended AI Models
Š 2025AIbase