curiousily/layoutlmv3-financial-document-classification

Model

This model is a fine-tuned version of microsoft/layoutlmv3-base trained on Financial Documents Clustering Kaggle Dataset.

It classifies document images into one of the following (5) classes:

• —Income Statements
• —Balance Sheets
• —Cash Flows
• —Notes
• —Others

Training

This model uses OCR data from EasyOCR instead of the default Tesseract OCR engine.

Libraries

• —transformers 4.25.1
• —pytorch-lightning 1.8.6
• —torchmetrics 0.11.0
• —easyocr 1.6.2