YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
SMS Transaction Extractor
An ultra-accurate SMS transaction extraction model that converts banking SMS messages into structured JSON data.
Features
- β Pure LLM approach (no regex)
- β Handles Indian banking SMS formats
- β Extracts: transaction type, amount, date, last4 digits
- β Filters promotional messages
- β Standardized date format (DD-MM-YYYY)
- β Clean numeric amounts (no commas/currency symbols)
Quick Start
Model Details
- Base Model: dslim/distilbert-NER
- Size: ~240MB
- Accuracy: 92%+ on transaction fields
- Processing Speed: <20ms per SMS
Created by
rawsun00001
- Downloads last month
- 22
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
π
Ask for provider support