metadata
license: apache-2.0
tags:
- token-classification
- pii-detection
- privacy
- named-entity-recognition
language:
- en
pipeline_tag: token-classification
PII Detection Model
This model is fine-tuned for detecting Personally Identifiable Information (PII) in text.
Detected PII Types
- Names
- Email addresses
- Phone numbers
- Aadhaar numbers
- PAN cards
- Credit card numbers
Usage
from transformers import pipeline
# Load the model
pii_pipe = pipeline(
"token-classification",
model="Dombara/pii-detection-model",
aggregation_strategy="simple"
)
# Detect PII
text = "Contact John Doe at john@example.com or 9876543210"
results = pii_pipe(text)
print(results)
Model Details
- Base model: DeBERTa
- Fine-tuned for PII detection
- Supports English text