OpenMed-PII-Hindi-mClinicalE5-Large-560M-v1

Hindi PII Detection Model | 560M Parameters | Open Source

Model Description

OpenMed-PII-Hindi-mClinicalE5-Large-560M-v1 is a transformer-based token classification model fine-tuned for Personally Identifiable Information (PII) detection in Hindi text. This model identifies and classifies 54 types of sensitive information including names, addresses, social security numbers, medical record numbers, and more.

Key Features

• Hindi-Optimized: Specifically trained on Hindi text for optimal performance
• High Accuracy: Achieves strong F1 scores across diverse PII categories
• Comprehensive Coverage: Detects 55+ entity types spanning personal, financial, medical, and contact information
• Privacy-Focused: Designed for de-identification and compliance with GDPR and other privacy regulations
• Production-Ready: Optimized for real-world text processing pipelines

Performance

Evaluated on the Hindi subset of AI4Privacy dataset:

Top 10 Hindi PII Models

Supported Entity Types

This model detects 54 PII entity types organized into categories:

Usage

Quick Start

from transformers import pipeline

# Load the PII detection pipeline
ner = pipeline("ner", model="OpenMed/OpenMed-PII-Hindi-mClinicalE5-Large-560M-v1", aggregation_strategy="simple")

text = """
रोगी राजेश कुमार (जन्म तिथि: 15/03/1985, आधार: 9876 5432 1098) की आज जांच हुई।
संपर्क: rajesh.kumar@email.in, फ़ोन: +91 98765 43210।
पता: 123 विकास मार्ग, 110092 नई दिल्ली।
"""

entities = ner(text)
for entity in entities:
 print(f"{entity['entity_group']}: {entity['word']} (score: {entity['score']:.3f})")

De-identification Example

def redact_pii(text, entities, placeholder='[REDACTED]'):
 """Replace detected PII with placeholders."""
 # Sort entities by start position (descending) to preserve offsets
 sorted_entities = sorted(entities, key=lambda x: x['start'], reverse=True)
 redacted = text
 for ent in sorted_entities:
 redacted = redacted[:ent['start']] + f"[{ent['entity_group']}]" + redacted[ent['end']:]
 return redacted

# Apply de-identification
redacted_text = redact_pii(text, entities)
print(redacted_text)

Batch Processing

from transformers import AutoModelForTokenClassification, AutoTokenizer
import torch

model_name = "OpenMed/OpenMed-PII-Hindi-mClinicalE5-Large-560M-v1"
model = AutoModelForTokenClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

texts = [
 "रोगी राजेश कुमार (जन्म तिथि: 15/03/1985, आधार: 9876 5432 1098) की आज जांच हुई।",
 "संपर्क: rajesh.kumar@email.in, फ़ोन: +91 98765 43210।",
]

inputs = tokenizer(texts, return_tensors='pt', padding=True, truncation=True)
with torch.no_grad():
 outputs = model(**inputs)
 predictions = torch.argmax(outputs.logits, dim=-1)

Training Details

Dataset

• Source: AI4Privacy PII Masking 400k (Hindi subset)
• Format: BIO-tagged token classification
• Labels: 109 total (54 entity types × 2 BIO tags + O)

Training Configuration

• Max Sequence Length: 512 tokens
• Epochs: 3
• Framework: Hugging Face Transformers + Trainer API

Intended Use & Limitations

Intended Use

• De-identification: Automated redaction of PII in Hindi clinical notes, medical records, and documents
• Compliance: Supporting GDPR, and other privacy regulation compliance
• Data Preprocessing: Preparing datasets for research by removing sensitive information
• Audit Support: Identifying PII in document collections

Limitations

Important: This model is intended as an assistive tool, not a replacement for human review.

• False Negatives: Some PII may not be detected; always verify critical applications
• Context Sensitivity: Performance may vary with domain-specific terminology
• Language: Optimized for Hindi text; may not perform well on other languages

Citation

@misc{openmed-pii-2026,
 title = {OpenMed-PII-Hindi-mClinicalE5-Large-560M-v1: Hindi PII Detection Model},
 author = {OpenMed Science},
 year = {2026},
 publisher = {Hugging Face},
 url = {https://huggingface.co/OpenMed/OpenMed-PII-Hindi-mClinicalE5-Large-560M-v1}
}

Links

• Organization: OpenMed

Base model

intfloat/multilingual-e5-large-instruct

(179)

Models for extracting PII entities and de-identifying clinical text, with support for HIPAA and GDPR compliance. • 366 items • Updated 22 days ago • 36

Multilingual models for extracting PII entities and de-identifying clinical text, with support for HIPAA and GDPR compliance. • 333 items • Updated 22 days ago • 24

35 open-source Hindi PII detection models. 54 entity types. Best F1: 96.6%. Apache 2.0. • 35 items • Updated Apr 14 • 4