ngocthanhdoan / phobert-cccd-ner

VietNerm - Căn cước công dân (CCCD) NER Model

PhoBERT-based Named Entity Recognition model for Vietnamese Căn cước công dân (CCCD) documents.

Model Description

This model is fine-tuned from vinai/phobert-base for token-level NER on Vietnamese administrative/medical documents. It extracts structured fields from OCR text output.

• Base model : vinai/phobert-base
• Task : Token Classification (NER)
• Language : Vietnamese (vi)
• Document type : Căn cước công dân (CCCD)
• Number of labels : 13

Labels

• B-date_of_birth
• B-date_of_expiry
• B-full_name
• B-gender
• B-id_number
• B-nationality
• B-place_of_origin
• B-place_of_residence
• I-full_name
• I-nationality
• I-place_of_origin
• I-place_of_residence

Usage

With VietNerm SDK

from vietnerm import VietNerm

ner = VietNerm(doc_type="cccd", model_path="ngocthanhdoan/phobert-cccd-ner")
result = ner.extract("your document text here")
print(result)

With Transformers

from transformers import AutoTokenizer, AutoModelForTokenClassification
import torch

tokenizer = AutoTokenizer.from_pretrained("ngocthanhdoan/phobert-cccd-ner")
model = AutoModelForTokenClassification.from_pretrained("ngocthanhdoan/phobert-cccd-ner")

text = "your document text here"
inputs = tokenizer(text, return_tensors="pt")

with torch.no_grad():
    outputs = model(**inputs)
    predictions = torch.argmax(outputs.logits, dim=-1)

Training

• Dataset : Synthetically generated with OCR noise simulation
• Framework : HuggingFace Transformers + Trainer API
• Optimizer : AdamW (lr=2e-5)
• Epochs : 5-7 (with early stopping)

About VietNerm

VietNerm is a Document AI Factory for Vietnamese documents. It provides a complete pipeline from template-based synthetic data generation to model training and deployment.

Learn more: VietNerm Repository