Downloads · 30 days
60
0% of all-time downloads
korean-pii-masking
seungkukim/korean-pii-masking
korean-pii-masking is a token classification model from seungkukim. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.
This model detects and masks personally identifiable information (PII) in Korean text.
All-time downloads
17.4K
Public
Parameters
110M
1.3 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pt880 MB · 67%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- Oct 13, 2025
- Updated
- Jan 16, 2026
- SHA
- 4986cd9e
Try a prompt
Datasets
Model card
From the Hugging Face model README
Korean PII Masking Model
This model detects and masks personally identifiable information (PII) in Korean text.
Supported PII Types
- PS_NAME: Person names
- QT_MOBILE/QT_PHONE: Phone numbers
- TMI_EMAIL: Email addresses
- QT_RESIDENT_NUMBER: Resident registration numbers
- QT_CARD_NUMBER: Card numbers
Usage
from transformers import pipeline
classifier = pipeline(
"token-classification",
model="seungkukim/korean-pii-masking",
aggregation_strategy="simple"
)
text = "제 이름은 홍길동이고 전화번호는 010-1234-5678입니다."
results = classifier(text)
print(results)
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- mit
- Languages
- ko
- Created
- Oct 13, 2025
- Updated
- Jan 16, 2026