Token Classification
Transformers
Safetensors
PyTorch
Telugu
distilbert
ner
pii
pii-detection
de-identification
privacy
healthcare
medical
clinical
phi
telugu
openmed
Eval Results (legacy)
Instructions to use OpenMed/OpenMed-PII-Telugu-LiteClinicalU-Small-66M-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMed/OpenMed-PII-Telugu-LiteClinicalU-Small-66M-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="OpenMed/OpenMed-PII-Telugu-LiteClinicalU-Small-66M-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("OpenMed/OpenMed-PII-Telugu-LiteClinicalU-Small-66M-v1") model = AutoModelForTokenClassification.from_pretrained("OpenMed/OpenMed-PII-Telugu-LiteClinicalU-Small-66M-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| Classification Report for Telugu PII Detection | |
| Model: distilbert/distilbert-base-uncased | |
| ============================================================ | |
| precision recall f1-score support | |
| AGE 0.93 0.91 0.92 191 | |
| BUILDINGNUMBER 0.90 0.84 0.87 225 | |
| CITY 0.61 0.51 0.56 375 | |
| CREDITCARD 0.90 0.83 0.86 63 | |
| DATE 0.99 1.00 1.00 300 | |
| EMAIL 1.00 1.00 1.00 232 | |
| FIRSTNAME 0.91 0.90 0.91 2468 | |
| GENDER 0.99 0.91 0.95 148 | |
| LASTNAME 0.88 0.81 0.84 1396 | |
| MASKEDNUMBER 0.95 0.51 0.67 187 | |
| PHONE 0.94 0.97 0.95 399 | |
| PREFIX 1.00 0.92 0.96 215 | |
| SSN 0.80 0.85 0.82 389 | |
| STREET 0.88 0.85 0.86 256 | |
| TIME 0.98 0.98 0.98 471 | |
| ZIPCODE 0.97 0.79 0.87 142 | |
| micro avg 0.90 0.86 0.88 7457 | |
| macro avg 0.91 0.85 0.88 7457 | |
| weighted avg 0.90 0.86 0.88 7457 | |