Token Classification
Transformers
Safetensors
PyTorch
Spanish
roberta
ner
pii
pii-detection
de-identification
privacy
healthcare
medical
clinical
phi
spanish
openmed
Eval Results (legacy)
Instructions to use OpenMed/OpenMed-PII-Spanish-FastClinical-Small-82M-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMed/OpenMed-PII-Spanish-FastClinical-Small-82M-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="OpenMed/OpenMed-PII-Spanish-FastClinical-Small-82M-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("OpenMed/OpenMed-PII-Spanish-FastClinical-Small-82M-v1") model = AutoModelForTokenClassification.from_pretrained("OpenMed/OpenMed-PII-Spanish-FastClinical-Small-82M-v1") - Notebooks
- Google Colab
- Kaggle
| Classification Report for Spanish PII Detection | |
| Model: distilbert/distilroberta-base | |
| ============================================================ | |
| precision recall f1-score support | |
| BANKACCOUNT 0.88 0.85 0.87 178 | |
| BUILDINGNUMBER 0.85 0.89 0.87 145 | |
| CITY 0.84 0.91 0.87 350 | |
| CREDITCARD 0.69 0.96 0.81 106 | |
| DATEOFBIRTH 0.74 0.78 0.76 178 | |
| EMAIL 0.99 1.00 0.99 338 | |
| FIRSTNAME 0.79 0.85 0.82 503 | |
| LASTNAME 0.77 0.69 0.73 354 | |
| MASKEDNUMBER 1.00 0.99 1.00 121 | |
| PASSWORD 0.99 0.96 0.98 109 | |
| PHONE 0.99 0.99 0.99 229 | |
| SSN 0.95 0.98 0.97 373 | |
| STREET 0.85 0.93 0.89 150 | |
| USERNAME 0.98 0.93 0.95 301 | |
| ZIPCODE 0.88 0.94 0.91 153 | |
| micro avg 0.88 0.90 0.89 3588 | |
| macro avg 0.88 0.91 0.89 3588 | |
| weighted avg 0.88 0.90 0.89 3588 | |