# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("NourBesrour/tun-ner-camembert")
model = AutoModelForTokenClassification.from_pretrained("NourBesrour/tun-ner-camembert", device_map="auto")Quick Links
🇹🇳 tun-ner-camembert
Tunisian Named Entity Recognition model for French text, fine-tuned from camembert-base.
Model Description
This model detects named entities in Tunisian French text. It was fine-tuned on a custom dataset of Tunisian French sentences collected from news websites, annotated using GLiNER.
Entity Types
| Label | Description | Example |
|---|---|---|
| PER | Person names | Ahmed Karray, Samir Saied |
| LOC | Cities, regions | Tunis, Sfax, Monastir |
| ORG | Organizations | STEG, Tunisair, BIAT |
Usage
pip install tun-camembert-ner
from tunisian_ner import NER ner = NER() ner("Ahmed Karray dirige la STEG à Tunis.")
Training
- Base model: camembert-base
- Epochs: 10
- Learning rate: 3e-5
- Batch size: 16
- Max length: 128
- Downloads last month
- 10
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="NourBesrour/tun-ner-camembert")