🇹🇳 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