CoolFace
Modelpublic

halimajaved592/urdu-english-code-switching-xlm-roberta

sourceHugging Faceupdated 1mo agoView on Hugging Face
0likes139downloads
Model Card

Urdu-English Code-Switching Classification Model

This model is an XLM-RoBERTa-based token classification model trained for Urdu-English code-switching detection.

Labels

  • —URD — Urdu
  • —ENG — English
  • —MIX — Mixed

Training

  • —Model: xlm-roberta-base
  • —Epochs: 5
  • —Dataset size: 971 rows

Evaluation

MetricScore
Accuracy96.43%
Precision96.64%
Recall96.43%
Weighted F196.12%

F1 by Label

LabelF1
URD0.99
ENG0.95
MIX0.71

Confusion Matrix

The model performs strongly on URD and ENG. MIX has lower recall because the test set contained only 11 MIX examples.