ADI-20: Arabic Dialect Identification dataset and models

Haroun Elleuch, Salima Mdhaffar, Yannick Estève, Fethi Bougares
11/13/2025
cs.CL

No official code found. Best implementation: elyadata/ADI-20 (7 stars, last commit 2025-11-25).

Abstract

We present ADI-20, an extension of the previously published ADI-17 Arabic Dialect Identification (ADI) dataset. ADI-20 covers all Arabic-speaking countries' dialects. It comprises 3,556 hours from 19 Arabic dialects in addition to Modern Standard Arabic (MSA). We used this dataset to train and evaluate various state-of-the-art ADI systems. We explored fine-tuning pre-trained ECAPA-TDNN-based models, as well as Whisper encoder blocks coupled with an attention pooling layer and a classification dense layer. We investigated the effect of (i) training data size and (ii) the model's number of parameters on identification performance. Our results show a small decrease in F1 score while using only 30% of the original training data. We open-source our collected data and trained models to enable the reproduction of our work, as well as support further research in ADI.

View on arXivView PDF

Code Implementations(1)

elyadata/ADI-20Community64%

Official implementation and resources for the "ADI-20: Arabic Dialect Identification dataset and models" paper.

73Shell, PythonMay 19, 202511 months ago

Similar Papers

Exploring Data and Parameter Efficient Strategies for Arabic Dialect Identifications

90% match2025

On the Robustness of Arabic Speech Dialect Identification

89% match2023

A Parameter-Efficient Learning Approach to Arabic Dialect Identification with Pre-Trained General-Purpose Speech Model

88% match1 repo412023

Voice Conversion Improves Cross-Domain Robustness for Spoken Arabic Dialect Identification

87% match2025

Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models

85% match2026

Arabic Dialect Classification using RNNs, Transformers, and Large Language Models: A Comparative Analysis

84% match2025

Cite this paper

@article{elleuch2025adi,
  title  = {ADI-20: Arabic Dialect Identification dataset and models},
  author = {Haroun Elleuch and Salima Mdhaffar and Yannick Estève and Fethi Bougares},
  year   = {2025},
  eprint = {2511.10070},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2511.10070v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2511.10070.svg)](https://codeofpaper.com/paper/2511.10070)

Discussion