ELYADATA & LIA at NADI 2025: ASR and ADI Subtasks

TL;DR

This paper presents Elyadata and LIA's top-ranking systems for Arabic dialect identification and speech recognition at NADI 2025, leveraging fine-tuned large pre-trained models to achieve high accuracy and low error rates.

Contribution

The paper introduces effective fine-tuning strategies for large pre-trained speech models to improve Arabic dialect identification and speech recognition performance.

Findings

ADI system achieved 79.83% accuracy

ASR system obtained 38.54% WER

Large pre-trained models are effective for Arabic speech tasks

Abstract

This paper describes Elyadata \& LIA's joint submission to the NADI multi-dialectal Arabic Speech Processing 2025. We participated in the Spoken Arabic Dialect Identification (ADI) and multi-dialectal Arabic ASR subtasks. Our submission ranked first for the ADI subtask and second for the multi-dialectal Arabic ASR subtask among all participants. Our ADI system is a fine-tuned Whisper-large-v3 encoder with data augmentation. This system obtained the highest ADI accuracy score of \textbf{79.83\%} on the official test set. For multi-dialectal Arabic ASR, we fine-tuned SeamlessM4T-v2 Large (Egyptian variant) separately for each of the eight considered dialects. Overall, we obtained an average WER and CER of \textbf{38.54\%} and \textbf{14.53\%}, respectively, on the test set. Our results demonstrate the effectiveness of large pre-trained speech models with targeted fine-tuning for Arabic speech processing.