Munsit at NADI 2025 Shared Task 2: Pushing the Boundaries of Multidialectal Arabic ASR with Weakly Supervised Pretraining and Continual Supervised Fine-tuning

TL;DR

This paper introduces a scalable training pipeline that combines weakly supervised pretraining and supervised fine-tuning to develop a high-performing, multi-dialectal Arabic speech recognition system, addressing low-resource challenges.

Contribution

It presents a novel approach that leverages large-scale weakly labeled data and continual fine-tuning to improve Arabic ASR across multiple dialects, achieving state-of-the-art results.

Findings

Achieved first place in the NADI 2025 Shared Task 2 for multi-dialectal Arabic ASR.

Demonstrated effectiveness of weak supervision combined with fine-tuning for low-resource languages.

Produced a robust Arabic ASR model capable of handling diverse dialects.

Abstract

Automatic speech recognition (ASR) plays a vital role in enabling natural human-machine interaction across applications such as virtual assistants, industrial automation, customer support, and real-time transcription. However, developing accurate ASR systems for low-resource languages like Arabic remains a significant challenge due to limited labeled data and the linguistic complexity introduced by diverse dialects. In this work, we present a scalable training pipeline that combines weakly supervised learning with supervised fine-tuning to develop a robust Arabic ASR model. In the first stage, we pretrain the model on 15,000 hours of weakly labeled speech covering both Modern Standard Arabic (MSA) and various Dialectal Arabic (DA) variants. In the subsequent stage, we perform continual supervised fine-tuning using a mixture of filtered weakly labeled data and a small, high-quality annotated dataset. Our approach achieves state-of-the-art results, ranking first in the multi-dialectal Arabic ASR challenge. These findings highlight the effectiveness of weak supervision paired with fine-tuning in overcoming data scarcity and delivering high-quality ASR for low-resource, dialect-rich languages.