Automatic Speech Recognition (ASR) models have achieved remarkable accuracy in general settings, yet their performance often degrades in domain-specific applications due to data mismatch and linguistic variability. This challenge is amplified for modern Large Language Model (LLM)-based ASR systems, whose massive scale and complex training dynamics make effective fine-tuning non-trivial. To address this gap, this paper proposes a principled and metric-driven fine-tuning framework for adapting both traditional and LLM-based ASR models to specialized domains. The framework emphasizes learning rate optimization based on performance metrics, combined with domain-specific data transformation and augmentation. We empirically evaluate our framework on state-of-the-art models, including Whisper, Whisper-Turbo, and Qwen2-Audio, across multi-domain, multilingual, and multi-length datasets. Our results not only validate the proposed framework but also establish practical protocols for improving domain-specific ASR performance while preventing overfitting.
@article{arxiv.2512.22165,
title = {Marco-ASR: A Principled and Metric-Driven Framework for Fine-Tuning Large-Scale ASR Models for Domain Adaptation},
author = {Xuanfan Ni and Fei Yang and Fengping Tian and Qingjuan Li and Chenyang Lyu and Yichao Du and Longyue Wang and Weihua Luo and Kaifu Zhang},
journal= {arXiv preprint arXiv:2512.22165},
year = {2025}
}