Fine-tuning multilingual ASR models like Whisper for low-resource languages often improves read speech but degrades spontaneous audio performance, a phenomenon we term studio-bias. To diagnose this mismatch, we introduce Vividh-ASR, a complexity-stratified benchmark for Hindi and Malayalam across four tiers: studio, broadcast, spontaneous, and synthetic noise. Through a controlled study of learning-rate timing and curriculum ordering, we find that early large parameter updates improve global WER by 12 absolute points, while a hard-to-easy curriculum adds gains for spontaneous speech. These findings motivate reverse multi-stage fine-tuning (R-MFT), a training recipe that enables a parameter-efficient 244M Whisper model to match or exceed conventionally fine-tuned 769M counterparts. Representational analysis via CKA and SVD reveals effective schedules concentrate adaptation in the decoder, preserving the pre-trained encoder's acoustic geometry. We release the benchmark and models.
@article{arxiv.2605.13087,
title = {Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech Recognition},
author = {Kush Juvekar and Kavya Manohar and Aditya Srinivas Menon and Arghya Bhattacharya and Kumarmanas Nethil},
journal= {arXiv preprint arXiv:2605.13087},
year = {2026}
}