Assessing the Feasibility of Lightweight Whisper Models for Low-Resource Urdu Transcription
It addresses the problem of limited automatic speech recognition for Urdu, a widely spoken language, but is incremental as it benchmarks existing models without fine-tuning.
This study assessed lightweight Whisper models for Urdu speech transcription in low-resource settings, finding that Whisper-Small achieved the lowest word error rate at 33.68%, outperforming smaller models.
This study evaluates the feasibility of lightweight Whisper models (Tiny, Base, Small) for Urdu speech recognition in low-resource settings. Despite Urdu being the 10th most spoken language globally with over 230 million speakers, its representation in automatic speech recognition (ASR) systems remains limited due to dialectal diversity, code-switching, and sparse training data. We benchmark these models on a curated Urdu dataset using word error rate (WER), without fine-tuning. Results show Whisper-Small achieves the lowest error rates (33.68\% WER), outperforming Tiny (67.08\% WER) and Base (53.67\% WER). Qualitative analysis reveals persistent challenges in phonetic accuracy and lexical coherence, particularly for complex utterances. While Whisper-Small demonstrates promise for deployable Urdu ASR, significant gaps remain. Our findings emphasize lay the groundwork for future research into effective, low-resource ASR systems.