Efficient Compression of Multitask Multilingual Speech Models

arXiv:2405.00966v1 Announce Type: new
Abstract: Whisper is a multitask and multilingual speech model covering 99 languages. It yields commendable automatic speech recognition (ASR) results in a subset of its covered languages, but the model still underperforms on a non-negligible number of under-represented languages, a problem exacerbated in smaller model versions. In this work, we examine its limitations, demonstrating the presence of speaker-related (gender, age) and model-related (resourcefulness and model size) bias. Despite that, we show that only model-related bias are …

abstract arxiv asr automatic speech recognition compression cs.ai cs.cl cs.sd eess.as languages multilingual recognition results speech speech recognition type versions whisper work