Referenceshttps://arxiv.org/abs/2502.20583 LiteASR: Efficient Automatic Speech Recognition with Low-Rank ApproximationModern automatic speech recognition (ASR) models, such as OpenAI's Whisper, rely on deep encoder-decoder architectures, and their encoders are a critical bottleneck for efficient deployment due to high computational intensity. We introduce LiteASR, a low-rarxiv.org Introduction현 ..