Modern 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-rank compression scheme for ASR encoders that significantly reduces inference costs while maintaining transcription accuracy. Our approach leverages the strong low-rank properties observed in intermediate activations: by applying principal component analysis (PCA) with a small calibration dataset, we approximate linear transformations with a chain of low-rank matrix multiplications, and further optimize self-attention to work in the reduced dimension. Evaluation results show that our method can compress Whisper large-v3's encoder size by over 50%, matching Whisper medium's size with better transcription accuracy, thereby establishing a new Pareto-optimal frontier of efficiency and performance. The code of LiteASR is available at https://github.com/efeslab/LiteASR.

翻译：现代自动语音识别（ASR）模型，例如OpenAI的Whisper，依赖于深度编码器-解码器架构，其编码器由于计算强度高而成为高效部署的关键瓶颈。本文提出LiteASR，一种针对ASR编码器的低秩压缩方案，能在保持转录精度的同时显著降低推理成本。我们的方法利用了在中间激活中观察到的强低秩特性：通过使用小型校准数据集进行主成分分析（PCA），我们以一系列低秩矩阵乘法来近似线性变换，并进一步优化自注意力机制使其在降维空间中工作。评估结果表明，该方法可将Whisper large-v3编码器尺寸压缩超过50%，在匹配Whisper medium模型尺寸的同时获得更优的转录精度，从而在效率与性能之间建立了新的帕累托最优边界。LiteASR的代码公开于https://github.com/efeslab/LiteASR。