Scaling Audio Models Efficiently: A Joint Study of Compute Constraints and Optimization Behavior

תקציר מקורי באנגליתarXiv:2606.22790v3 Announce Type: replace-cross Abstract: Large automatic speech recognition (ASR) models such as Whisper must be deployed across hardware with widely varying memory and inference-speed constraints. We present a compression framework that jointly parametrizes Whisper deployment along \emph{six} dimensions: model size $x_N$, temporal resolution $x_T$, encoder token stride $x_V$, low-rank adaptation capacity $x_R$, weight precision $x_Q$ and sparsity pattern $x_P$. All axes are jointly optimized against three deployment objectives (word error rate, inference FLOPs, and memory footprint) using a non-dominated sorting genetic evolutionary search (NSGA). Across 50 of the 1,680 candidate configurations evaluated, we measure the marginal effect of each axis on the three objectives