גזירה כמעצור: גזירה-מודעת-הגנבה של גזירה-אחת-פעם ב-ASR

תקציר מקורי באנגליתarXiv:2511.08092v2 Announce Type: replace-cross Abstract: We challenge the conventional view of neural network pruning as solely a compression technique, demonstrating that one-shot magnitude pruning serves as a powerful implicit regularizer for ASR. Using Whisper-small, we combine gradient- and Fisher-based sensitivity diagnostics with targeted, component-wise pruning. This reveals architectural asymmetries: decoder FFNs are pruning-fragile, whereas decoder self-attention and the last encoder layers contain redundancy that, when removed, improves generalization. Without fine-tuning, pruning 50% of decoder self-attention reduces WER by 2.38% absolute (20.44% relative) on LibriSpeech test-other; pruning the last four encoder layers at 50% instead yields a 1.72% absolute (14.8% relative) imp