SOURCE-LINKED INTELLIGENCE

Stride-k Subsampling: Train-Free Audio Token Reduction for Whisper

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Whisper exposes speech through a fixed 1500-token encoder interface, now a default representation for ASR decoders and Whisper-based speech language models (SpeechLMs), yet its redundancy remains largely unexamined. We propose stride-k subsampling, a deterministic indexing operation that retains every k-th token after the convolutional stem or encoder transformer. Across five Whisper scales, k=2 preserves baseline WER at both positions, with CKA attributing this stability to acoustic overlap at the stem and attention-induced redistribution at the encoder output. Applying stride-2 at both posit

Read original source ↗ Open in workspace

recordType

paper

region

Global