Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery

arXiv:2609.27980 · cs.CL, cs.LG · Submitted 2026-09-23 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-09-23

Updated: 2026-09-23

Code: https://github.com/rasgaard/whisper-encoder-layer-prunehttps:

Terminology

• Pruning — 18× in this paper · explained in 4 episodes
• Distillation — 15× in this paper · explained in 2 episodes
• Transformer — 6× in this paper · explained in 2 episodes
• Knowledge Distillation — 4× in this paper · explained in 11 episodes
• Word Error Rate — 3× in this paper
• In International Conference on Learning Representations — 2× in this paper
• Redundancy — 2× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Low-Resource Languages — 1× in this paper · explained in 4 episodes
• Mean Squared Error — 1× in this paper
• Regularization — 1× in this paper · explained in 3 episodes

Sources

• The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage
• Distilling the Knowledge in a Neural Network
• WhisperKit: On-device Real-time ASR with Billion-Scale Transformers

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering