研究库 论文知识库

内容库 / 论文

arXiv:2609.27980 · LLM 基础设施

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

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

类型：arxiv
标识：2609.27980
链接：https://arxiv.org/abs/2609.27980
主分类：llm-infra
形态：method
TLDR：Pruning large pre-trained transformer-based ASR models such as OpenAI's Whisper has seen great adoption, as pruning the decoder led to significant end-to-end transcription speedups. For instance, the {\tt whisper-large-v3-turbo} variant reduced the decoder from 32 to 4 layers, while Distill-Whisper similarly reduced the decoder to only 2 layers. Although some attention has been put towards reducing the size of the encoder, no approach has seen wide adoption. This could be due to the need for custom inference implementations to take advantage of the compressed model. We present an approach that
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-09-24-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

仓库 leon2k2k2k/llm-feedback-alignment

仓库 juliusadroit905/RAG-vs-Fine-Tuning

笔记 Cool Papers · cs.CL (papers.cool) · RSS 摘要

仓库 EvolvingLMMs-Lab/lmms-eval

笔记精读：Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects

笔记 VaLR: Vision-aligned Latent Reasoning for Multi-modal LLM

arXiv

2609.27980

TLDR

Pruning large pre-trained transformer-based ASR models such as OpenAI's Whisper has seen great adoption, as pruning the decoder led to significant end-to-end transcription speedups. For instance, the {\tt whisper-large-v3-turbo} variant reduced the decoder from 32 to 4 layers, while Distill-Whisper similarly reduced the decoder to only 2 layers. Although some attention has been put towards reducing the size of the encoder, no approach has seen wide adoption. This could be due to the need for custom inference implementations to take advantage of the compressed model. We present an approach that

arXiv ↗ 中文全文