Preprint
Oct 2026
Not All Frames Are Equal:Difference-Aware Quantization for Ultra-Low-Bit ASR
Post-training quantization (PTQ) methods such as GPTQ and AWQ compress large language models effectively, but applying them to automatic speech recognition (ASR) at ultra-low bit-widths (2-3 bits) causes severe transcription degradation. Unlike discrete text tokens, speech activations are highly correlated in steady-st...
W. Jeon, Jungmin So
· 0 citations