Quantization study enables smaller, more accurate Whisper-small ASR

A new study published on arXiv evaluates various post-training quantization (PTQ) techniques for the Whisper-small automatic speech recognition model. The research, which tested libraries like PyTorch, Optimum-Quanto, HQQ, and bitsandbytes, found that dynamic int8 quantization using Quanto provided the best balance of compression and accuracy. This method reduced model size by 57% while slightly improving word error rates on the LibriSpeech dataset, making Whisper-small more deployable on resource-constrained devices. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Enables more efficient deployment of speech recognition models on edge devices by reducing size and computational cost.

RANK_REASON The cluster contains an academic paper detailing research into model optimization techniques. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• arXiv
• bitsandbytes
• HQQ
• LibriSpeech
• Optimum-Quanto
• PyTorch
• Whisper-small

• paper
• product
• infra