A Model For Every User And Budget: Label-free And Personalized Mixed-precision Quantization

Abstract

Recent advancement in Automatic Speech Recognition (ASR) has produced large AI models, which become impractical for deployment in mobile devices. Model quantization is effective to produce compressed general-purpose models, however such models may only be deployed to a restricted sub-domain of interest. We show that ASR models can be personalized during quantization while relying on just a small set of unlabelled samples from the target domain. To this end, we propose myQASR, a mixed-precision quantization method that generates tailored quantization schemes for diverse users under any memory requirement with no fine-tuning. myQASR automatically evaluates the quantization sensitivity of network layers by analysing the full-precision activation values. We are then able to generate a personalised mixed-precision quantization scheme for any pre-determined memory budget. Results for large-scale ASR models show how myQASR improves performance for specific genders, languages, and speakers.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfish2023a

Related papers

• Usm-lite: Quantization And Sparsity Aware Fine-tuning For Speech Recognition With Universal Speech Models (2023)4.52
• Quantization Of Acoustic Model Parameters In Automatic Speech Recognition Framework (2020)0.00
• Towards Lightweight Speaker Verification Via Adaptive Neural Network Quantization (2024)5.84
• Mixed Precision Of Quantization Of Transformer Language Models For Speech Recognition (2021)8.09
• Stablequant: Layer Adaptive Post-training Quantization For Speech Foundation Models (2025)2.26
• Dq-whisper: Joint Distillation And Quantization For Efficient Multilingual Speech Recognition (2023)4.52
• Mobileasr: A Resource-aware On-device Learning Framework For User Voice Personalization Applications On Mobile Phones (2023)0.00
• Gated Low-rank Adaptation For Personalized Code-switching Automatic Speech Recognition On The Low-spec Devices (2024)0.00