← Search

Shivani Agrawal

2 accepted papers

2024

USM-Lite: Quantization and Sparsity Aware Fine-Tuning for Speech Recognition with Universal Speech Models

ICASSP 2024accepted

End-to-end automatic speech recognition (ASR) models have seen revolutionary quality gains with the recent development of large-scale universal speech models (USM). However, deploying these massive USMs is extremely expensive due to the enormous memory usage and computational cost. Therefore, model…

Cited by 0SourceScholar
2023

STEP: Learning N:M Structured Sparsity Masks from Scratch with Precondition

ICML 2023poster

Recent innovations on hardware (e.g. Nvidia A100) have motivated learning N:M structured sparsity masks from scratch for fast model inference. However, state-of-the-art learning recipes in this regime (e.g. SR-STE) are proposed for non-adaptive optimizers like momentum SGD, while incurring non-trivi…

Cited by 15SourcePDFScholar