公开(公告)号：US20230298569A1

公开(公告)日：2023-09-21

申请号：US18186774

申请日：2023-03-20

Applicant: Google LLC

Inventor： Shaojin Ding ,  Oleg Rybakov ,  Phoenix Meadowlark ,  Shivani Agrawal ,  Yanzhang He ,  Lukasz Lew

IPC: G10L15/06 ,  G10L15/16

CPC classification number: G10L15/063 ,  G10L15/16

Abstract: A method for training a model includes obtaining a plurality of training samples. Each respective training sample of the plurality of training samples includes a respective speech utterance and a respective textual utterance representing a transcription of the respective speech utterance. The method includes training, using quantization aware training with native integer operations, an automatic speech recognition (ASR) model on the plurality of training samples. The method also includes quantizing the trained ASR model to an integer target fixed-bit width. The quantized trained ASR model includes a plurality of weights. Each weight of the plurality of weights includes an integer with the target fixed-bit width. The method includes providing the quantized trained ASR model to a user device.