公开(公告)号：US20250054494A1

公开(公告)日：2025-02-13

申请号：US18930081

申请日：2024-10-29

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Pengzhi Gao ,  Ruiqing Zhang ,  Zhongjun He ,  Hua Wu

IPC: G10L15/06 ,  G10L15/02

Abstract: A method for training a speech translation model includes: obtaining a trained first text translation model and a speech recognition model, and constructing a candidate speech translation model to be trained based on the first text translation model and the speech recognition model; obtaining at least one of a first sample source language speech or a first sample source language text to obtain a training sample of the candidate speech translation model; and training the candidate speech translation model based on the training sample until the training is completed, and obtaining a trained target speech translation model.