Saved in:
Bibliographic Details
Main Authors: Chen, Xi, Zhang, Songyang, Bai, Qibing, Chen, Kai, Nakamura, Satoshi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.15415
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916331633246208
author Chen, Xi
Zhang, Songyang
Bai, Qibing
Chen, Kai
Nakamura, Satoshi
author_facet Chen, Xi
Zhang, Songyang
Bai, Qibing
Chen, Kai
Nakamura, Satoshi
contents We introduces LLaST, a framework for building high-performance Large Language model based Speech-to-text Translation systems. We address the limitations of end-to-end speech translation(E2E ST) models by exploring model architecture design and optimization techniques tailored for LLMs. Our approach includes LLM-based speech translation architecture design, ASR-augmented training, multilingual data augmentation, and dual-LoRA optimization. Our approach demonstrates superior performance on the CoVoST-2 benchmark and showcases exceptional scaling capabilities powered by LLMs. We believe this effective method will serve as a strong baseline for speech translation and provide insights for future improvements of the LLM-based speech translation framework. We release the data, code and models in https://github.com/openaudiolab/LLaST.
format Preprint
id arxiv_https___arxiv_org_abs_2407_15415
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models
Chen, Xi
Zhang, Songyang
Bai, Qibing
Chen, Kai
Nakamura, Satoshi
Computation and Language
We introduces LLaST, a framework for building high-performance Large Language model based Speech-to-text Translation systems. We address the limitations of end-to-end speech translation(E2E ST) models by exploring model architecture design and optimization techniques tailored for LLMs. Our approach includes LLM-based speech translation architecture design, ASR-augmented training, multilingual data augmentation, and dual-LoRA optimization. Our approach demonstrates superior performance on the CoVoST-2 benchmark and showcases exceptional scaling capabilities powered by LLMs. We believe this effective method will serve as a strong baseline for speech translation and provide insights for future improvements of the LLM-based speech translation framework. We release the data, code and models in https://github.com/openaudiolab/LLaST.
title LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2407.15415