Llast: Improved End-to-end Speech Translation System Leveraged By Large Language Models

Chen Xi, Zhang Songyang, Bai Qibing, Chen Kai, Nakamura Satoshi. Arxiv 2024

[Paper] [Code]    
Efficiency And Optimization Fine Tuning Has Code Model Architecture RAG Tools Training Techniques

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.

Similar Work