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

Abstract

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.

Stats

• citations10
• S2 citations—
• github stars26
• HF likes0
• heat score10.67
• arxiv keychen2024llast

Code

• openaudiolab/LLaST—

Related papers

• Zero-resource Speech Translation And Recognition With Llms (2024)3.58
• Investigating Decoder-only Large Language Models For Speech-to-text Translation (2024)0.00
• Blending Llms Into Cascaded Speech Translation: Kit's Offline Speech Translation System For IWSLT 2024 (2024)0.00
• Hearing To Translate: The Effectiveness Of Speech Modality Integration Into Llms (2026)0.00
• Multilingual End-to-end Speech Translation (2019)0.00
• SLM-S2ST: A Multimodal Language Model For Direct Speech-to-speech Translation (2025)0.00
• Boosting Large Language Model For Speech Synthesis: An Empirical Study (2023)6.77
• Chain-of-thought Prompting For Speech Translation (2024)6.34