LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models
This work addresses speech translation challenges for researchers and practitioners, offering a strong baseline and insights for future improvements, though it appears incremental as it builds on existing LLM-based approaches.
The authors tackled the limitations of end-to-end speech translation models by developing LLaST, a framework that leverages large language models with tailored architecture and optimization techniques, achieving superior performance on the CoVoST-2 benchmark and demonstrating exceptional scaling capabilities.
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.