Advancing Speech Language Models by Scaling Supervised Fine-Tuning with Over 60,000 Hours of Synthetic Speech Dialogue Data

1 code implementation • 2 Dec 2024 • Shuaijiang Zhao, Tingwei Guo, Bajian Xiang, Tongtang Wan, Qiang Niu, Wei Zou, Xiangang Li

The GPT-4o represents a significant milestone in enabling real-time interaction with large language models (LLMs) through speech, its remarkable low latency and high fluency not only capture attention but also stimulate research interest in the field.

Language Modeling Language Modelling