2 papers
cs.CL2025
PLaMo 2 Technical Report
Preferred Networks, :, Kaizaburo Chubachi +24
In this report, we introduce PLaMo 2, a series of Japanese-focused large language models featuring a hybrid Samba-based architecture that transitions to full attention via continua…
eess.AS2024
Enhancing Large Language Model-based Speech Recognition by Contextualization for Rare and Ambiguous Words
Kento Nozawa, Takashi Masuko, Toru Taniguchi
We develop a large language model (LLM) based automatic speech recognition (ASR) system that can be contextualized by providing keywords as prior information in text prompts. We ad…