Introduction

LMMs-Lab is an open research organization founded by students and faculty from NTU, Singapore, in close collaboration with research labs and companies worldwide. Our released models include abilities from vision, audio, and text. This is a model documentation page for the released model

Available Models

• Aero-1-Audio - Aero is a compact audio model capable of handling a range of audio tasks, including speech recognition, audio understanding, and audio instructions following.

More Info

• Github
• Huggingface