Audio conditioning option in the difference between audioldm-m-full and audioldm-l-full
#2
by
maxin-cn
- opened
Thank you for your wonderful work. I'm curious that there is an audio conditioning option in the difference between audioldm-m-full and audioldm-l-full. What does this audio conditioning refer to specifically, is it the condition of the CLAP audio embedding as a model in the paper?