Hi,
I wander why using subset of Speech Command to train but not the whole dataset?
In my experiments, diffusion model cannot handle dataset of a large data scale (1M for ~8hours). Did you try the whole dataset and what's the generation performance and the training cost?
Hi, I wander why using subset of Speech Command to train but not the whole dataset? In my experiments, diffusion model cannot handle dataset of a large data scale (1M for ~8hours). Did you try the whole dataset and what's the generation performance and the training cost?