Hi there, many thanks for your contribution. I would like to know if I want to train a model using 40k sampling rate, what would the config be like? I want to use RingFormer as decoder in my singing conversion project and it looks very promising. Specifically, what parameters need to be modified and what need to remain the same.
Hi there, many thanks for your contribution. I would like to know if I want to train a model using 40k sampling rate, what would the config be like? I want to use RingFormer as decoder in my singing conversion project and it looks very promising. Specifically, what parameters need to be modified and what need to remain the same.