WavTokenizer icon indicating copy to clipboard operation
WavTokenizer copied to clipboard

how to train the model with Token/s about 23, that is hopsize=1024

Open Liujingxiu23 opened this issue 5 months ago • 4 comments

I try to train the model with hopsize=1024, shout 23 tokens per second, I only change the upsample_rates to [8,8,4,4] and num_samples to 71680. The trainning is running now, but the results seems not, the synthesized wave is not intelligent, not very good. What is a good config?

Liujingxiu23 avatar Sep 21 '24 10:09 Liujingxiu23