Config?
#3
by edwixx - opened
I have started finetune this on a small single speaker english dataset? what are the optimal params for this model, since the dataset is of 50 hrs.. i have finetuned it for 25 epochs, 15 epochs but i get gibberish speech.
edwixx changed discussion status to closed
This model was trained on a small dataset. Please use the VyvoTTS-LFM2 model.
kadirnar changed discussion status to open
kadirnar changed discussion status to closed