Melgan pre-trained model fine-tuning with a single speaker (720 samples - 1 hour audio samples)
it didn't work. the loss keeps increasing after the 30th epoch, and generated samples are not good
May I know any reason for this? and How can we overcome this issue?
Kindly request, Please give your suggestions.
Thanks
Melgan pre-trained model fine-tuning with a single speaker (720 samples - 1 hour audio samples)
it didn't work. the loss keeps increasing after the 30th epoch, and generated samples are not good
May I know any reason for this? and How can we overcome this issue?
Kindly request, Please give your suggestions.
Thanks