A Voice Cloning Method Based on the Improved HiFi-GAN Model

Table 4

The main training parameters of the generator.

Initial learning rate	0.0002
	512
	[16, 16, 4, 4]
	[3, 7, 11]
	[[[1, 1], [3, 1], [5, 1]], [[1, 1], [3, 1], [5, 1]], [[1, 1], [3, 1], [5, 1]]]