jik876 / hifi-gan

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
MIT License
1.92k stars 506 forks source link

kernel_size=3? #152

Open a897456 opened 11 months ago

a897456 commented 11 months ago

in models.py
self.resblocks = nn.ModuleList() for i in range(len(self.ups)): ch = h.upsample_initial_channel//(2**(i+1)) for j, (k, d) in enumerate(zip(h.resblock_kernel_sizes, h.resblock_dilation_sizes)): self.resblocks.append(resblock(h, ch, k, d))

class ResBlock1(torch.nn.Module): def init(self, h, channels, kernel_size=3, dilation=(1, 3, 5)):

The k in the first paragraph is [3 7 11],Why is k fixed to 3 in the second paragraph?