Lint

fish_vocoder/modules/discriminators/mpd.py

@@ -3,7 +3,7 @@
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
-from torch.nn.utils.parametrizations import weight_norm, spectral_norm
+from torch.nn.utils.parametrizations import spectral_norm, weight_norm
 
 
 class DiscriminatorP(nn.Module):

fish_vocoder/modules/discriminators/mrd.py

@@ -1,7 +1,7 @@
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
-from torch.nn.utils.parametrizations import weight_norm, spectral_norm
+from torch.nn.utils.parametrizations import spectral_norm, weight_norm
 
 
 class DiscriminatorR(torch.nn.Module):

fish_vocoder/modules/encoders/convnext.py

@@ -2,6 +2,7 @@
 import torch.nn.functional as F
 from torch import nn
 
+
 # DropPath copied from timm library
 def drop_path(
     x, drop_prob: float = 0.0, training: bool = False, scale_by_keep: bool = True
@@ -176,9 +177,7 @@ def __init__(
             self.downsample_layers.append(mid_layer)
 
         self.stages = nn.ModuleList()
-        dp_rates = [
-            x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))
-        ]
+        dp_rates = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))]
 
         cur = 0
         for i in range(len(depths)):

fish_vocoder/modules/generators/hifigan.py

@@ -242,7 +242,6 @@ def forward(self, x, template=None):
             else:
                 x = self.resblocks[i](x)
 
-
         x = self.activation_post(x)
         x = self.conv_post(x)
         x = torch.tanh(x)

fish_vocoder/modules/generators/unify.py

@@ -4,9 +4,9 @@
 
 class UnifyGenerator(nn.Module):
     def __init__(
-        self, 
-        backbone: nn.Module, 
-        head: nn.Module, 
+        self,
+        backbone: nn.Module,
+        head: nn.Module,
         vq: nn.Module | None = None,
     ):
         super().__init__()