🐛 | Fixed model and training

generator.py

@@ -1,23 +1,17 @@
 import torch.nn as nn
 
 class SISUGenerator(nn.Module):
-    def __init__(self): # No noise_dim parameter
+    def __init__(self, upscale_scale=1): # No noise_dim parameter
         super(SISUGenerator, self).__init__()
         self.model = nn.Sequential(
-            nn.Conv1d(2, 64, kernel_size=7, stride=1, padding=3), # Input 2 channels (low-quality audio)
-            nn.LeakyReLU(0.2),
-            nn.Conv1d(64, 64, kernel_size=7, stride=1, padding=3),
-            nn.LeakyReLU(0.2),
-            nn.Conv1d(64, 128, kernel_size=5, stride=2, padding=2),
-            nn.LeakyReLU(0.2),
-            nn.Conv1d(128, 128, kernel_size=5, stride=1, padding=2),
-            nn.LeakyReLU(0.2),
-            nn.ConvTranspose1d(128, 64, kernel_size=4, stride=2, padding=1),
-            nn.LeakyReLU(0.2),
-            nn.Conv1d(64, 64, kernel_size=3, stride=1, padding=1),
-            nn.LeakyReLU(0.2),
-            nn.Conv1d(64, 2, kernel_size=3, stride=1, padding=1), # Output 2 channels (high-quality audio)
-            nn.Tanh()
+            nn.Conv1d(2, 128, kernel_size=3, padding=1),
+            nn.Conv1d(128, 256, kernel_size=3, padding=1),
+
+            nn.Upsample(scale_factor=upscale_scale, mode='nearest'),
+
+            nn.Conv1d(256, 128, kernel_size=3, padding=1),
+            nn.Conv1d(128, 64, kernel_size=3, padding=1),
+            nn.Conv1d(64, 2, kernel_size=3, padding=1)
         )
 
     def forward(self, x):