From 2ca8ee78530ef4e0b855fbeb499d69f456c86296 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Stardust=C2=B7=E5=87=8F?= <star_dust_chen@foxmail.com>
Date: Sun, 3 Sep 2023 12:36:35 +0800
Subject: [PATCH] try

---
 models.py | 40 +++++++++++++++++++---------------------
 1 file changed, 19 insertions(+), 21 deletions(-)

diff --git a/models.py b/models.py
index 9951bf6..87026d3 100644
--- a/models.py
+++ b/models.py
@@ -15,8 +15,6 @@ from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm
 from commons import init_weights, get_padding
 from text import symbols, num_tones, num_languages
 class DurationDiscriminator(nn.Module): #vits2
-  # TODO : not using "spk conditioning" for now according to the paper.
-  # Can be a better discriminator if we use it.
   def __init__(self, in_channels, filter_channels, kernel_size, p_dropout, gin_channels=0):
     super().__init__()
 
@@ -28,9 +26,9 @@ class DurationDiscriminator(nn.Module): #vits2
 
     self.drop = nn.Dropout(p_dropout)
     self.conv_1 = nn.Conv1d(in_channels, filter_channels, kernel_size, padding=kernel_size//2)
-    #self.norm_1 = modules.LayerNorm(filter_channels)
+    self.norm_1 = modules.LayerNorm(filter_channels)
     self.conv_2 = nn.Conv1d(filter_channels, filter_channels, kernel_size, padding=kernel_size//2)
-    #self.norm_2 = modules.LayerNorm(filter_channels)
+    self.norm_2 = modules.LayerNorm(filter_channels)
     self.dur_proj = nn.Conv1d(1, filter_channels, 1)
 
     self.pre_out_conv_1 = nn.Conv1d(2*filter_channels, filter_channels, kernel_size, padding=kernel_size//2)
@@ -38,8 +36,8 @@ class DurationDiscriminator(nn.Module): #vits2
     self.pre_out_conv_2 = nn.Conv1d(filter_channels, filter_channels, kernel_size, padding=kernel_size//2)
     self.pre_out_norm_2 = modules.LayerNorm(filter_channels)
 
-    # if gin_channels != 0:
-    #   self.cond = nn.Conv1d(gin_channels, in_channels, 1)
+    if gin_channels != 0:
+       self.cond = nn.Conv1d(gin_channels, in_channels, 1)
 
     self.output_layer = nn.Sequential(
         nn.Linear(filter_channels, 1), 
@@ -50,13 +48,13 @@ class DurationDiscriminator(nn.Module): #vits2
     dur = self.dur_proj(dur)
     x = torch.cat([x, dur], dim=1)
     x = self.pre_out_conv_1(x * x_mask)
-    #x = torch.relu(x)
-    #x = self.pre_out_norm_1(x)
-    #x = self.drop(x)
+    x = torch.relu(x)
+    x = self.pre_out_norm_1(x)
+    x = self.drop(x)
     x = self.pre_out_conv_2(x * x_mask)
-    #x = torch.relu(x)
-    #x = self.pre_out_norm_2(x)
-    #x = self.drop(x)
+    x = torch.relu(x)
+    x = self.pre_out_norm_2(x)
+    x = self.drop(x)
     x = x * x_mask
     x = x.transpose(1, 2)
     output_prob = self.output_layer(x)
@@ -64,17 +62,17 @@ class DurationDiscriminator(nn.Module): #vits2
 
   def forward(self, x, x_mask, dur_r, dur_hat, g=None):
     x = torch.detach(x)
-    # if g is not None:
-    #   g = torch.detach(g)
-    #   x = x + self.cond(g)
+     if g is not None:
+       g = torch.detach(g)
+       x = x + self.cond(g)
     x = self.conv_1(x * x_mask)
-    #x = torch.relu(x)
-    #x = self.norm_1(x)
-    #x = self.drop(x)
+    x = torch.relu(x)
+    x = self.norm_1(x)
+    x = self.drop(x)
     x = self.conv_2(x * x_mask)
-    #x = torch.relu(x)
-    #x = self.norm_2(x)
-    #x = self.drop(x)
+    x = torch.relu(x)
+    x = self.norm_2(x)
+    x = self.drop(x)
 
     output_probs = []
     for dur in [dur_r, dur_hat]: