delete redundant code

MoeGoe.py

@@ -40,6 +40,8 @@ def ask_if_continue():
 
 
 def print_speakers(speakers, escape=False):
+    if len(speakers) > 100:
+        return
     print('ID\tSpeaker')
     for id, name in enumerate(speakers):
         ex_print(str(id) + '\t' + name, escape)

commons.py

@@ -1,4 +1,3 @@
-import math
 import torch
 from torch.nn import functional as F
 import torch.jit

models.py

@@ -6,11 +6,10 @@
 import commons
 import modules
 import attentions
-import monotonic_align
 
-from torch.nn import Conv1d, ConvTranspose1d, Conv2d
-from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm
-from commons import init_weights, get_padding
+from torch.nn import Conv1d, ConvTranspose1d
+from torch.nn.utils import weight_norm
+from commons import init_weights
 
 
 class StochasticDurationPredictor(nn.Module):
@@ -295,104 +294,6 @@ def forward(self, x, g=None):
 
         return x
 
-    def remove_weight_norm(self):
-        print('Removing weight norm...')
-        for l in self.ups:
-            remove_weight_norm(l)
-        for l in self.resblocks:
-            l.remove_weight_norm()
-
-
-class DiscriminatorP(torch.nn.Module):
-    def __init__(self, period, kernel_size=5, stride=3, use_spectral_norm=False):
-        super(DiscriminatorP, self).__init__()
-        self.period = period
-        self.use_spectral_norm = use_spectral_norm
-        norm_f = weight_norm if use_spectral_norm == False else spectral_norm
-        self.convs = nn.ModuleList([
-            norm_f(Conv2d(1, 32, (kernel_size, 1), (stride, 1), padding=(get_padding(kernel_size, 1), 0))),
-            norm_f(Conv2d(32, 128, (kernel_size, 1), (stride, 1), padding=(get_padding(kernel_size, 1), 0))),
-            norm_f(Conv2d(128, 512, (kernel_size, 1), (stride, 1), padding=(get_padding(kernel_size, 1), 0))),
-            norm_f(Conv2d(512, 1024, (kernel_size, 1), (stride, 1), padding=(get_padding(kernel_size, 1), 0))),
-            norm_f(Conv2d(1024, 1024, (kernel_size, 1), 1, padding=(get_padding(kernel_size, 1), 0))),
-        ])
-        self.conv_post = norm_f(Conv2d(1024, 1, (3, 1), 1, padding=(1, 0)))
-
-    def forward(self, x):
-        fmap = []
-
-        # 1d to 2d
-        b, c, t = x.shape
-        if t % self.period != 0: # pad first
-            n_pad = self.period - (t % self.period)
-            x = F.pad(x, (0, n_pad), "reflect")
-            t = t + n_pad
-        x = x.view(b, c, t // self.period, self.period)
-
-        for l in self.convs:
-            x = l(x)
-            x = F.leaky_relu(x, modules.LRELU_SLOPE)
-            fmap.append(x)
-        x = self.conv_post(x)
-        fmap.append(x)
-        x = torch.flatten(x, 1, -1)
-
-        return x, fmap
-
-
-class DiscriminatorS(torch.nn.Module):
-    def __init__(self, use_spectral_norm=False):
-        super(DiscriminatorS, self).__init__()
-        norm_f = weight_norm if use_spectral_norm == False else spectral_norm
-        self.convs = nn.ModuleList([
-            norm_f(Conv1d(1, 16, 15, 1, padding=7)),
-            norm_f(Conv1d(16, 64, 41, 4, groups=4, padding=20)),
-            norm_f(Conv1d(64, 256, 41, 4, groups=16, padding=20)),
-            norm_f(Conv1d(256, 1024, 41, 4, groups=64, padding=20)),
-            norm_f(Conv1d(1024, 1024, 41, 4, groups=256, padding=20)),
-            norm_f(Conv1d(1024, 1024, 5, 1, padding=2)),
-        ])
-        self.conv_post = norm_f(Conv1d(1024, 1, 3, 1, padding=1))
-
-    def forward(self, x):
-        fmap = []
-
-        for l in self.convs:
-            x = l(x)
-            x = F.leaky_relu(x, modules.LRELU_SLOPE)
-            fmap.append(x)
-        x = self.conv_post(x)
-        fmap.append(x)
-        x = torch.flatten(x, 1, -1)
-
-        return x, fmap
-
-
-class MultiPeriodDiscriminator(torch.nn.Module):
-    def __init__(self, use_spectral_norm=False):
-        super(MultiPeriodDiscriminator, self).__init__()
-        periods = [2,3,5,7,11]
-
-        discs = [DiscriminatorS(use_spectral_norm=use_spectral_norm)]
-        discs = discs + [DiscriminatorP(i, use_spectral_norm=use_spectral_norm) for i in periods]
-        self.discriminators = nn.ModuleList(discs)
-
-    def forward(self, y, y_hat):
-        y_d_rs = []
-        y_d_gs = []
-        fmap_rs = []
-        fmap_gs = []
-        for i, d in enumerate(self.discriminators):
-            y_d_r, fmap_r = d(y)
-            y_d_g, fmap_g = d(y_hat)
-            y_d_rs.append(y_d_r)
-            y_d_gs.append(y_d_g)
-            fmap_rs.append(fmap_r)
-            fmap_gs.append(fmap_g)
-
-        return y_d_rs, y_d_gs, fmap_rs, fmap_gs
-
-
 
 class SynthesizerTrn(nn.Module):
   """
@@ -465,46 +366,6 @@ def __init__(self,
     if n_speakers > 1:
       self.emb_g = nn.Embedding(n_speakers, gin_channels)
 
-  def forward(self, x, x_lengths, y, y_lengths, sid=None, emotion_embedding=None):
-
-    x, m_p, logs_p, x_mask = self.enc_p(x, x_lengths ,emotion_embedding)
-    if self.n_speakers > 0:
-      g = self.emb_g(sid).unsqueeze(-1) # [b, h, 1]
-    else:
-      g = None
-
-    z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
-    z_p = self.flow(z, y_mask, g=g)
-
-    with torch.no_grad():
-      # negative cross-entropy
-      s_p_sq_r = torch.exp(-2 * logs_p) # [b, d, t]
-      neg_cent1 = torch.sum(-0.5 * math.log(2 * math.pi) - logs_p, [1], keepdim=True) # [b, 1, t_s]
-      neg_cent2 = torch.matmul(-0.5 * (z_p ** 2).transpose(1, 2), s_p_sq_r) # [b, t_t, d] x [b, d, t_s] = [b, t_t, t_s]
-      neg_cent3 = torch.matmul(z_p.transpose(1, 2), (m_p * s_p_sq_r)) # [b, t_t, d] x [b, d, t_s] = [b, t_t, t_s]
-      neg_cent4 = torch.sum(-0.5 * (m_p ** 2) * s_p_sq_r, [1], keepdim=True) # [b, 1, t_s]
-      neg_cent = neg_cent1 + neg_cent2 + neg_cent3 + neg_cent4
-
-      attn_mask = torch.unsqueeze(x_mask, 2) * torch.unsqueeze(y_mask, -1)
-      attn = monotonic_align.maximum_path(neg_cent, attn_mask.squeeze(1)).unsqueeze(1).detach()
-
-    w = attn.sum(2)
-    if self.use_sdp:
-      l_length = self.dp(x, x_mask, w, g=g)
-      l_length = l_length / torch.sum(x_mask)
-    else:
-      logw_ = torch.log(w + 1e-6) * x_mask
-      logw = self.dp(x, x_mask, g=g)
-      l_length = torch.sum((logw - logw_)**2, [1,2]) / torch.sum(x_mask) # for averaging 
-
-    # expand prior
-    m_p = torch.matmul(attn.squeeze(1), m_p.transpose(1, 2)).transpose(1, 2)
-    logs_p = torch.matmul(attn.squeeze(1), logs_p.transpose(1, 2)).transpose(1, 2)
-
-    z_slice, ids_slice = commons.rand_slice_segments(z, y_lengths, self.segment_size)
-    o = self.dec(z_slice, g=g)
-    return o, l_length, attn, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
-
   def infer(self, x, x_lengths, sid=None, noise_scale=1, length_scale=1, noise_scale_w=1., max_len=None, emotion_embedding=None):
     x, m_p, logs_p, x_mask = self.enc_p(x, x_lengths, emotion_embedding)
     if self.n_speakers > 0: