init

models/vocoder/fregan/generator.py

@@ -3,7 +3,7 @@ import torch.nn.functional as F
 import torch.nn as nn
 from torch.nn import Conv1d, ConvTranspose1d, AvgPool1d, Conv2d
 from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm
-from models.vocoder.fregan.utils import init_weights, get_padding
+from utils.util import init_weights, get_padding
 
 LRELU_SLOPE = 0.1
 

models/vocoder/fregan/utils.py

@@ -27,21 +27,12 @@ def plot_spectrogram(spectrogram):
     return fig
 
 
-def init_weights(m, mean=0.0, std=0.01):
-    classname = m.__class__.__name__
-    if classname.find("Conv") != -1:
-        m.weight.data.normal_(mean, std)
-
-
 def apply_weight_norm(m):
     classname = m.__class__.__name__
     if classname.find("Conv") != -1:
         weight_norm(m)
 
 
-def get_padding(kernel_size, dilation=1):
-    return int((kernel_size*dilation - dilation)/2)
-
 
 def load_checkpoint(filepath, device):
     assert os.path.isfile(filepath)

models/vocoder/hifigan/models.py

@@ -3,7 +3,7 @@ import torch.nn.functional as F
 import torch.nn as nn
 from torch.nn import Conv1d, ConvTranspose1d, AvgPool1d, Conv2d
 from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm
-from models.vocoder.hifigan.utils import init_weights, get_padding
+from utils.util import init_weights, get_padding
 
 LRELU_SLOPE = 0.1
 

models/vocoder/hifigan/utils.py

@@ -6,7 +6,6 @@ from torch.nn.utils import weight_norm
 matplotlib.use("Agg")
 import matplotlib.pylab as plt
 
-
 def plot_spectrogram(spectrogram):
     fig, ax = plt.subplots(figsize=(10, 2))
     im = ax.imshow(spectrogram, aspect="auto", origin="lower",
@@ -19,12 +18,6 @@ def plot_spectrogram(spectrogram):
     return fig
 
 
-def init_weights(m, mean=0.0, std=0.01):
-    classname = m.__class__.__name__
-    if classname.find("Conv") != -1:
-        m.weight.data.normal_(mean, std)
-
-
 def apply_weight_norm(m):
     classname = m.__class__.__name__
     if classname.find("Conv") != -1:
@@ -55,4 +48,3 @@ def scan_checkpoint(cp_dir, prefix):
     if len(cp_list) == 0:
         return None
     return sorted(cp_list)[-1]
-

models/vocoder/vocoder_dataset.py

@@ -1,7 +1,7 @@
 from torch.utils.data import Dataset
 from pathlib import Path
 from models.vocoder.wavernn import audio
-import vocoder.wavernn.hparams as hp
+import models.vocoder.wavernn.hparams as hp
 import numpy as np
 import torch
 

models/vocoder/wavernn/audio.py

@@ -1,7 +1,7 @@
 import math
 import numpy as np
 import librosa
-import vocoder.wavernn.hparams as hp
+import models.vocoder.wavernn.hparams as hp
 from scipy.signal import lfilter
 import soundfile as sf
 

models/vocoder/wavernn/train.py

@@ -7,7 +7,7 @@ from torch.utils.data import DataLoader
 from pathlib import Path
 from torch import optim
 import torch.nn.functional as F
-import vocoder.wavernn.hparams as hp
+import models.vocoder.wavernn.hparams as hp
 import numpy as np
 import time
 import torch