Spaces:
Sleeping
Sleeping
File size: 2,053 Bytes
2b5b9ef |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 |
# Adapted from https://github.com/jik876/hifi-gan under the MIT license.
# LICENSE is in incl_licenses directory.
import glob
import os
import matplotlib
import torch
from torch.nn.utils import weight_norm
matplotlib.use("Agg")
import matplotlib.pylab as plt
from meldataset import MAX_WAV_VALUE
from scipy.io.wavfile import write
def plot_spectrogram(spectrogram):
fig, ax = plt.subplots(figsize=(10, 2))
im = ax.imshow(spectrogram, aspect="auto", origin="lower",
interpolation='none')
plt.colorbar(im, ax=ax)
fig.canvas.draw()
plt.close()
return fig
def plot_spectrogram_clipped(spectrogram, clip_max=2.):
fig, ax = plt.subplots(figsize=(10, 2))
im = ax.imshow(spectrogram, aspect="auto", origin="lower",
interpolation='none', vmin=1e-6, vmax=clip_max)
plt.colorbar(im, ax=ax)
fig.canvas.draw()
plt.close()
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)
print("Loading '{}'".format(filepath))
checkpoint_dict = torch.load(filepath, map_location=device)
print("Complete.")
return checkpoint_dict
def save_checkpoint(filepath, obj):
print("Saving checkpoint to {}".format(filepath))
torch.save(obj, filepath)
print("Complete.")
def scan_checkpoint(cp_dir, prefix):
pattern = os.path.join(cp_dir, prefix + '????????')
cp_list = glob.glob(pattern)
if len(cp_list) == 0:
return None
return sorted(cp_list)[-1]
def save_audio(audio, path, sr):
# wav: torch with 1d shape
audio = audio * MAX_WAV_VALUE
audio = audio.cpu().numpy().astype('int16')
write(path, sr, audio) |