File size: 9,992 Bytes
5d50ffe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
import os
import glob
import sys
import argparse
import logging
import json
import subprocess

import librosa
import numpy as np
import torchaudio
from scipy.io.wavfile import read
import torch
import torchvision
from torch.nn import functional as F
from commons import sequence_mask
from hubert import hubert_model
MATPLOTLIB_FLAG = False

logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
logger = logging

f0_bin = 256
f0_max = 1100.0
f0_min = 50.0
f0_mel_min = 1127 * np.log(1 + f0_min / 700)
f0_mel_max = 1127 * np.log(1 + f0_max / 700)

def f0_to_coarse(f0):
  is_torch = isinstance(f0, torch.Tensor)
  f0_mel = 1127 * (1 + f0 / 700).log() if is_torch else 1127 * np.log(1 + f0 / 700)
  f0_mel[f0_mel > 0] = (f0_mel[f0_mel > 0] - f0_mel_min) * (f0_bin - 2) / (f0_mel_max - f0_mel_min) + 1

  f0_mel[f0_mel <= 1] = 1
  f0_mel[f0_mel > f0_bin - 1] = f0_bin - 1
  f0_coarse = (f0_mel + 0.5).long() if is_torch else np.rint(f0_mel).astype(np.int)
  assert f0_coarse.max() <= 255 and f0_coarse.min() >= 1, (f0_coarse.max(), f0_coarse.min())
  return f0_coarse


def get_hubert_model(rank=None):

  hubert_soft = hubert_model.hubert_soft("hubert/hubert-soft-0d54a1f4.pt")
  if rank is not None:
    hubert_soft = hubert_soft.cuda(rank)
  return hubert_soft

def get_hubert_content(hmodel, y=None, path=None):
  if path is not None:
    source, sr = torchaudio.load(path)
    source = torchaudio.functional.resample(source, sr, 16000)
    if len(source.shape) == 2 and source.shape[1] >= 2:
      source = torch.mean(source, dim=0).unsqueeze(0)
  else:
    source = y
  source = source.unsqueeze(0)
  with torch.inference_mode():
    units = hmodel.units(source)
    return units.transpose(1,2)


def get_content(cmodel, y):
    with torch.no_grad():
        c = cmodel.extract_features(y.squeeze(1))[0]
    c = c.transpose(1, 2)
    return c



def transform(mel, height): # 68-92
    #r = np.random.random()
    #rate = r * 0.3 + 0.85 # 0.85-1.15
    #height = int(mel.size(-2) * rate)
    tgt = torchvision.transforms.functional.resize(mel, (height, mel.size(-1)))
    if height >= mel.size(-2):
        return tgt[:, :mel.size(-2), :]
    else:
        silence = tgt[:,-1:,:].repeat(1,mel.size(-2)-height,1)
        silence += torch.randn_like(silence) / 10
        return torch.cat((tgt, silence), 1)


def stretch(mel, width): # 0.5-2
    return torchvision.transforms.functional.resize(mel, (mel.size(-2), width))


def load_checkpoint(checkpoint_path, model, optimizer=None):
  assert os.path.isfile(checkpoint_path)
  checkpoint_dict = torch.load(checkpoint_path, map_location='cpu')
  iteration = checkpoint_dict['iteration']
  learning_rate = checkpoint_dict['learning_rate']
  if iteration is None:
    iteration = 1
  if learning_rate is None:
    learning_rate = 0.0002
  if optimizer is not None and checkpoint_dict['optimizer'] is not None:
    optimizer.load_state_dict(checkpoint_dict['optimizer'])
  saved_state_dict = checkpoint_dict['model']
  if hasattr(model, 'module'):
    state_dict = model.module.state_dict()
  else:
    state_dict = model.state_dict()
  new_state_dict= {}
  for k, v in state_dict.items():
    try:
      new_state_dict[k] = saved_state_dict[k]
    except:
      logger.info("%s is not in the checkpoint" % k)
      new_state_dict[k] = v
  if hasattr(model, 'module'):
    model.module.load_state_dict(new_state_dict)
  else:
    model.load_state_dict(new_state_dict)
  logger.info("Loaded checkpoint '{}' (iteration {})" .format(
    checkpoint_path, iteration))
  return model, optimizer, learning_rate, iteration


def save_checkpoint(model, optimizer, learning_rate, iteration, checkpoint_path):
  # ckptname = checkpoint_path.split(os.sep)[-1]
  # newest_step = int(ckptname.split(".")[0].split("_")[1])
  # val_steps = 2000
  # last_ckptname = checkpoint_path.replace(str(newest_step), str(newest_step - val_steps*3))
  # if newest_step >= val_steps*3:
  #   os.system(f"rm {last_ckptname}")
  logger.info("Saving model and optimizer state at iteration {} to {}".format(
    iteration, checkpoint_path))
  if hasattr(model, 'module'):
    state_dict = model.module.state_dict()
  else:
    state_dict = model.state_dict()
  torch.save({'model': state_dict,
              'iteration': iteration,
              'optimizer': optimizer.state_dict(),
              'learning_rate': learning_rate}, checkpoint_path)


def summarize(writer, global_step, scalars={}, histograms={}, images={}, audios={}, audio_sampling_rate=22050):
  for k, v in scalars.items():
    writer.add_scalar(k, v, global_step)
  for k, v in histograms.items():
    writer.add_histogram(k, v, global_step)
  for k, v in images.items():
    writer.add_image(k, v, global_step, dataformats='HWC')
  for k, v in audios.items():
    writer.add_audio(k, v, global_step, audio_sampling_rate)


def latest_checkpoint_path(dir_path, regex="G_*.pth"):
  f_list = glob.glob(os.path.join(dir_path, regex))
  f_list.sort(key=lambda f: int("".join(filter(str.isdigit, f))))
  x = f_list[-1]
  print(x)
  return x


def plot_spectrogram_to_numpy(spectrogram):
  global MATPLOTLIB_FLAG
  if not MATPLOTLIB_FLAG:
    import matplotlib
    matplotlib.use("Agg")
    MATPLOTLIB_FLAG = True
    mpl_logger = logging.getLogger('matplotlib')
    mpl_logger.setLevel(logging.WARNING)
  import matplotlib.pylab as plt
  import numpy as np

  fig, ax = plt.subplots(figsize=(10,2))
  im = ax.imshow(spectrogram, aspect="auto", origin="lower",
                  interpolation='none')
  plt.colorbar(im, ax=ax)
  plt.xlabel("Frames")
  plt.ylabel("Channels")
  plt.tight_layout()

  fig.canvas.draw()
  data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep='')
  data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
  plt.close()
  return data


def plot_alignment_to_numpy(alignment, info=None):
  global MATPLOTLIB_FLAG
  if not MATPLOTLIB_FLAG:
    import matplotlib
    matplotlib.use("Agg")
    MATPLOTLIB_FLAG = True
    mpl_logger = logging.getLogger('matplotlib')
    mpl_logger.setLevel(logging.WARNING)
  import matplotlib.pylab as plt
  import numpy as np

  fig, ax = plt.subplots(figsize=(6, 4))
  im = ax.imshow(alignment.transpose(), aspect='auto', origin='lower',
                  interpolation='none')
  fig.colorbar(im, ax=ax)
  xlabel = 'Decoder timestep'
  if info is not None:
      xlabel += '\n\n' + info
  plt.xlabel(xlabel)
  plt.ylabel('Encoder timestep')
  plt.tight_layout()

  fig.canvas.draw()
  data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep='')
  data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
  plt.close()
  return data


def load_wav_to_torch(full_path):
  sampling_rate, data = read(full_path)
  return torch.FloatTensor(data.astype(np.float32)), sampling_rate


def load_filepaths_and_text(filename, split="|"):
  with open(filename, encoding='utf-8') as f:
    filepaths_and_text = [line.strip().split(split) for line in f]
  return filepaths_and_text


def get_hparams(init=True):
  parser = argparse.ArgumentParser()
  parser.add_argument('-c', '--config', type=str, default="./configs/base.json",
                      help='JSON file for configuration')
  parser.add_argument('-m', '--model', type=str, required=True,
                      help='Model name')

  args = parser.parse_args()
  model_dir = os.path.join("./logs", args.model)

  if not os.path.exists(model_dir):
    os.makedirs(model_dir)

  config_path = args.config
  config_save_path = os.path.join(model_dir, "config.json")
  if init:
    with open(config_path, "r") as f:
      data = f.read()
    with open(config_save_path, "w") as f:
      f.write(data)
  else:
    with open(config_save_path, "r") as f:
      data = f.read()
  config = json.loads(data)

  hparams = HParams(**config)
  hparams.model_dir = model_dir
  return hparams


def get_hparams_from_dir(model_dir):
  config_save_path = os.path.join(model_dir, "config.json")
  with open(config_save_path, "r") as f:
    data = f.read()
  config = json.loads(data)

  hparams =HParams(**config)
  hparams.model_dir = model_dir
  return hparams


def get_hparams_from_file(config_path):
  with open(config_path, "r") as f:
    data = f.read()
  config = json.loads(data)

  hparams =HParams(**config)
  return hparams


def check_git_hash(model_dir):
  source_dir = os.path.dirname(os.path.realpath(__file__))
  if not os.path.exists(os.path.join(source_dir, ".git")):
    logger.warn("{} is not a git repository, therefore hash value comparison will be ignored.".format(
      source_dir
    ))
    return

  cur_hash = subprocess.getoutput("git rev-parse HEAD")

  path = os.path.join(model_dir, "githash")
  if os.path.exists(path):
    saved_hash = open(path).read()
    if saved_hash != cur_hash:
      logger.warn("git hash values are different. {}(saved) != {}(current)".format(
        saved_hash[:8], cur_hash[:8]))
  else:
    open(path, "w").write(cur_hash)


def get_logger(model_dir, filename="train.log"):
  global logger
  logger = logging.getLogger(os.path.basename(model_dir))
  logger.setLevel(logging.DEBUG)

  formatter = logging.Formatter("%(asctime)s\t%(name)s\t%(levelname)s\t%(message)s")
  if not os.path.exists(model_dir):
    os.makedirs(model_dir)
  h = logging.FileHandler(os.path.join(model_dir, filename))
  h.setLevel(logging.DEBUG)
  h.setFormatter(formatter)
  logger.addHandler(h)
  return logger


class HParams():
  def __init__(self, **kwargs):
    for k, v in kwargs.items():
      if type(v) == dict:
        v = HParams(**v)
      self[k] = v

  def keys(self):
    return self.__dict__.keys()

  def items(self):
    return self.__dict__.items()

  def values(self):
    return self.__dict__.values()

  def __len__(self):
    return len(self.__dict__)

  def __getitem__(self, key):
    return getattr(self, key)

  def __setitem__(self, key, value):
    return setattr(self, key, value)

  def __contains__(self, key):
    return key in self.__dict__

  def __repr__(self):
    return self.__dict__.__repr__()