File size: 1,851 Bytes
df370f8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import logging
from json import loads
from torch import load, FloatTensor
from numpy import float32
import librosa


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__()


def load_checkpoint(checkpoint_path, model):
  checkpoint_dict = load(checkpoint_path, map_location='cpu')
  iteration = checkpoint_dict['iteration']
  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:
      logging.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)
  logging.info("Loaded checkpoint '{}' (iteration {})" .format(
    checkpoint_path, iteration))
  return


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

  hparams = HParams(**config)
  return hparams


def load_audio_to_torch(full_path, target_sampling_rate):
  audio, sampling_rate = librosa.load(full_path, sr=target_sampling_rate, mono=True)
  return FloatTensor(audio.astype(float32))