File size: 1,464 Bytes
1813b28 |
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 |
import numpy as np
import torch
import copy
from torch import nn
import torch.nn.functional as F
import torchaudio
import librosa
import matplotlib.pyplot as plt
from munch import Munch
def get_data_path_list(train_path=None, val_path=None):
if train_path is None:
train_path = "Data/train_list.txt"
if val_path is None:
val_path = "Data/val_list.txt"
with open(train_path, 'r', encoding='utf-8', errors='ignore') as f:
train_list = f.readlines()
with open(val_path, 'r', encoding='utf-8', errors='ignore') as f:
val_list = f.readlines()
return train_list, val_list
def length_to_mask(lengths):
mask = torch.arange(lengths.max()).unsqueeze(0).expand(lengths.shape[0], -1).type_as(lengths)
mask = torch.gt(mask+1, lengths.unsqueeze(1))
return mask
# for norm consistency loss
def log_norm(x, mean=-4, std=4, dim=2):
"""
normalized log mel -> mel -> norm -> log(norm)
"""
x = torch.log(torch.exp(x * std + mean).norm(dim=dim))
return x
def get_image(arrs):
plt.switch_backend('agg')
fig = plt.figure()
ax = plt.gca()
ax.imshow(arrs)
return fig
def recursive_munch(d):
if isinstance(d, dict):
return Munch((k, recursive_munch(v)) for k, v in d.items())
elif isinstance(d, list):
return [recursive_munch(v) for v in d]
else:
return d
def log_print(message, logger):
logger.info(message)
print(message)
|