File size: 1,087 Bytes
a722365 |
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 |
import numpy as np
from scipy.io.wavfile import read
import torch
from hparams import create_hparams
#hparam = create_hparams()
#hparam.cuda_enabled = False
def get_mask_from_lengths(lengths):
max_len = torch.max(lengths).item()
#if hparam.cuda_enabled :
if create_hparams.cuda_enabled :
ids = torch.arange(0, max_len, out=torch.cuda.LongTensor(max_len))
mask = (ids < lengths.unsqueeze(1)).bool()
else :
ids = torch.arange(0, max_len, out=torch.LongTensor(max_len))
mask = (ids < lengths.unsqueeze(1)).bool()
return mask
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 to_gpu(x):
x = x.contiguous()
if torch.cuda.is_available():
x = x.cuda(non_blocking=True)
return torch.autograd.Variable(x)
|