You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
32 lines
917 B
32 lines
917 B
import numpy as np
|
|
from scipy.io.wavfile import read
|
|
import torch
|
|
|
|
|
|
def get_mask_from_lengths(lengths):
|
|
max_len = torch.max(lengths)
|
|
ids = torch.arange(0, max_len, out=torch.LongTensor(max_len)).cuda()
|
|
mask = (ids < lengths.unsqueeze(1)).byte()
|
|
return mask
|
|
|
|
|
|
def load_wav_to_torch(full_path, sr):
|
|
sampling_rate, data = read(full_path)
|
|
assert sr == sampling_rate, "{} SR doesn't match {} on path {}".format(
|
|
sr, sampling_rate, full_path)
|
|
return torch.FloatTensor(data.astype(np.float32))
|
|
|
|
|
|
def load_filepaths_and_text(filename, sort_by_length, split="|"):
|
|
with open(filename, encoding='utf-8') as f:
|
|
filepaths_and_text = [line.strip().split(split) for line in f]
|
|
|
|
if sort_by_length:
|
|
filepaths_and_text.sort(key=lambda x: len(x[1]))
|
|
|
|
return filepaths_and_text
|
|
|
|
|
|
def to_gpu(x):
|
|
x = x.contiguous().cuda(async=True)
|
|
return torch.autograd.Variable(x)
|