62 lines
2.3 KiB
Python
62 lines
2.3 KiB
Python
# BSD 3-Clause License
|
|
|
|
# Copyright (c) 2018-2020, NVIDIA Corporation
|
|
# All rights reserved.
|
|
|
|
# Redistribution and use in source and binary forms, with or without
|
|
# modification, are permitted provided that the following conditions are met:
|
|
|
|
# * Redistributions of source code must retain the above copyright notice, this
|
|
# list of conditions and the following disclaimer.
|
|
|
|
# * Redistributions in binary form must reproduce the above copyright notice,
|
|
# this list of conditions and the following disclaimer in the documentation
|
|
# and/or other materials provided with the distribution.
|
|
|
|
# * Neither the name of the copyright holder nor the names of its
|
|
# contributors may be used to endorse or promote products derived from
|
|
# this software without specific prior written permission.
|
|
|
|
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
|
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
|
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
|
|
# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
|
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
|
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
|
|
# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
|
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
|
|
"""https://github.com/NVIDIA/tacotron2"""
|
|
|
|
import numpy as np
|
|
from scipy.io.wavfile import read
|
|
import torch
|
|
|
|
|
|
def get_mask_from_lengths(lengths):
|
|
max_len = torch.max(lengths).item()
|
|
ids = torch.arange(0, max_len, out=torch.cuda.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)
|