DeepLearningExamples/PyTorch/SpeechSynthesis/FastPitch/common/utils.py

# *****************************************************************************
#  Copyright (c) 2018, 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 NVIDIA CORPORATION 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 NVIDIA CORPORATION 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.
#
# *****************************************************************************

import os
from pathlib import Path
from typing import Optional

import numpy as np

import torch
from scipy.io.wavfile import read


def mask_from_lens(lens, max_len: Optional[int] = None):
    if max_len is None:
        max_len = int(lens.max().item())
    ids = torch.arange(0, max_len, device=lens.device, dtype=lens.dtype)
    mask = torch.lt(ids, lens.unsqueeze(1))
    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(dataset_path, filename, split="|"):
    def split_line(root, line):
        parts = line.strip().split(split)
        paths, text = parts[:-1], parts[-1]
        return tuple(os.path.join(root, p) for p in paths) + (text,)
    with open(filename, encoding='utf-8') as f:
        filepaths_and_text = [split_line(dataset_path, line) for line in f]
    return filepaths_and_text


def stats_filename(dataset_path, filelist_path, feature_name):
    stem = Path(filelist_path).stem
    return Path(dataset_path, f'{feature_name}_stats__{stem}.json')


def to_gpu(x):
    x = x.contiguous()
    if torch.cuda.is_available():
        x = x.cuda(non_blocking=True)
    return torch.autograd.Variable(x)


def to_device_async(tensor, device):
    return tensor.to(device, non_blocking=True)


def to_numpy(x):
    return x.cpu().numpy() if isinstance(x, torch.Tensor) else x