fastspeech_squeezewave/FastSpeech/waveglow/inference.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 scipy.io.wavfile import write
import torch
from waveglow.mel2samp import files_to_list, MAX_WAV_VALUE
# from denoiser import Denoiser


def inference(mel, waveglow, audio_path, sigma=1.0, sampling_rate=22050):
    with torch.no_grad():
        audio = waveglow.infer(mel, sigma=sigma)
        audio = audio * MAX_WAV_VALUE
    audio = audio.squeeze()
    audio = audio.cpu().numpy()
    audio = audio.astype('int16')
    write(audio_path, sampling_rate, audio)


def test_speed(mel, waveglow, sigma=1.0, sampling_rate=22050):
    with torch.no_grad():
        audio = waveglow.infer(mel, sigma=sigma)
        audio = audio * MAX_WAV_VALUE


def get_wav(mel, waveglow, sigma=1.0, sampling_rate=22050):
    with torch.no_grad():
        audio = waveglow.infer(mel, sigma=sigma)
        audio = audio * MAX_WAV_VALUE
    audio = audio.squeeze()
    audio = audio.cpu()

    return audio