DL-Art-School/codes/models/tacotron2/layers.py

82 lines
3.0 KiB
Python

import torch
from librosa.filters import mel as librosa_mel_fn
from models.tacotron2.audio_processing import dynamic_range_compression
from models.tacotron2.audio_processing import dynamic_range_decompression
from models.tacotron2.stft import STFT
class LinearNorm(torch.nn.Module):
def __init__(self, in_dim, out_dim, bias=True, w_init_gain='linear'):
super(LinearNorm, self).__init__()
self.linear_layer = torch.nn.Linear(in_dim, out_dim, bias=bias)
torch.nn.init.xavier_uniform_(
self.linear_layer.weight,
gain=torch.nn.init.calculate_gain(w_init_gain))
def forward(self, x):
return self.linear_layer(x)
class ConvNorm(torch.nn.Module):
def __init__(self, in_channels, out_channels, kernel_size=1, stride=1,
padding=None, dilation=1, bias=True, w_init_gain='linear'):
super(ConvNorm, self).__init__()
if padding is None:
assert(kernel_size % 2 == 1)
padding = int(dilation * (kernel_size - 1) / 2)
self.conv = torch.nn.Conv1d(in_channels, out_channels,
kernel_size=kernel_size, stride=stride,
padding=padding, dilation=dilation,
bias=bias)
torch.nn.init.xavier_uniform_(
self.conv.weight, gain=torch.nn.init.calculate_gain(w_init_gain))
def forward(self, signal):
conv_signal = self.conv(signal)
return conv_signal
class TacotronSTFT(torch.nn.Module):
def __init__(self, filter_length=1024, hop_length=256, win_length=1024,
n_mel_channels=80, sampling_rate=22050, mel_fmin=0.0,
mel_fmax=8000.0):
super(TacotronSTFT, self).__init__()
self.n_mel_channels = n_mel_channels
self.sampling_rate = sampling_rate
self.stft_fn = STFT(filter_length, hop_length, win_length)
mel_basis = librosa_mel_fn(
sampling_rate, filter_length, n_mel_channels, mel_fmin, mel_fmax)
mel_basis = torch.from_numpy(mel_basis).float()
self.register_buffer('mel_basis', mel_basis)
def spectral_normalize(self, magnitudes):
output = dynamic_range_compression(magnitudes)
return output
def spectral_de_normalize(self, magnitudes):
output = dynamic_range_decompression(magnitudes)
return output
def mel_spectrogram(self, y):
"""Computes mel-spectrograms from a batch of waves
PARAMS
------
y: Variable(torch.FloatTensor) with shape (B, T) in range [-1, 1]
RETURNS
-------
mel_output: torch.FloatTensor of shape (B, n_mel_channels, T)
"""
assert(torch.min(y.data) >= -10)
assert(torch.max(y.data) <= 10)
y = torch.clip(y, min=-1, max=1)
magnitudes, phases = self.stft_fn.transform(y)
magnitudes = magnitudes.data
mel_output = torch.matmul(self.mel_basis, magnitudes)
mel_output = self.spectral_normalize(mel_output)
return mel_output