vits_decoder/bigv.py

import torch
import torch.nn.functional as F
import torch.nn as nn

from torch import nn, sin, pow
from torch.nn import Parameter
from torch.nn import Conv1d
from torch.nn.utils import weight_norm, remove_weight_norm


from .alias import *


def init_weights(m, mean=0.0, std=0.01):
    classname = m.__class__.__name__
    if classname.find("Conv") != -1:
        m.weight.data.normal_(mean, std)


def get_padding(kernel_size, dilation=1):
    return int((kernel_size*dilation - dilation)/2)


class SnakeBeta(nn.Module):
    '''
    A modified Snake function which uses separate parameters for the magnitude of the periodic components
    Shape:
        - Input: (B, C, T)
        - Output: (B, C, T), same shape as the input
    Parameters:
        - alpha - trainable parameter that controls frequency
        - beta - trainable parameter that controls magnitude
    References:
        - This activation function is a modified version based on this paper by Liu Ziyin, Tilman Hartwig, Masahito Ueda:
        https://arxiv.org/abs/2006.08195
    Examples:
        >>> a1 = snakebeta(256)
        >>> x = torch.randn(256)
        >>> x = a1(x)
    '''

    def __init__(self, in_features, alpha=1.0, alpha_trainable=True, alpha_logscale=False):
        '''
        Initialization.
        INPUT:
            - in_features: shape of the input
            - alpha - trainable parameter that controls frequency
            - beta - trainable parameter that controls magnitude
            alpha is initialized to 1 by default, higher values = higher-frequency.
            beta is initialized to 1 by default, higher values = higher-magnitude.
            alpha will be trained along with the rest of your model.
        '''
        super(SnakeBeta, self).__init__()
        self.in_features = in_features
        # initialize alpha
        self.alpha_logscale = alpha_logscale
        if self.alpha_logscale:  # log scale alphas initialized to zeros
            self.alpha = Parameter(torch.zeros(in_features) * alpha)
            self.beta = Parameter(torch.zeros(in_features) * alpha)
        else:  # linear scale alphas initialized to ones
            self.alpha = Parameter(torch.ones(in_features) * alpha)
            self.beta = Parameter(torch.ones(in_features) * alpha)
        self.alpha.requires_grad = alpha_trainable
        self.beta.requires_grad = alpha_trainable
        self.no_div_by_zero = 0.000000001

    def forward(self, x):
        '''
        Forward pass of the function.
        Applies the function to the input elementwise.
        SnakeBeta ∶= x + 1/b * sin^2 (xa)
        '''
        alpha = self.alpha.unsqueeze(
            0).unsqueeze(-1)  # line up with x to [B, C, T]
        beta = self.beta.unsqueeze(0).unsqueeze(-1)
        if self.alpha_logscale:
            alpha = torch.exp(alpha)
            beta = torch.exp(beta)
        x = x + (1.0 / (beta + self.no_div_by_zero)) * pow(sin(x * alpha), 2)
        return x


class AMPBlock(torch.nn.Module):
    def __init__(self, h, channels, kernel_size=3, dilation=(1, 3, 5)):
        super(AMPBlock, self).__init__()
        self.h = h
        self.convs1 = nn.ModuleList([
            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=dilation[0],
                               padding=get_padding(kernel_size, dilation[0]))),
            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=dilation[1],
                               padding=get_padding(kernel_size, dilation[1]))),
            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=dilation[2],
                               padding=get_padding(kernel_size, dilation[2])))
        ])
        self.convs1.apply(init_weights)

        self.convs2 = nn.ModuleList([
            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=1,
                               padding=get_padding(kernel_size, 1))),
            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=1,
                               padding=get_padding(kernel_size, 1))),
            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=1,
                               padding=get_padding(kernel_size, 1)))
        ])
        self.convs2.apply(init_weights)

        # total number of conv layers
        self.num_layers = len(self.convs1) + len(self.convs2)

        # periodic nonlinearity with snakebeta function and anti-aliasing
        self.activations = nn.ModuleList([
            Activation1d(
                activation=SnakeBeta(channels, alpha_logscale=True))
            for _ in range(self.num_layers)
        ])

    def forward(self, x):
        acts1, acts2 = self.activations[::2], self.activations[1::2]
        for c1, c2, a1, a2 in zip(self.convs1, self.convs2, acts1, acts2):
            xt = a1(x)
            xt = c1(xt)
            xt = a2(xt)
            xt = c2(xt)
            x = xt + x
        return x

    def remove_weight_norm(self):
        for l in self.convs1:
            remove_weight_norm(l)
        for l in self.convs2:
            remove_weight_norm(l)