espnet2.gan_svs.visinger2.visinger2_vocoder.Generator_Harm

source

class espnet2.gan_svs.visinger2.visinger2_vocoder.Generator_Harm(hidden_channels: int = 192, n_harmonic: int = 64, kernel_size: int = 3, padding: int = 1, dropout_rate: float = 0.1, sample_rate: int = 22050, hop_size: int = 256)

Bases: Module

Initialize harmonic generator module.

This module generates harmonics from input pitch and harmonic data. It uses a convolutional neural network architecture to process the input and produce harmonic signals.

Args: : hidden_channels (int): Number of channels in the input and hidden : layers. <br/> n_harmonic (int): Number of harmonic channels. kernel_size (int): Size of the convolutional kernel. padding (int): Amount of padding added to the input. dropout_rate (float): Dropout rate for regularization. sample_rate (int): Sampling rate of the input audio. hop_size (int): Hop size used in the analysis of the input audio.

Examples: : ```python

generator = Generator_Harm(hidden_channels=192, n_harmonic=64) f0 = torch.randn(1, 1, 100) # Example pitch tensor harm = torch.randn(1, 192, 100) # Example harmonic data mask = torch.ones(1, 1, 100) # Example mask output = generator(f0, harm, mask) output.shape torch.Size([1, 64, 25600]) # Output shape after generating harmonics

Returns: : Tensor: Harmonic signal tensor of shape (B, n_harmonic, T * hop_length).

Initialize harmonic generator module.

• Parameters:
  • hidden_channels (int) – Number of channels in the input and hidden layers.
  • n_harmonic (int) – Number of harmonic channels.
  • kernel_size (int) – Size of the convolutional kernel.
  • padding (int) – Amount of padding added to the input.
  • dropout_rate (float) – Dropout rate.
  • sample_rate (int) – Sampling rate of the input audio.
  • hop_size (int) – Hop size used in the analysis of the input audio.

forward(f0, harm, mask)

Initialize harmonic generator module.

This module generates harmonics from input pitch (F0) and harmonic data.

• Parameters:
  • hidden_channels (int) – Number of channels in the input and hidden layers.
  • n_harmonic (int) – Number of harmonic channels.
  • kernel_size (int) – Size of the convolutional kernel.
  • padding (int) – Amount of padding added to the input.
  • dropout_rate (float) – Dropout rate.
  • sample_rate (int) – Sampling rate of the input audio.
  • hop_size (int) – Hop size used in the analysis of the input audio.