torchaudio.prototype.models.hifigan_vocoder¶
- torchaudio.prototype.models.hifigan_vocoder(in_channels: int, upsample_rates: Tuple[int, ...], upsample_initial_channel: int, upsample_kernel_sizes: Tuple[int, ...], resblock_kernel_sizes: Tuple[int, ...], resblock_dilation_sizes: Tuple[Tuple[int, ...], ...], resblock_type: int, lrelu_slope: float) HiFiGANVocoder[source]¶
Builds HiFi GAN Vocoder [Kong et al., 2020].
- Parameters:
in_channels (int) – See
HiFiGANVocoder.upsample_rates (tuple of
int) – SeeHiFiGANVocoder.upsample_initial_channel (int) – See
HiFiGANVocoder.upsample_kernel_sizes (tuple of
int) – SeeHiFiGANVocoder.resblock_kernel_sizes (tuple of
int) – SeeHiFiGANVocoder.resblock_dilation_sizes (tuple of tuples of
int) – SeeHiFiGANVocoder.resblock_type (int, 1 or 2) – See
HiFiGANVocoder.
- Returns:
generated model.
- Return type:
