Adaptive Layer Normalization module with learnable embeddings per `num_embeddings` classes Args: num_embeddings (int): Number of emb

Inverse Modified Discrete Cosine Transform (IMDCT) module. Args: frame_len (int): Length of the MDCT frame. padding (str, op

ConvNeXt Block adapted from https://github.com/facebookresearch/ConvNeXt to 1D audio signal. Args: dim (int): Number of input channels.

Custom implementation of ISTFT since torch.istft doesn't allow custom padding (other than `center=True`) with windowing. This is because the

ISTFT Head module for predicting STFT complex coefficients. Args: dim (int): Hidden dimension of the model. n_fft (int): Siz

ResBlock adapted from HiFi-GAN V1 (https://github.com/jik876/hifi-gan) with dilated 1D convolutions, but without upsampling layers. Args

Vocos backbone module built with ConvNeXt blocks. Supports additional conditioning with Adaptive Layer Normalization Args: input_cha

Base class for the generator's backbone. It preserves the same temporal resolution across all layers.

Base class for inverse fourier modules.

IMDCT Head module for predicting MDCT coefficients with parametrizing MDCT = exp(m) · cos(p) Args: dim (int): Hidden dimension of th

IMDCT Head module for predicting MDCT coefficients with symmetric exponential function Args: dim (int): Hidden dimension of the mode

Modified Discrete Cosine Transform (MDCT) module. Args: frame_len (int): Length of the MDCT frame. padding (str, optional):

Introduced in SoundStream: An end2end neural audio codec https://arxiv.org/abs/2107.03312

Vector quantization and factorized vecotor quantization implementation Args: input_dim (int): Dimension of input. codebook_size (i

Vocos backbone module built with ResBlocks. Args: input_channels (int): Number of input features channels. dim (int): Hidden