Class method to create a new Vocos model instance from hyperparameters stored in a yaml configuration file.

Class method to create a new Vocos model instance from hyperparameters stored in a yaml configuration file.

Compute the gradient norm. Args: model (Module): PyTorch model. norm_type (float, optional): Type of the norm. Defaults to 2

Normalize an input signal to a user loudness in dB LKFS. Audio loudness is defined according to the ITU-R BS.1770-4 recommendation. Args:

For getting encoding in a streaming fashion Attention!!!!! we apply dropout only once at the whole utterance level in a none

Pull a single value from the stream, potentially reading some extra bytes from the underlying file-object. Returns `None` whe

Push a new value to the stream. This will immediately write as many uint8 as possible to the underlying file-object.

Compute relative positional encoding. Args: x (torch.Tensor): Input tensor (batch, head, time1, 2*time1-1). time1 mea

Computes the element-wise logarithm of the input tensor with clipping to avoid near-zero values. Args: x (Tensor): Input tensor.

Save a matplotlib figure to a numpy array. Args: fig (Figure): Matplotlib figure object. Returns: ndarray: Numpy array

Fixed euler solver for ODEs. Args: x (torch.Tensor): random noise t_span (torch.Tensor): n_timesteps interpol

Create mask for subsequent steps (size, size). This mask is used only in decoder which works in an auto-regressive mode. This means the curre

Calculate accuracy. Args: pad_outputs (Tensor): Prediction tensors (B * Lmax, D). pad_targets (LongTensor): Target label tensors

Compute the tiny-value corresponding to an input's data type.

Train one epoch

Resample data. Inplace operation. Args: data: Iterable[{key, wav, label, sample_rate}] resample_rate: target