x : torch.Tensor, shape = (batch_size, n_mels, n_ctx) the mel spectrogram of the audio include_embeddings: bool

x : torch.LongTensor, shape = (batch_size, <= n_ctx) the text tokens xa : torch.Tensor, shape = (batch_size, n_mels, n_au

Obtain (x,y) coordinates given a set of N heatmaps. If the center and the scale is provided the function will return the points also in the or

Obtain (x,y) coordinates given a set of N heatmaps. If the centers and the scales is provided the function will return the points also in the

Get sliced features based on a given index :param feature_array: :param start_idx: the start index of the feature :p

Returns the token id corresponding to the value of the `language` field

Returns the list of tokens to suppress in order to avoid any speaker tags or non-speech annotations, to prevent sampling texts that a

Compute left and right padding

Draws samples from an lognormal distribution.

Replace any other markers, symbols, punctuations with a space, keeping diacritics

Constructs a ResNet-50 model.

VGGFace model. Args: pretrained (bool): If True, returns pre-trained model