Runs checks on the layout to ensure a valid pattern is defined. A pattern is considered invalid if: - Multiple timesteps for a sam

Apply reduction to collection of losses.

Create a MultiConditioner from a conditioning config dictionary Args: config: the conditioning config dictionary device: the

Decode latents to audio. If chunked is True, split the latents into chunks of a given maximum size chunk_size, with given overlap, b

Encode audios into latents. Audios should already be preprocesed by preprocess_audio_for_encoder. If chunked is True, split the audio

x is of shape (1, BS, C, T, H, W) where S is the number of segments.

get urls of shards (tar files) for multiple datasets in one s3 bucket

Returns a list of full S3 paths to files in a given S3 bucket and directory path.

Get codebook coordinates in the layout that corresponds to the specified timestep t and optionally to the codebook q. Coordinates are returned

Return a window function. Args: win_type (str): Window type. Can either be one of the window function provided in PyTorch ['h

very fast `glob` alternative. from https://stackoverflow.com/a/59803793/4259243

for non-cacheable computations

Preprocess a [list] of audio (Channels x Length) into a batch tensor to be compatable with the encoder. The audio in that list can b

feats are of shape (B*S, T, D) where T = 1 + (224 // 16) * (224 // 16) * 8 Our goal is to make them of shape (B*S, t, h, w, D

Create sinusoidal timestep embeddings. :param t: a 1-D Tensor of N indices, one per batch element. These ma