Register this class with a given auto class. This should only be used for custom models as the ones in the library are already mapped

Args: in_dim: The final dimension of inputs to the layer out_dim: The final dimension

Decodes a batch of audio codebook sequences into their respective audio waveforms via the `audio_tokenizer`. See [`~DacModel.decode`]

Check if the model class is in supported by the pipeline. Args: supported_models (`list[str]` or `dict`):

Creates a repository in a temporary directory mimicking the structure of Transformers. Uses the list of models provided (which defaults to ju

Returns the dtype of the underlying rotation. Returns: The dtype of the underlying rotation

Encodes the input audio waveform into discrete codes. Args: input_values (`torch.Tensor` of shape `(batch_size, channels

r""" Instantiate an encoder and a decoder from one or two base classes of the library from pretrained model checkpoints. The

r""" Get the memory footprint of a model. This will return the memory footprint of the current model in bytes. Useful to benchmark the

Loads `video` to a numpy array. Args: video (`VideoInput`): The video to convert to the numpy array format. Can be a lin

Wrapper around torch.meshgrid to avoid warning messages about the introduced `indexing` argument. Reference: https://pytorch.org/docs/1.13/g

Just EOS

Pads a batch of images to the bottom and right of the image with zeros to the size of largest height and width in the batch and optio

Adjust the indentation of a docstring to match the specified indent level.

Converts `image` to a numpy array. Optionally rescales it and puts the channel dimension as the first dimension. Args:

Basic Tokenization of a piece of text. For sub-word tokenization, see WordPieceTokenizer. Args: never_split (`List[str]`

Computes the number of placeholder tokens needed for multimodal inputs with the given sizes. Args: image_sizes (`list[lis

Process new points, boxes, or masks for a video frame and add them to the inference session. Args: inference_session (`S

Unified API to get any scheduler from its name. Args: name (`str` or `SchedulerType`): The name of the scheduler to use.

Ensure that the input is a list of videos. If the input is a single video, it is converted to a list of length 1. If the input is a batch of

Get number of (optionally, trainable or non-embeddings) parameters in the module. Args: only_trainable (`bool`, *optiona

Pads a batch of images to the bottom and right of the image with zeros to the size of largest height and width in the batch and optio

When used in normal mode, this method forwards all its arguments to MCTCTFeatureExtractor's [`~MCTCTFeatureExtractor.pad`] and return

This function prepares a list of PIL images for testing

Catches the default value in the description of an argument inside a docstring and replaces it by the value passed. Args: descriptio

require_version wrapper which emits a core-specific hint on failure

Convert a string representation of truth to true (1) or false (0). True values are 'y', 'yes', 't', 'true', 'on', and '1'; false values are 'n',

Convert a PyTorch tensor, Numpy array or python list to a python list.

Export the wrapped module using `torch.export`. Args: input_ids (`Optional[torch.Tensor]`): Tensor repre

Return a logger with the specified name. This function is not supposed to be directly accessed unless you are writing a custom transformers

This function prepares a batch of videos: a list of list of PIL images, or a list of list of numpy arrays if one specifies numpify=True, or a list

Selects the best resolution from a list of possible resolutions based on the original size. This is done by calculating the effective and wa

Calculates spectrograms for a list of waveforms using the Short-Time Fourier Transform, optimized for batch processing. This function extends

Converts `image` to the channel dimension format specified by `channel_dim`. The input can have arbitrary number of leading dimensions. Only

Save this instance to a json file.