
    fThL                     <    S r SSKJr  SSKJr   " S S\5      rS/rg)z%
Audio/Text processor class for CLAP
   )ProcessorMixin)BatchEncodingc                   Z   ^  \ rS rSrSrSrSrU 4S jrSS jrS r	S r
\S	 5       rS
rU =r$ )ClapProcessor   a  
Constructs a CLAP processor which wraps a CLAP feature extractor and a RoBerta tokenizer into a single processor.

[`ClapProcessor`] offers all the functionalities of [`ClapFeatureExtractor`] and [`RobertaTokenizerFast`]. See the
[`~ClapProcessor.__call__`] and [`~ClapProcessor.decode`] for more information.

Args:
    feature_extractor ([`ClapFeatureExtractor`]):
        The audio processor is a required input.
    tokenizer ([`RobertaTokenizerFast`]):
        The tokenizer is a required input.
ClapFeatureExtractor)RobertaTokenizerRobertaTokenizerFastc                 $   > [         TU ]  X5        g N)super__init__)selffeature_extractor	tokenizer	__class__s      `/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/clap/processing_clap.pyr   ClapProcessor.__init__(   s    *6    c                 
   UR                  SS5      nUc  Uc  [        S5      eUb  U R                  " U4SU0UD6nUb  U R                  " U4XSS.UD6nUb  Ub  WR	                  W5        U$ Ub  W$ [        [        S0 WD6US9$ )a/  
Main method to prepare for the model one or several sequences(s) and audio(s). This method forwards the `text`
and `kwargs` arguments to RobertaTokenizerFast's [`~RobertaTokenizerFast.__call__`] if `text` is not `None` to
encode the text. To prepare the audio(s), this method forwards the `audios` and `kwrags` arguments to
ClapFeatureExtractor's [`~ClapFeatureExtractor.__call__`] if `audios` is not `None`. Please refer to the
docstring of the above two methods for more information.

Args:
    text (`str`, `List[str]`, `List[List[str]]`):
        The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
        (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
        `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
    audios (`np.ndarray`, `torch.Tensor`, `List[np.ndarray]`, `List[torch.Tensor]`):
        The audio or batch of audios to be prepared. Each audio can be NumPy array or PyTorch tensor. In case
        of a NumPy array/PyTorch tensor, each audio should be of shape (C, T), where C is a number of channels,
        and T the sample length of the audio.

    return_tensors (`str` or [`~utils.TensorType`], *optional*):
        If set, will return tensors of a particular framework. Acceptable values are:

        - `'tf'`: Return TensorFlow `tf.constant` objects.
        - `'pt'`: Return PyTorch `torch.Tensor` objects.
        - `'np'`: Return NumPy `np.ndarray` objects.
        - `'jax'`: Return JAX `jnp.ndarray` objects.

Returns:
    [`BatchEncoding`]: A [`BatchEncoding`] with the following fields:

    - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`.
    - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when
      `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not
      `None`).
    - **audio_features** -- Audio features to be fed to a model. Returned when `audios` is not `None`.
sampling_rateNz?You have to specify either text or audios. Both cannot be none.return_tensors)r   r   )datatensor_type )pop
ValueErrorr   r   updater   dict)r   textaudiosr   kwargsr   encodingaudio_featuress           r   __call__ClapProcessor.__call__+   s    F 

?D9<FN^__~~dT>TVTH!33&3V\N  2OON+OO d&<^&<.YYr   c                 :    U R                   R                  " U0 UD6$ )z
This method forwards all its arguments to RobertaTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please
refer to the docstring of this method for more information.
)r   batch_decoder   argsr"   s      r   r(   ClapProcessor.batch_decodec   s    
 ~~**D;F;;r   c                 :    U R                   R                  " U0 UD6$ )z
This method forwards all its arguments to RobertaTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer
to the docstring of this method for more information.
)r   decoder)   s      r   r-   ClapProcessor.decodej   s    
 ~~$$d5f55r   c                     U R                   R                  nU R                  R                  n[        [        R                  X-   5      5      $ r   )r   model_input_namesr   listr   fromkeys)r   tokenizer_input_namesfeature_extractor_input_namess      r   r0   ClapProcessor.model_input_namesq   s<     $ @ @(,(>(>(P(P%DMM"7"WXYYr   r   )NNN)__name__
__module____qualname____firstlineno____doc__feature_extractor_classtokenizer_classr   r%   r(   r-   propertyr0   __static_attributes____classcell__)r   s   @r   r   r      sA     5BO76Zp<6 Z Zr   r   N)r:   processing_utilsr   tokenization_utils_baser   r   __all__r   r   r   <module>rC      s-    / 4^ZN ^ZB 
r   