h<dZddlmZddlmZGddeZdgZy)z% Audio/Text processor class for CLAP )ProcessorMixin) BatchEncodingc2eZdZdZdZdZfdZddZxZS) ClapProcessora 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)RobertaTokenizerRobertaTokenizerFastc&t|||y)N)super__init__)selffeature_extractor tokenizer __class__s f/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/transformers/models/clap/processing_clap.pyr zClapProcessor.__init__(s *I6c |jdd}| | td||j|fd|i|}||j|f||d|}||j |S|St t di|S)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)rr)data tensor_type)pop ValueErrorrrupdaterdict)r textaudiosrkwargsrencodingaudio_featuress r__call__zClapProcessor.__call__+sF ?D9 TVTH  3T33&3NV\N   2 OON +O  O d&<^&<.Y Yr)NNN) __name__ __module__ __qualname____doc__feature_extractor_classtokenizer_classr r" __classcell__)rs@rrrs  5BO76ZrrN)r&processing_utilsrtokenization_utils_baserr__all__rrrr-s-/4JZNJZZ  r