o ZhL@s6dZddlmZddlmZGdddeZdgZdS)z% Audio/Text processor class for CLAP )ProcessorMixin) BatchEncodingcsNeZdZdZdZdZfddZdddZd d Zd d Z e d dZ Z S) 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. ZClapFeatureExtractor)ZRobertaTokenizerZRobertaTokenizerFastcst||dSN)super__init__)selffeature_extractor tokenizer __class__W/var/www/auris/lib/python3.10/site-packages/transformers/models/clap/processing_clap.pyr(szClapProcessor.__init__NcKs|dd}|dur|durtd|dur!|j|fd|i|}|dur1|j|f||d|}|dur@|dur@|||S|durF|Sttdi||dS)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)dataZ tensor_typer )pop ValueErrorr r updaterdict)rtextZaudiosrkwargsrencodingZaudio_featuresr r r__call__+s& # zClapProcessor.__call__cO|jj|i|S)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_decoderargsrr r rrczClapProcessor.batch_decodecOr)z This method forwards all its arguments to RobertaTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )r decoderr r rrjrzClapProcessor.decodecCs"|jj}|jj}tt||Sr)r model_input_namesr listrfromkeys)rZtokenizer_input_namesZfeature_extractor_input_namesr r rr qszClapProcessor.model_input_names)NNN) __name__ __module__ __qualname____doc__Zfeature_extractor_classZtokenizer_classrrrrpropertyr __classcell__r r r rrs   8rN)r&Zprocessing_utilsrZtokenization_utils_baserr__all__r r r rs    a