U 9%e@s$dZddlmZGdddeZdS)z$Speech processor class for SpeechT5.)ProcessorMixincsHeZdZdZdZdZfddZddZdd Zd d Z d d Z Z S)SpeechT5Processora} Constructs a SpeechT5 processor which wraps a feature extractor and a tokenizer into a single processor. [`SpeechT5Processor`] offers all the functionalities of [`SpeechT5FeatureExtractor`] and [`SpeechT5Tokenizer`]. See the docstring of [`~SpeechT5Processor.__call__`] and [`~SpeechT5Processor.decode`] for more information. Args: feature_extractor (`SpeechT5FeatureExtractor`): An instance of [`SpeechT5FeatureExtractor`]. The feature extractor is a required input. tokenizer (`SpeechT5Tokenizer`): An instance of [`SpeechT5Tokenizer`]. The tokenizer is a required input. ZSpeechT5FeatureExtractorZSpeechT5Tokenizercst||dS)N)super__init__)selffeature_extractor tokenizer __class__o/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/transformers/models/speecht5/processing_speecht5.pyr$szSpeechT5Processor.__init__c Osb|dd}|dd}|dd}|dd}|dd}|dk rT|dk rTtd|dk rl|dk rltd|dkr|dkr|dkr|dkrtd |dk r|j|f|d|i|}n|dk r|j|f|}nd}|dk r|j|||d |} | d } n&|dk r|j|f|} | d } nd} |dkr0| S| dk r^| |d <| d} | dk r^| |d<|S)a Processes audio and text input, as well as audio and text targets. You can process audio by using the argument `audio`, or process audio targets by using the argument `audio_target`. This forwards the arguments to SpeechT5FeatureExtractor's [`~SpeechT5FeatureExtractor.__call__`]. You can process text by using the argument `text`, or process text labels by using the argument `text_target`. This forwards the arguments to SpeechT5Tokenizer's [`~SpeechT5Tokenizer.__call__`]. Valid input combinations are: - `text` only - `audio` only - `text_target` only - `audio_target` only - `text` and `audio_target` - `audio` and `audio_target` - `text` and `text_target` - `audio` and `text_target` Please refer to the docstring of the above two methods for more information. audioNtext text_target audio_target sampling_ratez\Cannot process both `audio` and `text` inputs. Did you mean `audio_target` or `text_target`?z\Cannot process both `audio_target` and `text_target` inputs. Did you mean `audio` or `text`?zaYou need to specify either an `audio`, `audio_target`, `text`, or `text_target` input to process.)rr input_values input_idslabelsattention_maskdecoder_attention_mask)pop ValueErrorrrget) rargskwargsr rrrrinputstargetsrrr r r __call__'sJ             zSpeechT5Processor.__call__c OsX|dd}|dd}|dd}|dk r<|dk rs