^jFdZddlmZddlmZeGddeZdgZy)z$Speech processor class for SpeechT5.)ProcessorMixin)auto_docstringc4eZdZfdZedZdZxZS)SpeechT5Processorc&t|||y)N)super__init__)selffeature_extractor tokenizer __class__s {/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/speecht5/processing_speecht5.pyr zSpeechT5Processor.__init__s *I6c<|jdd}|jdd}|jdd}|jdd}|jdd}| | td| | td||| | td||j|g|d|i|}n||j|fi|}nd}||j|||d |} | d } n||j|fi|} | d } nd} || S|  |d <| j d } | | |d<|S)Naudiotext text_target audio_target sampling_ratez\Cannot process both `audio` and `text` inputs. Did you mean `audio_target` or `text_target`?z\Cannot process both `audio_target` and `text_target` inputs. Did you mean `audio` or `text`?zaYou need to specify either an `audio`, `audio_target`, `text`, or `text_target` input to process.)rr input_values input_idslabelsattention_maskdecoder_attention_mask)pop ValueErrorr r get) r argskwargsrrrrrinputstargetsrrs r__call__zSpeechT5Processor.__call__s 7D)zz&$'jj5 zz.$7  ?D9  !1n   # (?n  =\1dl{GZs   +T++E`D` `Y_`F  #T^^D3F3FF  #,d,,,]juntuG^,F  $$dnn[;F;G[)FG >N  %F8 %,[[1A%B "%13I/0 rc|jdd}|jdd}|jdd}| | td|| | td|!|jj|g|i|}n"||jj|fi|}nd}|d|vst |t r*d|dvr#|jj|fi|}|d}nt|jj}|jj|j_|jj|g|i|}||j_|d}nd}||S|||d<|jd} | | |d <|S) au Collates the audio and text inputs, as well as their targets, into a padded batch. Audio inputs are padded by SpeechT5FeatureExtractor's [`~SpeechT5FeatureExtractor.pad`]. Text inputs are padded by SpeechT5Tokenizer's [`~SpeechT5Tokenizer.pad`]. Valid input combinations are: - `input_ids` only - `input_values` only - `labels` only, either log-mel spectrograms or text tokens - `input_ids` and log-mel spectrogram `labels` - `input_values` and text `labels` Please refer to the docstring of the above two methods for more information. rNrrz:Cannot process both `input_values` and `input_ids` inputs.zZYou need to specify either an `input_values`, `input_ids`, or `labels` input to be padded.rr) rrr padr isinstancelist feature_size num_mel_binsr) r rrrrrr r!feature_size_hackrs rr%zSpeechT5Processor.padJs"zz.$7 JJ{D1 Hd+  # (=YZ Z  I$5&.l   #/T++// NtNvNF  "'T^^'' v> -$($:$:$G$G!6:6L6L6Y6Y&&34$0044VMdMfM6G&&3 0G >N  %F8 %,[[1A%B "%13I/0 r)__name__ __module__ __qualname__r rr"r% __classcell__)r s@rrrs"7..`:rrN)__doc__processing_utilsrutilsrr__all__rrr4s9+.#oood  r