fTh0SrSSKJr "SS\5rS/rg)z$Speech processor class for SpeechT5.)ProcessorMixincL^\rSrSrSrSrSrU4SjrSrSr Sr S r S r U=r $) SpeechT5ProcessoraY Constructs a SpeechT5 processor which wraps a feature extractor and a tokenizer into a single processor. [`SpeechT5Processor`] offers all the functionalities of [`SpeechT5FeatureExtractor`] and [`SpeechT5Tokenizer`]. See the docstring of [`~SpeechT5Processor.__call__`] and [`~SpeechT5Processor.decode`] for more information. Args: feature_extractor (`SpeechT5FeatureExtractor`): An instance of [`SpeechT5FeatureExtractor`]. The feature extractor is a required input. tokenizer (`SpeechT5Tokenizer`): An instance of [`SpeechT5Tokenizer`]. The tokenizer is a required input. SpeechT5FeatureExtractorSpeechT5Tokenizerc$>[TU]X5 g)N)super__init__)selffeature_extractor tokenizer __class__s h/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/speecht5/processing_speecht5.pyr SpeechT5Processor.__init__%s *6cVURSS5nURSS5nURSS5nURSS5nURSS5nUbUb [S5eUbUb [S5eUcUcUcUc [S 5eUbUR"U/UQ7SU0UD6nOUbUR"U40UD6nOSnUbUR"XUS .UD6n U S n OUbUR"U40UD6n U S n OSn UcU $U bW US 'U R S5n U bXS'U$)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 ValueErrorr rget) r argskwargsrrrrrinputstargetsrrs r__call__SpeechT5Processor.__call__(s0 7D)zz&$'jj5 zz.$7  ?D9  !1n   # (?n  =\1dl{GZs   ++E`D` `Y_`F  ^^D3F3FF  #,,]juntuG^,F  $nn[;F;G[)FG >N  %F8 %,[[1A%B "%13I/0 rc URSS5nURSS5nURSS5nUbUb [S5eUcUcUc [S5eUb!URR"U/UQ70UD6nO#UbURR"U40UD6nOSnUbSU;d[ U[ 5(a,SUS;a#URR"U40UD6nUSnOsURRnURRURlURR"U/UQ70UD6nXRlUSnOSnUcU$UbXVS'URS5n U bXS 'U$) a Collates the audio and text inputs, as well as their targets, into a padded batch. Audio inputs are padded by SpeechT5FeatureExtractor's [`~SpeechT5FeatureExtractor.pad`]. Text inputs are padded by SpeechT5Tokenizer's [`~SpeechT5Tokenizer.pad`]. Valid input combinations are: - `input_ids` only - `input_values` only - `labels` only, either log-mel spectrograms or text tokens - `input_ids` and log-mel spectrogram `labels` - `input_values` and text `labels` Please refer to the docstring of the above two methods for more information. rNrrz:Cannot process both `input_values` and `input_ids` inputs.zZYou need to specify either an `input_values`, `input_ids`, or `labels` input to be padded.rr) rrr padr isinstancelist feature_size num_mel_binsr ) r r!r"rrrr#r$feature_size_hackrs rr)SpeechT5Processor.pados"zz.$7 JJ{D1 Hd+  # (=YZ Z  I$5&.l   #++// NtNvNF  "^^'' v> -$($:$:$G$G!6:6L6L6Y6Y&&30044VMdMfM6G&&3 0G >N  %8 %,[[1A%B "%13I/0 rc:URR"U0UD6$)z This method forwards all its arguments to SpeechT5Tokenizer's [`~SpeechT5Tokenizer.batch_decode`]. Please refer to the docstring of this method for more information. )r batch_decoder r!r"s rr1SpeechT5Processor.batch_decodes ~~**D;F;;rc:URR"U0UD6$)z This method forwards all its arguments to SpeechT5Tokenizer's [`~SpeechT5Tokenizer.decode`]. Please refer to the docstring of this method for more information. )rdecoder2s rr5SpeechT5Processor.decodes ~~$$d5f55r)__name__ __module__ __qualname____firstlineno____doc__feature_extractor_classtokenizer_classr r%r)r1r5__static_attributes__ __classcell__)rs@rrrs6 9)O7EN:x<66rrN)r<processing_utilsrr__all__r7rrrCs&+.c6c6L  r