qisdZddlZddlZddlmZddlmZddlm Z m Z m Z ddl m Z mZddlmZed eGd d eZd gZy) zProcessor class for Pop2Piano.N) BatchFeature)ProcessorMixin) BatchEncodingPaddingStrategyTruncationStrategy) TensorTypeauto_docstring)requires)essentialibrosa pretty_midiscipytorch)backendsc,eZdZfdZe ddej eezeej zde ee zdzde de dzdee zde e ze zd e e zezd e dzd e dzd e d eezfdZ ddede d efdZfdZedZxZS)Pop2PianoProcessorc&t|||yN)super__init__)selffeature_extractor tokenizer __class__s d/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/pop2piano/processing_pop2piano.pyrzPop2PianoProcessor.__init__s *I6Naudio sampling_ratesteps_per_beatresamplenotespadding truncation max_lengthpad_to_multiple_ofverbosereturnc || | td|||jd||||d| } ||jd||||| | d| } | S|| S d d<| S)a sampling_rate (`int` or `list[int]`, *optional*): The sampling rate of the input audio in Hz. This should match the sampling rate used by the feature extractor. If not provided, the default sampling rate from the processor configuration will be used. steps_per_beat (`int`, *optional*, defaults to `2`): The number of time steps per musical beat. This parameter controls the temporal resolution of the musical representation. A higher value provides finer temporal granularity but increases the sequence length. Used when processing audio to extract musical features. notes (`list` or `TensorType`, *optional*): Pre-extracted musical notes in MIDI format. When provided, the processor skips audio feature extraction and directly processes the notes through the tokenizer. Each note should be represented as a list or tensor containing pitch, velocity, and timing information. z{You have to specify at least audios and sampling_rate in order to use feature extractor or notes to use the tokenizer part.)rrr r!)r"r#r$r%r&r' token_ids) ValueErrorrr)rrrr r!r"r#r$r%r&r'kwargsinputsencoded_token_idss r__call__zPop2PianoProcessor.__call__!s< Mm3%-3   !:+T+++-!   F   .!%%#5 !!  =M ]m3$ $#4K"@F; Mrfeature_extractor_output return_midic>|jj|||S)z This method uses [`Pop2PianoTokenizer.batch_decode`] method to convert model generated token_ids to midi_notes. Please refer to the docstring of the above two methods for more information. )r*r1r2)r batch_decode)rr*r1r2s rr4zPop2PianoProcessor.batch_decodebs)~~**:R`k+  rc tjj|rtd|dtj|dt ||fi|S)NzProvided path (z#) should be a directory, not a fileT)exist_ok)ospathisfiler,makedirsrsave_pretrained)rsave_directoryr-rs rr;z"Pop2PianoProcessor.save_pretrainedrsL 77>>. )~.>>abc c NT2w&~@@@rc 2|j|fi|}||Sr)_get_arguments_from_pretrained)clspretrained_model_name_or_pathr-argss rfrom_pretrainedz"Pop2PianoProcessor.from_pretrainedxs%1s112OZSYZDzr) NNTNFNNNT)T)__name__ __module__ __qualname__rr npndarraylistfloatintboolr strrrrrr0r4r; classmethodrB __classcell__)rs@rrrs=7>B04 $#'056:!%)->zzDK'$rzz*::>T#Y-> > + > j >o->3J!33>$J> $J>>  %>>H!  #/     A rr)__doc__r7numpyrGfeature_extraction_utilsrprocessing_utilsrtokenization_pythonrrrutilsr r utils.import_utilsr r__all__r+rrrXsZ% 4.UU/* KL^^M^B r