~Vji vddlZddlZddlmZddlmZmZddlmZddl m Z ddl m Z dZ Gdd e ZdS) N)Path)TupleUnion)Tensor)Dataset)_load_waveformi>c eZdZdZd deeefdefdZdede eeeeeeeeffdZ defd Z dede e eeeeeeeffd Z d S) FluentSpeechCommandsa+*Fluent Speech Commands* :cite:`fluent` dataset Args: root (str of Path): Path to the directory where the dataset is found. subset (str, optional): subset of the dataset to use. Options: [``"train"``, ``"valid"``, ``"test"``]. (Default: ``"train"``) trainrootsubsetc"|dvrtdtj|}tj|d|_tj|jstdtj|jd|d}t|5}tj |}t|}dddn #1swxYwY|d|_ |dd|_ dS) N)r validtestz2`subset` must be one of ['train', 'valid', 'test']fluent_speech_commands_datasetzDataset not found.dataz _data.csvr) ValueErrorosfspathpathjoin_pathisdir RuntimeErroropencsvreaderlistheaderr)selfr r subset_path subset_csv subset_readerrs \/root/voice-cloning/.venv/lib/python3.11/site-packages/torchaudio/datasets/fluentcommands.py__init__zFluentSpeechCommands.__init__s' 3 3 3QRR RyW\\$(HII w}}TZ(( 5344 4gll4:v&7K7K7KLL +   '*Jz22M &&D ' ' ' ' ' ' ' ' ' ' ' ' ' ' '1g H s8$C((C,/C,nreturncL|j|}||jddd}|dd}|dd\}}}}}tjdd ||d } | t||||||fS) aGet metadata for the n-th sample from the dataset. Returns filepath instead of waveform, but otherwise returns the same fields as :py:func:`__getitem__`. Args: n (int): The index of the sample to be loaded Returns: Tuple of the following items; str: Path to audio int: Sample rate str: File name int: Speaker ID str: Transcription str: Action str: Object str: Location r/.rNwavsspeakersz.wav)rr indexsplitrrr SAMPLE_RATE) r!r'sample file_name speaker_id transcriptionactionobjlocation file_paths r% get_metadataz!FluentSpeechCommands.get_metadata)s614;,,V445;;C@@D OOC((+ ;A!"":8 M63GLLZIASASASTT +y*mVUXZbbbc*t|jS)N)lenr)r!s r%__len__zFluentSpeechCommands.__len__Ms49~~r<c||}t|j|d|d}|f|ddzS)aLoad the n-th sample from the dataset. Args: n (int): The index of the sample to be loaded Returns: Tuple of the following items; Tensor: Waveform int: Sample rate str: File name int: Speaker ID str: Transcription str: Action str: Object str: Location rrN)r;rr)r!r'metadatawaveforms r% __getitem__z FluentSpeechCommands.__getitem__PsG4$$Q''!$*hqk8A;GG{Xabb\))r<N)r )__name__ __module__ __qualname____doc__rstrrr&intrr;r?rrCr<r%r r sU39-s$"cc"ceCc3S#s,R&S"c"c"c"cH*S*U63S#sCQT+T%U******r<r )rrpathlibrtypingrrtorchrtorch.utils.datartorchaudio.datasets.utilsrr2r rJr<r%rPs $$$$$$444444 _*_*_*_*_*7_*_*_*_*_*r<