ujh nddlZddlZddlmZddlmZmZddlmZddl m Z ddl m Z dZ Gdd e Zy) N)Path)TupleUnion)Tensor)Dataset)_load_waveformi>c eZdZdZd deeefdefdZdede eeeeeeeeffdZ defdZ dede e eeeeeeeffd Z y ) 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"``) rootsubsetc|dvr tdtj|}tjj |d|_tjj |j s tdtjj |j d|d}t|5}tj|}t|}dddd|_ |dd|_ y#1swYxYw) N)trainvalidtestz2`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 `/var/www/html/dev/engine/venv/lib/python3.12/site-packages/torchaudio/datasets/fluentcommands.py__init__zFluentSpeechCommands.__init__s 3 3QR RyyWW\\$(HI ww}}TZZ(34 4ggll4::v&7KL +  '*JJz2M &D '1g H  ' 's 7!C55C>nreturnc$|j|}||jjdjdd}|jdd}|dd\}}}}}tj j dd ||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;;,,V45;;C@D OOC(+ ;A!":8 M63GGLLZI;dAST +y*mVUXZbbbc,t|jS)N)lenr)r!s r%__len__zFluentSpeechCommands.__len__Ms499~r<cp|j|}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__PsA4$$Q'!$**hqk8A;G{Xab\))r<N)r)__name__ __module__ __qualname____doc__rstrrr&intrr;r?rrCr<r%r r sU39-s$"cc"ceCc3S#s,R&S"cH*S*U63S#sCQT+T%U*r<r )rrpathlibrtypingrrtorchrtorch.utils.datartorchaudio.datasets.utilsrr2r rJr<r%rPs- $4 _*7_*r<