:j ddlZddlZddlmZddlmZmZmZmZddl Z ddl m Z ddl m Z deedeeded ed ed ee eeeefff d ZGd de Zy)N)Path)DictListTupleUnion)Tensor)Datasetlineheaderpath folder_audio ext_audioreturnc|ddk7rtd|d|d}tjj|||}|j |s||z }t j |\}}tt||} ||| fS)Nr z)expect `header[1]` to be 'path', but got ) ValueErrorosr joinendswith torchaudioloaddictzip) r r r r rfileidfilenamewaveform sample_ratedics t/home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/torchaudio/datasets/commonvoice.pyload_commonvoice_itemr s ayFDVAYKPQQ !WFww||D,7H   Y 'I&OOH5Hk s64 !C [# %%c neZdZdZdZdZdZd deee fdeddfd Z d e de e e eeefffd Zde fd Zy) COMMONVOICEa*CommonVoice* :cite:`ardila2020common` dataset. Args: root (str or Path): Path to the directory where the dataset is located. (Where the ``tsv`` file is present.) tsv (str, optional): The name of the tsv file used to construct the metadata, such as ``"train.tsv"``, ``"test.tsv"``, ``"dev.tsv"``, ``"invalidated.tsv"``, ``"validated.tsv"`` and ``"other.tsv"``. (default: ``"train.tsv"``) z.txtz.mp3clipsroottsvrNcZtj||_tjj |j||_t |j d5}tj|d}t||_ t||_ dddy#1swYyxYw)Nr ) delimiter) rfspath_pathr r_tsvopencsvreadernext_headerlist_walker)selfr%r&tsv_walkers r__init__zCOMMONVOICE.__init__.sxYYt_ GGLLS1 $))S ! (TZZ5FrMsz ++$& s)&!#Y&.1&AD&QT& 63S#X &'&&8!'8!r!