U ,:%e @sddlZddlZddlmZddlmZmZmZmZddl Z ddl m Z ddl m Z eeeeeeeee eeeeffdddZGd d d e ZdS) N)Path)DictListTupleUnion)Tensor)Dataset)lineheaderpath folder_audio ext_audioreturnc Csn|ddkrtd|d|d}tj|||}||sH||7}t|\}}tt||} ||| fS)Nr z)expect `header[1]` to be 'path', but got ) ValueErrorosr joinendswith torchaudioloaddictzip) r r r r r ZfileidfilenameZwaveformZ sample_rateZdicr^/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/torchaudio/datasets/commonvoice.pyload_commonvoice_item s  rc@sheZdZdZdZdZdZdeee fedddd Z e e e e eeeffd d d Ze d ddZdS) 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.mp3Zclips train.tsvN)roottsvrc Cs\t||_tj|j||_t|jd(}tj|dd}t ||_ t ||_ W5QRXdS)Nr ) delimiter) rfspath_pathr rZ_tsvopencsvreadernext_headerlist_walker)selfrrZtsv_Zwalkerrrr__init__.s   zCOMMONVOICE.__init__)nrcCs"|j|}t||j|j|j|jS)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 Dict[str, str]: Dictionary containing the following items from the corresponding TSV file; * ``"client_id"`` * ``"path"`` * ``"sentence"`` * ``"up_votes"`` * ``"down_votes"`` * ``"age"`` * ``"gender"`` * ``"accent"`` )r+rr)r$ _folder_audio _ext_audio)r,r.r rrr __getitem__9s zCOMMONVOICE.__getitem__)rcCs t|jS)N)lenr+)r,rrr__len__UszCOMMONVOICE.__len__)r)__name__ __module__ __qualname____doc__Z_ext_txtr0r/rstrrr-intrrrr1r3rrrrrs  "r)r&rpathlibrtypingrrrrrZtorchrZtorch.utils.datarr8r9rrrrrrs