U %dC@sddlZddlZddlmZddlmZmZddlZddlm Z ddl m Z ddl m Z ddlmZdZd Zd d d d dddddddddddddddZeeeeee eeefdddZGd d!d!e ZdS)"N)Path)TupleUnion)Tensor)download_url_to_file)Dataset)extract_archiveaewZARCTICZ@645cb33c0f0b2ce41384fdd8d3db2c3f5fc15c1e688baeb74d2e08cab18ab406Z@024664adeb892809d646a3efd043625b46b5bfa3e6189b3500b2d0d59dfab06cZ@2c55bc3050caa996758869126ad10cf42e1441212111db034b3a45189c18b6fcZ@d74a950c9739a65f7bfc4dfa6187f2730fa03de5b8eb3f2da97a51b74df64d3cZ@dd65c3d2907d1ee52f86e44f578319159e60f4bf722a9142be01161d84e330ffZ@26b91aaf48b2799b2956792b4632c2f926cd0542f402b5452d5adecb60942904Z@3f16dc3f3b97955ea22623efb33b444341013fc660677b2e170efdcc959fa7c6Z@8a0ee4e5acbd4b2f61a4fb947c1730ab3adcc9dc50b195981d99391d29928e8aZ@3fcff629412b57233589cdb058f730594a62c4f3a75c20de14afe06621ef45e2Z@dc82e7967cbd5eddbed33074b0699128dbd4482b41711916d58103707e38c67fZ@3a37c0e1dfc91e734fdbc88b562d9e2ebca621772402cdc693bbc9b09b211d73Z@8029cafce8296f9bed3022c44ef1e7953332b6bf6943c14b929f468122532717Z@b23993765cbf2b9e7bbc3c85b6c56eaf292ac81ee4bb887b638a24d104f921a0Z@4faf34d71aa7112813252fb20c5433e2fdd9a9de55a00701ffcbf05f24a5991aZ@c6dc11235629c58441c071a7ba8a2d067903dfefbaabc4056d87da35b72ecda4Z@1fa4271c393e5998d200e56c102ff46fcfea169aaa2148ad9e9469616fbfdd9bZ@54345ed55e45c23d419e9a823eef427f1cc93c83a710735ec667d068c916abf1Z@7c173297916acf3cc7fcab2713be4c60b27312316765a90934651d367226b4ea)z>http://festvox.org/cmu_arctic/packed/cmu_us_aew_arctic.tar.bz2z>http://festvox.org/cmu_arctic/packed/cmu_us_ahw_arctic.tar.bz2z>http://festvox.org/cmu_arctic/packed/cmu_us_aup_arctic.tar.bz2z>http://festvox.org/cmu_arctic/packed/cmu_us_awb_arctic.tar.bz2z>http://festvox.org/cmu_arctic/packed/cmu_us_axb_arctic.tar.bz2z>http://festvox.org/cmu_arctic/packed/cmu_us_bdl_arctic.tar.bz2z>http://festvox.org/cmu_arctic/packed/cmu_us_clb_arctic.tar.bz2z>http://festvox.org/cmu_arctic/packed/cmu_us_eey_arctic.tar.bz2z>http://festvox.org/cmu_arctic/packed/cmu_us_fem_arctic.tar.bz2z>http://festvox.org/cmu_arctic/packed/cmu_us_gka_arctic.tar.bz2z>http://festvox.org/cmu_arctic/packed/cmu_us_jmk_arctic.tar.bz2z>http://festvox.org/cmu_arctic/packed/cmu_us_ksp_arctic.tar.bz2z>http://festvox.org/cmu_arctic/packed/cmu_us_ljm_arctic.tar.bz2z>http://festvox.org/cmu_arctic/packed/cmu_us_lnh_arctic.tar.bz2z>http://festvox.org/cmu_arctic/packed/cmu_us_rms_arctic.tar.bz2z>http://festvox.org/cmu_arctic/packed/cmu_us_rxr_arctic.tar.bz2z>http://festvox.org/cmu_arctic/packed/cmu_us_slp_arctic.tar.bz2z>http://festvox.org/cmu_arctic/packed/cmu_us_slt_arctic.tar.bz2)linepath folder_audio ext_audioreturnc Csd|ddddd\}}|dd}tj||||}t|\}}||||ddfS)Nr _)stripsplitosr join torchaudioload) r r r r Z utterance_idZ transcriptZ file_audioZwaveformZ sample_raterA/tmp/pip-unpacked-wheel-lbdmvq91/torchaudio/datasets/cmuarctic.pyload_cmuarctic_item$s   rc@speZdZdZdZdZdZdZee dfe e e fe e e ddd d Zeeeee e fd d d ZedddZdS) CMUARCTICaGCreate a Dataset for *CMU ARCTIC* [:footcite:`Kominek03cmuarctic`]. Args: root (str or Path): Path to the directory where the dataset is found or downloaded. url (str, optional): The URL to download the dataset from or the type of the dataset to download. (default: ``"aew"``) Allowed type values are ``"aew"``, ``"ahw"``, ``"aup"``, ``"awb"``, ``"axb"``, ``"bdl"``, ``"clb"``, ``"eey"``, ``"fem"``, ``"gka"``, ``"jmk"``, ``"ksp"``, ``"ljm"``, ``"lnh"``, ``"rms"``, ``"rxr"``, ``"slp"`` or ``"slt"``. folder_in_archive (str, optional): The top-level directory of the dataset. (default: ``"ARCTIC"``) download (bool, optional): Whether to download the dataset if it is not found at root path. (default: ``False``). z txt.done.dataetcz.wavZwavFN)rooturlfolder_in_archivedownloadrc CsB|dkr.d|d}d}d}tj|||}t|}tj|}tj||}tj|sht|tj||}|dd}tj|||_|rtj|jstj |st |d} t ||| dt |n tj|jstd |jd tj|j|j|j|_t|jd } tj| d d } t| |_W5QRXdS)N)r ZahwZaupZawbZaxbZbdlZclbZeeyZfemZgkaZjmkZkspZljmZlnhZrmsZrxrZslpZsltZcmu_us_Z_arcticz.tar.bz2z)http://www.festvox.org/cmu_arctic/packed/.r)Z hash_prefixz The path zT doesn't exist. Please check the ``root`` path or set `download=True` to download itr ) delimiter)rr rfspathbasenameisdirmkdirr_pathisfile _CHECKSUMSgetrrexists RuntimeError _folder_text _file_textZ_textopencsvreaderlist_walker) selfrr r!r"Z ext_archivebase_urlr(archiveZchecksumtextwalkerrrr__init__Is6         zCMUARCTIC.__init__)nrcCs|j|}t||j|j|jS)zLoad the n-th sample from the dataset. Args: n (int): The index of the sample to be loaded Returns: (Tensor, int, str, str): ``(waveform, sample_rate, transcript, utterance_id)`` )r7rr+ _folder_audio _ext_audio)r8r>r rrr __getitem__s zCMUARCTIC.__getitem__)rcCs t|jS)N)lenr7)r8rrr__len__szCMUARCTIC.__len__)__name__ __module__ __qualname____doc__r2r1r@r?URLFOLDER_IN_ARCHIVErstrrboolr=intrrrArCrrrrr3s"  > r)r4rpathlibrtypingrrrZtorchrZ torch.hubrZtorch.utils.datarZtorchaudio.datasets.utilsrrHrIr-rJrLrrrrrrs>     "