
    ujh                     "   d dl Z d dlZd dlmZ d dlmZmZ d dlZd dlm	Z	 d dl
mZ d dlmZ d dlmZ dZd	Zi d
dddddddddddddddddddddd d!d"d#d$d%d&d'd(d)d*d+d,d-iZd.ed/ed0ed1ed2ee	eeef   f
d3Z G d4 d5e      Zy)6    N)Path)TupleUnion)Tensor)Dataset)download_url_to_file)_extract_taraewARCTICz>http://festvox.org/cmu_arctic/packed/cmu_us_aew_arctic.tar.bz2@645cb33c0f0b2ce41384fdd8d3db2c3f5fc15c1e688baeb74d2e08cab18ab406z>http://festvox.org/cmu_arctic/packed/cmu_us_ahw_arctic.tar.bz2@024664adeb892809d646a3efd043625b46b5bfa3e6189b3500b2d0d59dfab06cz>http://festvox.org/cmu_arctic/packed/cmu_us_aup_arctic.tar.bz2@2c55bc3050caa996758869126ad10cf42e1441212111db034b3a45189c18b6fcz>http://festvox.org/cmu_arctic/packed/cmu_us_awb_arctic.tar.bz2@d74a950c9739a65f7bfc4dfa6187f2730fa03de5b8eb3f2da97a51b74df64d3cz>http://festvox.org/cmu_arctic/packed/cmu_us_axb_arctic.tar.bz2@dd65c3d2907d1ee52f86e44f578319159e60f4bf722a9142be01161d84e330ffz>http://festvox.org/cmu_arctic/packed/cmu_us_bdl_arctic.tar.bz2@26b91aaf48b2799b2956792b4632c2f926cd0542f402b5452d5adecb60942904z>http://festvox.org/cmu_arctic/packed/cmu_us_clb_arctic.tar.bz2@3f16dc3f3b97955ea22623efb33b444341013fc660677b2e170efdcc959fa7c6z>http://festvox.org/cmu_arctic/packed/cmu_us_eey_arctic.tar.bz2@8a0ee4e5acbd4b2f61a4fb947c1730ab3adcc9dc50b195981d99391d29928e8az>http://festvox.org/cmu_arctic/packed/cmu_us_fem_arctic.tar.bz2@3fcff629412b57233589cdb058f730594a62c4f3a75c20de14afe06621ef45e2z>http://festvox.org/cmu_arctic/packed/cmu_us_gka_arctic.tar.bz2@dc82e7967cbd5eddbed33074b0699128dbd4482b41711916d58103707e38c67fz>http://festvox.org/cmu_arctic/packed/cmu_us_jmk_arctic.tar.bz2@3a37c0e1dfc91e734fdbc88b562d9e2ebca621772402cdc693bbc9b09b211d73z>http://festvox.org/cmu_arctic/packed/cmu_us_ksp_arctic.tar.bz2@8029cafce8296f9bed3022c44ef1e7953332b6bf6943c14b929f468122532717z>http://festvox.org/cmu_arctic/packed/cmu_us_ljm_arctic.tar.bz2@b23993765cbf2b9e7bbc3c85b6c56eaf292ac81ee4bb887b638a24d104f921a0z>http://festvox.org/cmu_arctic/packed/cmu_us_lnh_arctic.tar.bz2@4faf34d71aa7112813252fb20c5433e2fdd9a9de55a00701ffcbf05f24a5991az>http://festvox.org/cmu_arctic/packed/cmu_us_rms_arctic.tar.bz2@c6dc11235629c58441c071a7ba8a2d067903dfefbaabc4056d87da35b72ecda4z>http://festvox.org/cmu_arctic/packed/cmu_us_rxr_arctic.tar.bz2@1fa4271c393e5998d200e56c102ff46fcfea169aaa2148ad9e9469616fbfdd9bz>http://festvox.org/cmu_arctic/packed/cmu_us_slp_arctic.tar.bz2@54345ed55e45c23d419e9a823eef427f1cc93c83a710735ec667d068c916abf1z>http://festvox.org/cmu_arctic/packed/cmu_us_slt_arctic.tar.bz2@7c173297916acf3cc7fcab2713be4c60b27312316765a90934651d367226b4ealinepathfolder_audio	ext_audioreturnc                    | d   j                         j                  dd      dd  \  }}|dd }t        j                  j	                  ||||z         }t        j                  |      \  }}||||j                  d      d   fS )Nr          _)stripsplitosr   join
torchaudioload)	r   r   r    r!   utterance_id
transcript
file_audiowaveformsample_rates	            [/var/www/html/dev/engine/venv/lib/python3.12/site-packages/torchaudio/datasets/cmuarctic.pyload_cmuarctic_itemr5   $   s    #Aw}}44S!<QR@L* Ab!JdL,2JKJ 'OOJ7Hkk:|/A/A#/Fq/IJJ    c                   x    e Zd ZdZdZdZdZdZee	dfde
eef   ded	ed
eddf
dZdedeeeeef   fdZdefdZy)	CMUARCTICa4  *CMU ARCTIC* :cite:`Kominek03cmuarctic` dataset.

    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.dataetcz.wavwavFrooturlfolder_in_archivedownloadr"   Nc                    |dv r/d|z   dz   }d}d}t         j                  j                  |||z         }t        j                  |      }t         j                  j	                  |      }t         j                  j                  ||      }t         j                  j                  |      st        j                  |       t         j                  j                  ||      }|j                  d      d   }t         j                  j                  ||      | _        |rxt         j                  j                  | j                        st         j                  j                  |      s$t        j                  |d       }	t        |||	       t        |       nBt         j                  j                  | j                        st        d	| j                   d
      t         j                  j                  | j                  | j                   | j"                        | _        t'        | j$                  d      5 }
t)        j*                  |
d      }t-        |      | _        d d d        y # 1 sw Y   y xY w)N)r
   ahwaupawbaxbbdlclbeeyfemgkajmkkspljmlnhrmsrxrslpsltcmu_us__arcticz.tar.bz2z)http://www.festvox.org/cmu_arctic/packed/.r   )hash_prefixz	The path zT doesn't exist. Please check the ``root`` path or set `download=True` to download itr
)	delimiter)r+   r   r,   fspathbasenameisdirmkdirr*   _pathisfile
_CHECKSUMSgetr   r	   existsRuntimeError_folder_text
_file_text_textopencsvreaderlist_walker)selfr;   r<   r=   r>   ext_archivebase_urlrY   archivechecksumtextwalkers               r4   __init__zCMUARCTIC.__init__I   s     
 
* c/I-C$KBH'',,x{):;C yy77##C(ww||D"34ww}}T"HHTN'',,tX.>>#&q)WW\\$1
77==,ww~~g.)~~c48H(g8LW%77>>$**-"

| ,[ [  WW\\$**d.?.?Q
$**c" 	(dZZ5F<DL	( 	( 	(s   +(II%nc                 x    | j                   |   }t        || j                  | j                  | j                        S )ai  Load 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:
                Transcript
            str:
                Utterance ID
        )ri   r5   r\   _folder_audio
_ext_audio)rj   rr   r   s      r4   __getitem__zCMUARCTIC.__getitem__   s0    $ ||A"4T5G5GYYr6   c                 ,    t        | j                        S )N)lenri   )rj   s    r4   __len__zCMUARCTIC.__len__   s    4<<  r6   )__name__
__module____qualname____doc__rc   rb   ru   rt   URLFOLDER_IN_ARCHIVEr   strr   boolrq   intr   r   rv   ry    r6   r4   r8   r8   3   s      !JLJM 25O`sx<(#t)$<(+.<(IL<(lp<(	<(|ZS ZU63S+@%A Z*! !r6   r8   )rf   r+   pathlibr   typingr   r   r-   torchr   torch.utils.datar   torchaudio._internalr   torchaudio.datasets.utilsr	   r~   r   r^   r   r   r5   r8   r   r6   r4   <module>r      s   
 	     $ 5 2 D  GID  GI E  GI E  GI	
 E  GI E  GI E  GI E  GI E  GI E  GI E  GI E  GI E  GI E  GI E  GI  E  GI!" E  GI#$ E  GI%
,Kc K KC KC KTYZ`begjloZoTp Kj! j!r6   