
    h                     $   S SK r S SKrS SKJr  S SKJrJr  S SKrS SKJ	r	  S SK
Jr  S SKJr  S SKJr  SrS	r0 S
S_SS_SS_SS_SS_SS_SS_SS_SS_SS_SS_S S!_S"S#_S$S%_S&S'_S(S)_S*S+_S,S-0ErS.\S/\S0\S1\S2\\	\\\4   4
S3 jr " S4 S5\5      rg)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                     U S   R                  5       R                  SS5      SS  u  pEUSS n[        R                  R	                  XXC-   5      n[
        R                  " U5      u  pxXxXTR                  S5      S   4$ )Nr          _)stripsplitosr   join
torchaudioload)	r   r   r    r!   utterance_id
transcript
file_audiowaveformsample_rates	            U/var/www/auris/envauris/lib/python3.13/site-packages/torchaudio/datasets/cmuarctic.pyload_cmuarctic_itemr5   $   s{    #Aw}}44S!<QR@L Ab!Jd,2JKJ 'OOJ7H:/A/A#/Fq/IJJ    c                       \ rS rSrSrSrSrSrSr\	\
S4S\\\4   S	\S
\S\SS4
S jjrS\S\\\\\4   4S jrS\4S jrSrg)	CMUARCTIC3   a   *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                     US;   a.  SU-   S-   nSnSn[         R                  R                  XbU-   5      n[         R                  " U5      n[         R                  R	                  U5      n[         R                  R                  X5      n[         R                  R                  U5      (       d  [         R                  " U5        [         R                  R                  X5      nUR                  S5      S   n[         R                  R                  X5      U l        U(       a~  [         R                  R                  U R                  5      (       dO  [         R                  R                  U5      (       d   [        R                  US 5      n	[        X(U	S9  [        U5        OG[         R                  R                  U R                  5      (       d  [        S	U R                   S
35      e[         R                  R                  U R                  U R                   U R"                  5      U l        ['        U R$                  S5       n
[(        R*                  " U
SS9n[-        U5      U l        S S S 5        g ! , (       d  f       g = f)N)r
   ahwaupawbaxbbdlclbeeyfemgkajmkkspljmlnhrmsrxrslpsltcmu_us__arcticz.tar.bz2z)http://www.festvox.org/cmu_arctic/packed/.r   )hash_prefixz	The path zT doesn't exist. Please check the ``root`` path or set `download=True` to download itr
)	delimiter)r+   r   r,   fspathbasenameisdirmkdirr*   _pathisfile
_CHECKSUMSgetr   r	   existsRuntimeError_folder_text
_file_text_textopencsvreaderlist_walker)selfr<   r=   r>   r?   ext_archivebase_urlrZ   archivechecksumtextwalkers               r4   __init__CMUARCTIC.__init__I   s     
 
* c/I-C$KBH'',,x{):;C yy77##C(ww||D4ww}}T""HHTN'',,t.>>#&q)WW\\$1
77==,,ww~~g..)~~c48H(8LW%77>>$**--"

| ,[ [  WW\\$**d.?.?Q
$**c"dZZ5F<DL #""s    &I//
I=nc                 v    U R                   U   n[        X R                  U R                  U R                  5      $ )a  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
)rj   r5   r]   _folder_audio
_ext_audio)rk   rt   r   s      r4   __getitem__CMUARCTIC.__getitem__   s.    $ ||A"4T5G5GYYr6   c                 ,    [        U R                  5      $ )N)lenrj   )rk   s    r4   __len__CMUARCTIC.__len__   s    4<<  r6   )r]   re   rj   )__name__
__module____qualname____firstlineno____doc__rd   rc   rw   rv   URLFOLDER_IN_ARCHIVEr   strr   boolrr   intr   r   rx   r|   __static_attributes__ r6   r4   r8   r8   3   s      !JLJM 25O`sx<(#t)$<(+.<(IL<(lp<(	<(|ZS ZU63S+@%A Z*! !r6   r8   )rg   r+   pathlibr   typingr   r   r-   torchr   torch.utils.datar   torchaudio._internalr   torchaudio.datasets.utilsr	   r   r   r_   r   r   r5   r8   r   r6   r4   <module>r      s   
 	     $ 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   