o
    *i                     @   s  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
d3d4ZG d5d6 d6eZdS )7    N)Path)TupleUnion)Tensor)Dataset)download_url_to_file)_extract_taraewZARCTICz>http://festvox.org/cmu_arctic/packed/cmu_us_aew_arctic.tar.bz2Z@645cb33c0f0b2ce41384fdd8d3db2c3f5fc15c1e688baeb74d2e08cab18ab406z>http://festvox.org/cmu_arctic/packed/cmu_us_ahw_arctic.tar.bz2Z@024664adeb892809d646a3efd043625b46b5bfa3e6189b3500b2d0d59dfab06cz>http://festvox.org/cmu_arctic/packed/cmu_us_aup_arctic.tar.bz2Z@2c55bc3050caa996758869126ad10cf42e1441212111db034b3a45189c18b6fcz>http://festvox.org/cmu_arctic/packed/cmu_us_awb_arctic.tar.bz2Z@d74a950c9739a65f7bfc4dfa6187f2730fa03de5b8eb3f2da97a51b74df64d3cz>http://festvox.org/cmu_arctic/packed/cmu_us_axb_arctic.tar.bz2Z@dd65c3d2907d1ee52f86e44f578319159e60f4bf722a9142be01161d84e330ffz>http://festvox.org/cmu_arctic/packed/cmu_us_bdl_arctic.tar.bz2Z@26b91aaf48b2799b2956792b4632c2f926cd0542f402b5452d5adecb60942904z>http://festvox.org/cmu_arctic/packed/cmu_us_clb_arctic.tar.bz2Z@3f16dc3f3b97955ea22623efb33b444341013fc660677b2e170efdcc959fa7c6z>http://festvox.org/cmu_arctic/packed/cmu_us_eey_arctic.tar.bz2Z@8a0ee4e5acbd4b2f61a4fb947c1730ab3adcc9dc50b195981d99391d29928e8az>http://festvox.org/cmu_arctic/packed/cmu_us_fem_arctic.tar.bz2Z@3fcff629412b57233589cdb058f730594a62c4f3a75c20de14afe06621ef45e2z>http://festvox.org/cmu_arctic/packed/cmu_us_gka_arctic.tar.bz2Z@dc82e7967cbd5eddbed33074b0699128dbd4482b41711916d58103707e38c67fz>http://festvox.org/cmu_arctic/packed/cmu_us_jmk_arctic.tar.bz2Z@3a37c0e1dfc91e734fdbc88b562d9e2ebca621772402cdc693bbc9b09b211d73z>http://festvox.org/cmu_arctic/packed/cmu_us_ksp_arctic.tar.bz2Z@8029cafce8296f9bed3022c44ef1e7953332b6bf6943c14b929f468122532717z>http://festvox.org/cmu_arctic/packed/cmu_us_ljm_arctic.tar.bz2Z@b23993765cbf2b9e7bbc3c85b6c56eaf292ac81ee4bb887b638a24d104f921a0z>http://festvox.org/cmu_arctic/packed/cmu_us_lnh_arctic.tar.bz2Z@4faf34d71aa7112813252fb20c5433e2fdd9a9de55a00701ffcbf05f24a5991az>http://festvox.org/cmu_arctic/packed/cmu_us_rms_arctic.tar.bz2Z@c6dc11235629c58441c071a7ba8a2d067903dfefbaabc4056d87da35b72ecda4z>http://festvox.org/cmu_arctic/packed/cmu_us_rxr_arctic.tar.bz2Z@1fa4271c393e5998d200e56c102ff46fcfea169aaa2148ad9e9469616fbfdd9bz>http://festvox.org/cmu_arctic/packed/cmu_us_slp_arctic.tar.bz2Z@54345ed55e45c23d419e9a823eef427f1cc93c83a710735ec667d068c916abf1z>http://festvox.org/cmu_arctic/packed/cmu_us_slt_arctic.tar.bz2Z@7c173297916acf3cc7fcab2713be4c60b27312316765a90934651d367226b4ealinepathfolder_audio	ext_audioreturnc           	      C   sd   | d   dddd  \}}|dd }tj|||| }t|\}}||||dd fS )Nr          _)stripsplitosr   join
torchaudioload)	r
   r   r   r   Zutterance_idZ
transcriptZ
file_audioZwaveformZsample_rate r   l/var/www/html/eduruby.in/lip-sync/lip-sync-env/lib/python3.10/site-packages/torchaudio/datasets/cmuarctic.pyload_cmuarctic_item$   s
    r   c                   @   sz   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dZdedeeeeef fddZdefddZdS )	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.wavZwavFrooturlfolder_in_archivedownloadr   Nc                 C   sX  |dv rd| d }d}d}t j||| }t |}t j|}t j||}t j|s4t | t j||}|dd }t j||| _|rkt j| jsjt j	|sft
|d }	t|||	d t| nt j| js{td	| j d
t j| j| j| j| _t| jd}
tj|
dd}t|| _W d    d S 1 sw   Y  d S )N)r	   ZahwZaupZawbZaxbZbdlZclbZeeyZfemZgkaZjmkZkspZljmZlnhZrmsZrxrZslpZsltZcmu_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 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"   Zext_archivebase_urlr(   archiveZchecksumtextZwalkerr   r   r   __init__I   s:   

"zCMUARCTIC.__init__nc                 C   s   | 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
        )r8   r   r+   _folder_audio
_ext_audio)r9   r>   r
   r   r   r   __getitem__   s   
zCMUARCTIC.__getitem__c                 C   s
   t | jS )N)lenr8   )r9   r   r   r   __len__   s   
zCMUARCTIC.__len__)__name__
__module____qualname____doc__r2   r1   r@   r?   URLFOLDER_IN_ARCHIVEr   strr   boolr=   intr   r   rA   rC   r   r   r   r   r   3   s(    

>r   )r5   r   pathlibr   typingr   r   r   Ztorchr   Ztorch.utils.datar   Ztorchaudio._internalr   Ztorchaudio.datasets.utilsr   rH   rI   r-   rJ   rL   r   r   r   r   r   r   <module>   sd    	
*