o
    -i                     @   s   d dl Z d dlmZ d dlmZmZ d dlmZ d dlm	Z	 d dl
mZ d dlmZmZ dZd	Zd
Zg dZddddddddZdd Zdedededededeeeeeeef fddZG dd de	ZdS )     N)Path)TupleUnion)Tensor)Dataset)download_url_to_file)_extract_tar_load_waveformtrain-clean-100LibriSpeechi>  )z	dev-cleanz	dev-otherz
test-cleanz
test-otherr
   ztrain-clean-360ztrain-other-500@76f87d090650617fca0cac8f88b9416e0ebf80350acb97b343a85fa903728ab3@12661c48e8c3fe1de2c1caa4c3e135193bfb1811584f11f569dd12645aa84365@39fde525e59672dc6d1551919b1478f724438a95aa55f874b576be21967e6c23@d09c181bba5cf717b3dee7d4d592af11a3ee3a09e08ae025c5506f6ebe961c29@d4ddd1d5a6ab303066f14971d768ee43278a5f2a0aa43dc716b0e64ecbbbf6e2@146a56496217e96c14334a160df97fffedd6e0a04e66b9c5af0d40be3c792ecf@ddb22f27f96ec163645d53215559df6aa36515f26e01dd70798188350adcb6d2)z4http://www.openslr.org/resources/12/dev-clean.tar.gzz4http://www.openslr.org/resources/12/dev-other.tar.gzz5http://www.openslr.org/resources/12/test-clean.tar.gzz5http://www.openslr.org/resources/12/test-other.tar.gzz:http://www.openslr.org/resources/12/train-clean-100.tar.gzz:http://www.openslr.org/resources/12/train-clean-360.tar.gzz:http://www.openslr.org/resources/12/train-other-500.tar.gzc                 C   s^   d}d}|| }t j| |}t j||}t j|s)t|d }t|||d t| d S )Nz$http://www.openslr.org/resources/12/z.tar.gz)hash_prefix)ospathjoinisfile
_CHECKSUMSgetr   r   )rooturlbase_urlext_archivefilenamearchivedownload_urlchecksum r"   X/home/ubuntu/LTX-2/.venv/lib/python3.10/site-packages/torchaudio/datasets/librispeech.py_download_librispeech!   s   r$   fileidr   folder	ext_audioext_txtreturnc                 C   s   |  d\}}}| d| d| }tj|||| | }	| d| | }
tj|||||
}
t|
$}|D ]}|  dd\}}||krK nq9td| W d    n1 s]w   Y  |	t|t|t|t|fS )N-    zTranslation not found for )	splitr   r   r   openstripFileNotFoundErrorSAMPLE_RATEint)r%   r   r&   r'   r(   
speaker_id
chapter_idutterance_idfileid_audiofilepath	file_textftlinefileid_text
transcriptr"   r"   r#   _get_librispeech_metadata.   s*   

r=   c                   @   s   e 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eef fddZded	eeee	eeef fddZd	efddZd
S )LIBRISPEECHa  *LibriSpeech* :cite:`7178964` 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 dowload.
            Allowed type values are ``"dev-clean"``, ``"dev-other"``, ``"test-clean"``,
            ``"test-other"``, ``"train-clean-100"``, ``"train-clean-360"`` and
            ``"train-other-500"``. (default: ``"train-clean-100"``)
        folder_in_archive (str, optional):
            The top-level directory of the dataset. (default: ``"LibriSpeech"``)
        download (bool, optional):
            Whether to download the dataset if it is not found at root path. (default: ``False``).
    z
.trans.txtz.flacFr   r   folder_in_archivedownloadr)   Nc                 C   s   || _ |tvrtd| dt dt|}tj||| _tj|||| _tj	| js@|r7t
|| n	td| j dtdd t| jd| j D | _d S )	NzInvalid url 'z' given; please provide one of .zDataset not found at z5. Please set `download=True` to download the dataset.c                 s   s    | ]}t |jV  qd S N)strstem).0pr"   r"   r#   	<genexpr>w   s    z'LIBRISPEECH.__init__.<locals>.<genexpr>z*/*/*)_url_DATA_SUBSETS
ValueErrorr   fspathr   r   _archive_pathisdirr$   RuntimeErrorsortedr   glob
_ext_audio_walker)selfr   r   r?   r@   r"   r"   r#   __init__`   s   
*zLIBRISPEECH.__init__nc                 C   s"   | j | }t|| j| j| j| jS )a>  Get metadata for the n-th sample from the dataset. Returns filepath instead of waveform,
        but otherwise returns the same fields as :py:func:`__getitem__`.

        Args:
            n (int): The index of the sample to be loaded

        Returns:
            Tuple of the following items;

            str:
                Path to audio
            int:
                Sample rate
            str:
                Transcript
            int:
                Speaker ID
            int:
                Chapter ID
            int:
                Utterance ID
        )rS   r=   rL   rH   rR   _ext_txt)rT   rV   r%   r"   r"   r#   get_metadatay   s   
zLIBRISPEECH.get_metadatac                 C   s2   |  |}t| j|d |d }|f|dd  S )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
            int:
                Speaker ID
            int:
                Chapter ID
            int:
                Utterance ID
        r   r,   N)rX   r	   rL   )rT   rV   metadatawaveformr"   r"   r#   __getitem__   s   
zLIBRISPEECH.__getitem__c                 C   s
   t | jS rB   )lenrS   )rT   r"   r"   r#   __len__   s   
zLIBRISPEECH.__len__)__name__
__module____qualname____doc__rW   rR   URLFOLDER_IN_ARCHIVEr   rC   r   boolrU   r2   r   rX   r   r[   r]   r"   r"   r"   r#   r>   M   s*    

""r>   )r   pathlibr   typingr   r   torchr   torch.utils.datar   torchaudio._internalr   torchaudio.datasets.utilsr   r	   rb   rc   r1   rI   r   r$   rC   r2   r=   r>   r"   r"   r"   r#   <module>   sD    

