U ,:%e @sddlZddlmZddlmZmZddlmZddlm Z ddl m Z ddl m Z mZdZd Zd Zd d d ddddgZddddddddZddZeeeeeeeeeeeefdddZGddde ZdS) N)Path)TupleUnion)Tensor)Dataset)download_url_to_file) _extract_tar_load_waveformztrain-clean-100Z LibriSpeechi>z dev-cleanz dev-otherz test-cleanz test-otherztrain-clean-360ztrain-other-500Z@76f87d090650617fca0cac8f88b9416e0ebf80350acb97b343a85fa903728ab3Z@12661c48e8c3fe1de2c1caa4c3e135193bfb1811584f11f569dd12645aa84365Z@39fde525e59672dc6d1551919b1478f724438a95aa55f874b576be21967e6c23Z@d09c181bba5cf717b3dee7d4d592af11a3ee3a09e08ae025c5506f6ebe961c29Z@d4ddd1d5a6ab303066f14971d768ee43278a5f2a0aa43dc716b0e64ecbbbf6e2Z@146a56496217e96c14334a160df97fffedd6e0a04e66b9c5af0d40be3c792ecfZ@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.gzcCs^d}d}||}tj||}tj||}tj|sRt|d}t|||dt|dS)Nz$http://www.openslr.org/resources/12/z.tar.gz)Z hash_prefix)ospathjoinisfile _CHECKSUMSgetrr)rooturlbase_urlZ ext_archivefilenamearchive download_urlZchecksumr^/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/torchaudio/datasets/librispeech.py_download_librispeech!s  r)fileidrfolder ext_audioext_txtreturnc Cs|d\}}}|d|d|}tj|||||} |d||} tj||||| } t| >} | D]$} | dd\} }|| krrqqrtd|W5QRX| t|t|t|t|fS)N- zTranslation not found for ) splitr r r openstripFileNotFoundError SAMPLE_RATEint)rrrrrZ speaker_idZ chapter_idZ utterance_idZ fileid_audiofilepathZ file_textftlineZ fileid_textZ transcriptrrr_get_librispeech_metadata.s$ r*c@seZdZdZdZdZeedfee e fe e e ddddZ e eee e e e e fd d d Ze eee e e e e fd d d Ze dddZdS) 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.flacFN)rrfolder_in_archivedownloadrcCs||_|tkr$td|dtdt|}tj|||_tj||||_tj |js|rnt ||nt d|jdt ddt |jd|jD|_dS) Nz Invalid url 'z' given; please provide one of .zDataset not found at z5. Please set `download=True` to download the dataset.css|]}t|jVqdSN)strstem).0prrr wsz'LIBRISPEECH.__init__..z*/*/*)_url _DATA_SUBSETS ValueErrorr fspathr r _archive_pathisdirr RuntimeErrorsortedrglob _ext_audio_walker)selfrrr,r-rrr__init__`s   zLIBRISPEECH.__init__)nrcCs"|j|}t||j|j|j|jS)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 )r@r*r9r5r?_ext_txt)rArCrrrr get_metadatays zLIBRISPEECH.get_metadatacCs2||}t|j|d|d}|f|ddS)aLoad 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 rr N)rEr r9)rArCmetadataZwaveformrrr __getitem__s zLIBRISPEECH.__getitem__)rcCs t|jSr/)lenr@)rArrr__len__szLIBRISPEECH.__len__)__name__ __module__ __qualname____doc__rDr?URLFOLDER_IN_ARCHIVErr0rboolrBr&rrrErGrIrrrrr+Ms     r+)r pathlibrtypingrrZtorchrZtorch.utils.datarZtorchaudio._internalrZtorchaudio.datasets.utilsrr rNrOr%r6rrr0r&r*r+rrrrsD