U ,:%e @sddlZddlmZddlmZmZddlZddlmZddl m Z ddl m Z ddl mZdZd Zd d d d ddddZeeeeeeeeeeeeefdddZGddde ZdS)N)Path)TupleUnion)Tensor)Dataset)download_url_to_file) _extract_tartrain-clean-100ZLibriTTSZ@da0864e1bd26debed35da8a869dd5c04dfc27682921936de7cff9c8a254dbe1aZ@d413eda26f3a152ac7c9cf3658ef85504dfb1b625296e5fa83727f5186cca79cZ@234ea5b25859102a87024a4b9b86641f5b5aaaf1197335c95090cde04fe9a4f5Z@33a5342094f3bba7ccc2e0500b9e72d558f72eb99328ac8debe1d9080402f10dZ@c5608bf1ef74bb621935382b8399c5cdd51cd3ee47cec51f00f885a64c6c7f6bZ@ce7cff44dcac46009d18379f37ef36551123a1dc4e5c8e4eb73ae57260de4886Z@e35f7e34deeb2e2bdfe4403d88c8fdd5fbf64865cae41f027a185a6965f0a5df)z4http://www.openslr.org/resources/60/dev-clean.tar.gzz4http://www.openslr.org/resources/60/dev-other.tar.gzz5http://www.openslr.org/resources/60/test-clean.tar.gzz5http://www.openslr.org/resources/60/test-other.tar.gzz:http://www.openslr.org/resources/60/train-clean-100.tar.gzz:http://www.openslr.org/resources/60/train-clean-360.tar.gzz:http://www.openslr.org/resources/60/train-other-500.tar.gz)fileidpath ext_audioext_original_txtext_normalized_txtreturnc Cs|d\}}}}|}||} tj|||| } ||} tj|||| } ||} tj|||| } t| \} } t| }|} W5QRXt| d}|} W5QRX| | | | t|t||fS)N_r) splitosr join torchaudioloadopenreadlineint)r r r r rZ speaker_idZ chapter_idZ segment_idZ utterance_idZnormalized_textZ original_textZ file_audioZwaveformZ sample_rateftr[/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/torchaudio/datasets/libritts.pyload_libritts_items*  rc @sreZdZdZdZdZdZeedfe e e fe e e dddd Z eeeee e eee fd d d Zed ddZdS)LIBRITTSa*LibriTTS* :cite:`Zen2019LibriTTSAC` 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: ``"LibriTTS"``) download (bool, optional): Whether to download the dataset if it is not found at root path. (default: ``False``). z .original.txtz.normalized.txtz.wavFN)rooturlfolder_in_archivedownloadrc Cs|dkr"d}d}tj|||}t|}tj|}tj||}|dd}tj||}tj|||_|rtj|jstj|st |d} t ||| dt |n tj |jstd|jdtd d t|jd |jD|_dS) N)z dev-cleanz dev-otherz test-cleanz test-otherr ztrain-clean-360ztrain-other-500z.tar.gzz$http://www.openslr.org/resources/60/.r)Z hash_prefixz The path zT doesn't exist. Please check the ``root`` path or set `download=True` to download itcss|]}t|jVqdSN)strstem).0prrr sz$LIBRITTS.__init__..z*/*/*)rr rfspathbasenamer_pathisdirisfile _CHECKSUMSgetrrexists RuntimeErrorsortedrglob _ext_audio_walker) selfrr r!r"Z ext_archivebase_urlr+archiveZchecksumrrr__init__Us*       zLIBRITTS.__init__)nrcCs"|j|}t||j|j|j|jS)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: Original text str: Normalized text int: Speaker ID int: Chapter ID str: Utterance ID )r6rr,r5_ext_original_txt_ext_normalized_txt)r7r;r rrr __getitem__s zLIBRITTS.__getitem__)rcCs t|jSr$)lenr6)r7rrr__len__szLIBRITTS.__len__)__name__ __module__ __qualname____doc__r<r=r5URLFOLDER_IN_ARCHIVErr%rboolr:rrrr>r@rrrrrAs   1"!r)rpathlibrtypingrrrZtorchrZtorch.utils.datarZtorchaudio._internalrZtorchaudio.datasets.utilsrrErFr/r%rrrrrrrs2       )