:jddlZddlmZddlmZmZddlZddlmZddl m Z ddl m Z ddl mZdZd Zd d d d ddddZdedededededeeeeeeeeff dZGdde Zy)N)Path)TupleUnion)Tensor)Dataset)download_url_to_file) _extract_tartrain-clean-100LibriTTS@da0864e1bd26debed35da8a869dd5c04dfc27682921936de7cff9c8a254dbe1a@d413eda26f3a152ac7c9cf3658ef85504dfb1b625296e5fa83727f5186cca79c@234ea5b25859102a87024a4b9b86641f5b5aaaf1197335c95090cde04fe9a4f5@33a5342094f3bba7ccc2e0500b9e72d558f72eb99328ac8debe1d9080402f10d@c5608bf1ef74bb621935382b8399c5cdd51cd3ee47cec51f00f885a64c6c7f6b@ce7cff44dcac46009d18379f37ef36551123a1dc4e5c8e4eb73ae57260de4886@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.gzfileidpath ext_audioext_original_txtext_normalized_txtreturncD|jd\}}}}|}||z} tjj|||| } ||z} tjj|||| } ||z} tjj|||| } t j | \} } t | 5}|j} dddt | d5}|j} ddd| | | | t|t||fS#1swYIxYw#1swY0xYw)N_r) splitosrjoin torchaudioloadopenreadlineint)rrrrr speaker_id chapter_id segment_id utterance_idnormalized_text original_text file_audiowaveform sample_ratefts q/home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/torchaudio/datasets/libritts.pyload_libritts_itemr/s 8>||C7H4J J L"%77Oggll4ZQO #33MGGLLz:}MM )JdJ JGJ'OOJ7Hk m & & os #(r++-(  J J &&((s1D D DDc zeZdZdZdZdZdZeedfde e e fde de d e d d f d Z d ed eeee e eee ffdZd efdZy )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.wavFrooturlfolder_in_archivedownloadrNc|dvr'd}d}tjj|||z}tj|}tjj |}tjj||}|j dd}tjj||}tjj|||_|rxtjj|j stjj|s$tj|d} t||| t|nBtjj|j std|j dtd t!|j j#d |j$zD|_y) N)z dev-cleanz dev-otherz test-cleanz test-otherr ztrain-clean-360ztrain-other-500z.tar.gzz$http://www.openslr.org/resources/60/.r) hash_prefixz The path zT doesn't exist. Please check the ``root`` path or set `download=True` to download itc3FK|]}t|jywN)strstem).0ps r. z$LIBRITTS.__init__..sdac!&&kds!z*/*/*)rrrfspathbasenamer_pathisdirisfile _CHECKSUMSgetrr exists RuntimeErrorsortedrglob _ext_audio_walker) selfr2r3r4r5 ext_archivebase_urlrAarchivechecksums r.__init__zLIBRITTS.__init__Usd   $K=H'',,x{):;Cyy77##C('',,tX.>>#&q)GGLL):HEWW\\$(9: 77==,ww~~g.)~~c48H(g8LW%77>>$**-" |,[[ d4 3C3H3HSWSbSbIb3cdd nc|j|}t||j|j|j|j S)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 )rLr/rBrK_ext_original_txt_ext_normalized_txt)rMrTrs r. __getitem__zLIBRITTS.__getitem__sA0a!  JJ OO  " "  $ $   rSc,t|jSr:)lenrL)rMs r.__len__zLIBRITTS.__len__s4<<  rS)__name__ __module__ __qualname____doc__rVrWrKURLFOLDER_IN_ARCHIVErr;rboolrRr#rrrXr[rSr.r1r1As (+J !2 /eCI/e/e /e  /e  /eb S U63S#sC+O%P B!!rSr1)rpathlibrtypingrrrtorchrtorch.utils.datartorchaudio._internalrtorchaudio.datasets.utilsr r`rarEr;r#r/r1rcrSr.rjs $52<~<~==CECECE & & && &  &  63S#sC /0 &Rg!wg!rS