U ,:%e1 @sddlZddlmZddlmZmZmZddlmZddl m Z ddl m Z ddl mZmZdZd Zd Zd d d ddddgZddddddddZddZeeeeeeeeeeeeeefdddZGddde ZdS) N)Path)ListTupleUnion)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$http://www.openslr.org/resources/12/z.tar.gz)Z hash_prefix)ospathjoinisfile _CHECKSUMSgetrr )rooturlbase_urlZ ext_archivefilenamearchive download_urlZchecksumrf/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/torchaudio/datasets/librispeech_biasing.py_download_librispeech!s  r)fileidrfolder ext_audioext_txtblistreturnc Cs|pg}|d\}}}|d|d|} tj|||| |} |d||} tj||||| } g} t| f} | D]L}|dd\}}| |kr~|D]}||kr|| kr| |qqq~td| W5QRX| t|t |t |t || fS)N- zTranslation not found for ) splitr r r openstripappendFileNotFoundError SAMPLE_RATEint)rrrrrrZ speaker_idZ chapter_idZ utterance_idZ fileid_audiofilepathZ file_textZuttblistftlineZ fileid_textZ transcriptwordrrr_get_librispeech_metadata.s0   r.c@seZdZdZdZdZeeddfee e fe e e e e ddddZ eeeee eeefd d d Zeeeee eeefd d d ZedddZdS)LibriSpeechBiasinga*LibriSpeech* :cite:`7178964` dataset with prefix-tree construction and biasing support. Args: root (str or Path): Path to the directory where the dataset is found or downloaded. url (str, optional): The URL to download the dataset from, or the type of the dataset to dowload. Allowed type values are ``"dev-clean"``, ``"dev-other"``, ``"test-clean"``, ``"test-other"``, ``"train-clean-100"``, ``"train-clean-360"`` and ``"train-other-500"``. (default: ``"train-clean-100"``) folder_in_archive (str, optional): The top-level directory of the dataset. (default: ``"LibriSpeech"``) download (bool, optional): Whether to download the dataset if it is not found at root path. (default: ``False``). blist (list, optional): The list of biasing words (default: ``[]``). z .trans.txtz.flacFN)rrfolder_in_archivedownloadrrcCs||_|tkr$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 sz.LibriSpeechBiasing.__init__..z*/*/*)_url _DATA_SUBSETS ValueErrorr fspathr r _archive_pathisdirr RuntimeErrorsortedrglob _ext_audio_walkerr)selfrrr0r1rrrr__init__is   &zLibriSpeechBiasing.__init__)nrcCs&|j|}t||j|j|j|j|jS)aGet 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 list: List of biasing words in the utterance )rDr.r=r9rC_ext_txtr)rErGrrrr get_metadatas zLibriSpeechBiasing.get_metadatacCs2||}t|j|d|d}|f|ddS)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 list: List of biasing words in the utterance rr"N)rIr r=)rErGmetadataZwaveformrrr __getitem__s zLibriSpeechBiasing.__getitem__)rcCs t|jSr3)lenrD)rErrr__len__szLibriSpeechBiasing.__len__)__name__ __module__ __qualname____doc__rHrCURLFOLDER_IN_ARCHIVErr4rboolrrFr)rrrIrKrMrrrrr/Ts$    r/)r pathlibrtypingrrrZtorchrZtorch.utils.datarZtorchaudio._internalrZtorchaudio.datasets.utilsr r rRrSr(r:rrr4r)r.r/rrrrsF       &