@jddlZddlmZddlmZmZmZddlmZddl m Z ddl m Z ddl mZmZdZd Zd Zgd Zd d ddddddZdZdedededededeedeeeeeeeffdZGdde ZdS)N)Path)ListTupleUnion)Tensor)Dataset)download_url_to_file) _extract_tar_load_waveformtrain-clean-100 LibriSpeechi>)z dev-cleanz dev-otherz test-cleanz test-otherr ztrain-clean-360ztrain-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.gzcNd}d}||z}tj||}tj||}tj|s-t|d}t |||t|dS)Nz$http://www.openslr.org/resources/12/z.tar.gz) hash_prefix)ospathjoinisfile _CHECKSUMSgetr r )rooturlbase_url ext_archivefilenamearchive download_urlchecksums XC:\Projects\Historical\venv\Lib\site-packages\torchaudio/datasets/librispeech_biasing.py_download_librispeechr&!s5HK[ Hgll4**G7<<(33L 7>>' " "J>>,55\7IIIIfileidrfolder ext_audioext_txtblistreturnc|pg}|d\}}}|d|d|} tj|||| |} |d||} tj||||| } g} t | 5} | D]i}|dd\}}| |kr6|D]}||vr|| vr| | njtd|  dddn #1swxYwY| t|t|t|t|| fS)N- zTranslation not found for ) splitrrropenstripappendFileNotFoundError SAMPLE_RATEint)r(rr)r*r+r, speaker_id chapter_id utterance_id fileid_audiofilepath file_textuttblistftline fileid_text transcriptwords r%_get_librispeech_metadatarE.s KRE+1<<+<+<(J L!>>:>> >>Lw||FJ |K|]}t|jVdSN)strstem).0ps r% z.LibriSpeechBiasing.__init__..s*ddac!&kkddddddr'z*/*/*)_url _DATA_SUBSETS ValueErrorrfspathrr_archive_pathisdirr& RuntimeErrorsortedrglob _ext_audio_walkerr,)selfrrrHrIr,s r%__init__zLibriSpeechBiasing.__init__is m # #aSaaQ^aaabb by T+<== W\\$(93?? w}}TZ((  %dC0000"mDJmmmdd4 3C3C3H3HSWSbIb3c3cddddd  r'ncv|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 )r^rErWrSr]_ext_txtr,)r_rar(s r% get_metadatazLibriSpeechBiasing.get_metadatas52a( 4?\`\ikokuvvvr'c||}t|j|d|d}|f|ddzS)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 rr1N)rdr rW)r_rametadatawaveforms r% __getitem__zLibriSpeechBiasing.__getitem__sG0$$Q''!$-!hqkJJ{Xabb\))r'c*t|jSrM)lenr^)r_s r%__len__zLibriSpeechBiasing.__len__s4<   r')__name__ __module__ __qualname____doc__rcr]URLFOLDER_IN_ARCHIVErrNrboolrr`r8rrdrrhrkr'r%rGrGTs!"HJ !2 CI    Cy  6wcweCc3S,H&Iwwww8*S*U63S#s+J%K****8!!!!!!!r'rG)rpathlibrtypingrrrtorchrtorch.utils.datartorchaudio._internalr torchaudio.datasets.utilsr r rprqr7rTrr&rNr8rErGrsr'r%rzs %%%%%%%%%%$$$$$$555555BBBBBBBB!  =<~==CECECE    # ##$'#47#BE#NRSVi# 3S#sC '(####Li!i!i!i!i!i!i!i!i!i!r'