@jRddlZddlmZddlmZmZddlmZddlm Z ddl m Z ddl m Z mZdZd Zd Zgd Zd d ddddddZdZdedededededeeeeeeeff dZGdde ZdS)N)Path)TupleUnion)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$http://www.openslr.org/resources/12/z.tar.gz) hash_prefix)ospathjoinisfile _CHECKSUMSgetrr )rooturlbase_url ext_archivefilenamearchive download_urlchecksums PC:\Projects\Historical\venv\Lib\site-packages\torchaudio/datasets/librispeech.py_download_librispeechr%!s5HK[ Hgll4**G7<<(33L 7>>' " "J>>,55\7IIIIfileidrfolder ext_audioext_txtreturnc8|d\}}}|d|d|}tj|||||} |d||} tj||||| } t | 5} | D]5} | dd\} }|| krn6t d| dddn #1swxYwY| t|t|t|t|fS)N- zTranslation not found for ) splitrrropenstripFileNotFoundError SAMPLE_RATEint)r'rr(r)r* speaker_id chapter_id utterance_id fileid_audiofilepath file_textftline fileid_text transcripts r$_get_librispeech_metadatar@.s,2<<+<+<(J L!>>:>> >>Lw||FJ |K|]}t|jVdSN)strstem).0ps r$ z'LIBRISPEECH.__init__..ws*ddac!&kkddddddr&z*/*/*)_url _DATA_SUBSETS ValueErrorrfspathrr_archive_pathisdirr% RuntimeErrorsortedrglob _ext_audio_walker)selfrrrCrDs r$__init__zLIBRISPEECH.__init__`s m # #aSaaQ^aaabb by T+<== W\\$(93?? w}}TZ((  %dC0000"mDJmmmdd4 3C3C3H3HSWSbIb3c3cddddd r&ncj|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 )rYr@rRrNrX_ext_txt)rZr\r's r$ get_metadatazLIBRISPEECH.get_metadatays/.a( 4?\`\ijjjr&c||}t|j|d|d}|f|ddzS)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)r_r rR)rZr\metadatawaveforms r$ __getitem__zLIBRISPEECH.__getitem__sG,$$Q''!$-!hqkJJ{Xabb\))r&c*t|jSrH)lenrY)rZs r$__len__zLIBRISPEECH.__len__s4<   r&)__name__ __module__ __qualname____doc__r^rXURLFOLDER_IN_ARCHIVErrIrboolr[r5rr_rrcrfr&r$rBrBMs  HJ !2 eeCIee e  e  eeee2kckeCc3S,H&Ikkkk4*S*U63S#s+J%K****4!!!!!!!r&rB)rpathlibrtypingrrtorchrtorch.utils.datartorchaudio._internalrtorchaudio.datasets.utilsr r rkrlr4rOrr%rIr5r@rBrnr&r$rusz $$$$$$555555BBBBBBBB!  =<~==CECECE     $'47BE 3S#sC '(>a!a!a!a!a!'a!a!a!a!a!r&