:j9 ddlZddlmZddlmZmZmZddlmZddl m Z ddl m Z ddl mZmZdZd Zd Zd Zd Zd ddZdZdededeeeeeeffdZGdde Zy)N)Path)OptionalTupleUnion)Tensor)Dataset)download_url_to_file) _extract_tar_load_waveformSpeechCommandsspeech_commands_v0.02_nohash__background_noise_i>@743935421bb51cccdb6bdd152e04c5c70274e935c82119ad7faeec31780d811d@af14739ee7dc311471de98f5f9d2c9191b18aedfe957f4a6ff791c709868ff58)z@http://download.tensorflow.org/data/speech_commands_v0.01.tar.gzz@http://download.tensorflow.org/data/speech_commands_v0.02.tar.gzc Zg}|D]}tjj||}t|5}||Dcgc]M}tjj tjj||j Oc}z }ddd|Scc}w#1swYxYwN)ospathjoinopennormpathstrip)root filenamesoutputfilenamefilepathfileobjlines w/home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/torchaudio/datasets/speechcommands.py _load_listr"s F_77<<h/ (^ _w V]^drww'' T4::<(HI^ ^F _ __ M_ _ _sB!AB B!B!!B* rrreturnctjj||}tjj|\}}tjj|\}}tjj |\}}tjj |\}}|jt \}} t | } |t||| fSr)rrrelpathsplitsplitext HASH_DIVIDERint SAMPLE_RATE) rrr%reldirr_labelspeaker speaker_idutterance_numbers r!_get_speechcommands_metadatar1sggooh-Gww}}W-FHww}}V$HAu!!(+JGQ!!'*JGQ#*==#> J +, K 4D DDc eZdZdZeeddfdeeefdedede de ed df d Z d e d e ee eee ffd Zd e d e ee eee ffd Zd e fdZy)SPEECHCOMMANDSa,*Speech Commands* :cite:`speechcommandsv2` dataset. Args: root (str or Path): Path to the directory where the dataset is found or downloaded. url (str, optional): The URL to download the dataset from, or the type of the dataset to dowload. Allowed type values are ``"speech_commands_v0.01"`` and ``"speech_commands_v0.02"`` (default: ``"speech_commands_v0.02"``) folder_in_archive (str, optional): The top-level directory of the dataset. (default: ``"SpeechCommands"``) download (bool, optional): Whether to download the dataset if it is not found at root path. (default: ``False``). subset (str or None, optional): Select a subset of the dataset [None, "training", "validation", "testing"]. None means the whole dataset. "validation" and "testing" are defined in "validation_list.txt" and "testing_list.txt", respectively, and "training" is the rest. Details for the files "validation_list.txt" and "testing_list.txt" are explained in the README of the dataset and in the introduction of Section 7 of the original paper and its reference 12. The original paper can be found `here `_. (Default: ``None``) FNrurlfolder_in_archivedownloadsubsetr#c>||dvr td|dvr'd}d}tjj|||z}tj|}tjj|||_tjj |}tjj||} |jddd}tjj||}tjj|||_|rtjj|jstjj| s$tj|d} t|| | t| |jnBtjj|jst!d |jd |d k(rt#|jd |_y|dk(rt#|jd|_y|dk(rt't#|jd d} t)dt+|jj-dD} | D cgc]5} t.| vr+t0| vr#tjj3| | vr| 7c} |_yt)dt+|jj-dD} | D cgc]} t.| vs t0| vs| c} |_ycc} wcc} w)N)training validationtestingzSWhen `subset` is not None, it must be one of ['training', 'validation', 'testing'].)zspeech_commands_v0.01r z$http://download.tensorflow.org/data/z.tar.gz.r) hash_prefixz The path zT doesn't exist. Please check the ``root`` path or set `download=True` to download itr;zvalidation_list.txtr<ztesting_list.txtr:c32K|]}t|ywrstr.0ps r! z*SPEECHCOMMANDS.__init__..|MqCFMz*/*.wavc32K|]}t|ywrrArCs r!rFz*SPEECHCOMMANDS.__init__..rGrH) ValueErrorrrrfspath_archivebasenamersplit_pathisdirisfile _CHECKSUMSgetr r exists RuntimeErrorr"_walkersetsortedrglobr( EXCEPT_FOLDERr)selfrr5r6r7r8base_url ext_archiverMarchivechecksumexcludeswalkerws r!__init__zSPEECHCOMMANDS.__init__Hs{  &0U"Urs s   >H#K'',,x{):;Cyy T+<= 77##C('',,tX.??3*1-GGLL):HEWW\\$(9: 77==,ww~~g.)~~c48H(g8LWdjj177>>$**-" |,[[ \ !%djj2GHDL y %djj2DEDL z !:djj2GI[\]HMD,<,A,A),LMMF 1$a)?BGGDTDTUVDW_gDgDL MD,<,A,A),LMMF'-^!1B}\]G]A^DL_s6:L1 L?LLncL|j|}t||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 the audio int: Sample rate str: Label str: Speaker ID int: Utterance number )rVr1rL)r[rdfileids r! get_metadatazSPEECHCOMMANDS.get_metadatas"*a+FDMMBBr2cp|j|}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: Label str: Speaker ID int: Utterance number rN)rgr rL)r[rdmetadatawaveforms r! __getitem__zSPEECHCOMMANDS.__getitem__sA($$Q'!$--!hqkJ{Xab\))r2c,t|jSr)lenrV)r[s r!__len__zSPEECHCOMMANDS.__len__s4<<  r2)__name__ __module__ __qualname____doc__URLFOLDER_IN_ARCHIVErrBrboolrrcr)rrgrrlror2r!r4r42s0!2 $ <_CI<_<_ <_  <_  <_ <_|CcCeCc3,C&DC0*S*U63S#+E%F*0!!r2r4)rpathlibrtypingrrrtorchrtorch.utils.datartorchaudio._internalr torchaudio.datasets.utilsr r rurtr(rZr*rRr"rBr)r1r4rwr2r!r~s ))$5B$ $  IKIK E3EcEeCcSVX[D[>\E(E!WE!r2