a h9@sddlZddlmZddlmZmZmZddlmZddl m Z ddl m Z ddl mZmZdZd Zd Zd Zd Zd ddZddZeeeeeeeefdddZGddde ZdS)N)Path)OptionalTupleUnion)Tensor)Dataset)download_url_to_file) _extract_tar_load_waveformZSpeechCommandsspeech_commands_v0.02Z_nohash_Z_background_noise_i>Z@743935421bb51cccdb6bdd152e04c5c70274e935c82119ad7faeec31780d811dZ@af14739ee7dc311471de98f5f9d2c9191b18aedfe957f4a6ff791c709868ff58)z@http://download.tensorflow.org/data/speech_commands_v0.01.tar.gzz@http://download.tensorflow.org/data/speech_commands_v0.02.tar.gzc s^g}|D]P}tj|}t|&}|fdd|D7}Wdq1sN0Yq|S)Nc s&g|]}tjtj|qS)ospathnormpathjoinstrip).0linerootr P/var/www/auris/lib/python3.9/site-packages/torchaudio/datasets/speechcommands.py z_load_list..)r rropen)r filenamesoutputfilenamefilepathfileobjr rr _load_lists  6r)rrreturnc Csrtj||}tj|\}}tj|\}}tj|\}}tj|\}}|t\}} t| } |t||| fSN)r rrelpathsplitsplitext HASH_DIVIDERint SAMPLE_RATE) rrr"Zreldirr_labelZspeakerZ speaker_idZutterance_numberr r r_get_speechcommands_metadatasr*c@seZdZdZeeddfeeefeee e eddddZ e e ee eee fddd Ze e ee eee fdd d Ze d d dZdS)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``) FN)rurlfolder_in_archivedownloadsubsetr c s|dur|dvrtd|dvr:d}d}tj|||}t|}tj|||_tj|}tj||} |ddd}tj||}tj|||_|rtj |jstj | st |d} t || | d t| |jn"tj|jstd |jd |d krt|jd |_n|dkr8t|jd|_n~|dkrtt|jd dtddt|jdD} fdd| D|_n.tddt|jdD} dd| D|_dS)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)Z hash_prefixz The path zT doesn't exist. Please check the ``root`` path or set `download=True` to download itr1zvalidation_list.txtr2ztesting_list.txtr0css|]}t|VqdSr!strrpr r r |rz*SPEECHCOMMANDS.__init__..z*/*.wavcs0g|](}t|vrt|vrtj|vr|qSr )r% EXCEPT_FOLDERr rrrwexcludesr rr}s z+SPEECHCOMMANDS.__init__..css|]}t|VqdSr!r5r7r r rr9rcSs g|]}t|vrt|vr|qSr )r%r:r;r r rrr) ValueErrorr rrfspath_archivebasenamersplit_pathisdirisfile _CHECKSUMSgetrr exists RuntimeErrorr_walkersetsortedrglob) selfrr,r-r.r/base_urlZ ext_archiverBarchiveZchecksumwalkerr r=r__init__HsF           zSPEECHCOMMANDS.__init__)nr cCs|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 )rKr*rA)rOrTZfileidr r r get_metadatas zSPEECHCOMMANDS.get_metadatacCs2||}t|j|d|d}|f|ddS)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)rUr rA)rOrTmetadataZwaveformr r r __getitem__s zSPEECHCOMMANDS.__getitem__)r cCs t|jSr!)lenrK)rOr r r__len__szSPEECHCOMMANDS.__len__)__name__ __module__ __qualname____doc__URLFOLDER_IN_ARCHIVErr6rboolrrSr&rrUrrXrZr r r rr+2s   >r+)r pathlibrtypingrrrZtorchrZtorch.utils.datarZtorchaudio._internalrZtorchaudio.datasets.utilsr r r`r_r%r:r'rGrr6r&r*r+r r r rs"