o 7vi9 @sddlZddlmZddlmZmZmZddlmZddl m Z ddl m Z ddl mZmZdZd Zd Zd Zd Zd ddZddZdededeeeeeeffddZGddde ZdS)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 s^g}|D](}tj|}t|}|fdd|D7}Wdn1s'wYq|S)Nc s&g|]}tjtj|qS)ospathnormpathjoinstrip).0linerootr_/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchaudio/datasets/speechcommands.py s&z_load_list..)rrropen)r filenamesoutputfilenamefilepathfileobjrrr _load_lists r#r!rreturnc Csrtj||}tj|\}}tj|\}}tj|\}}tj|\}}|t\}} t| } |t||| fSN)rrrelpathsplitsplitext HASH_DIVIDERint SAMPLE_RATE) r!rr&reldirr _labelspeaker speaker_idutterance_numberrrr_get_speechcommands_metadatasr2c @seZdZdZeeddfdeeefdedede de ed df d d Z d e d e ee eee ffd dZd e d e ee eee ffddZd e fddZdS)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$c s|dur |dvr td|dvrd}d}tj|||}t|}tj|||_tj|}tj||} |ddd}tj||}tj|||_|rqtj |jsptj | sjt |d} t || | d t| |jntj|jstd |jd |d krt|jd |_dS|dkrt|jd|_dS|dkrtt|jd dtddt|jdD} fdd| D|_dStddt|jdD} dd| D|_dS)N)training validationtestingzSWhen `subset` is not None, it must be one of ['training', 'validation', 'testing'].)zspeech_commands_v0.01r z$http://download.tensorflow.org/data/z.tar.gz.r) hash_prefixz The path zT doesn't exist. Please check the ``root`` path or set `download=True` to download itr9zvalidation_list.txtr:ztesting_list.txtr8cs|]}t|VqdSr%strrprrr |z*SPEECHCOMMANDS.__init__..z*/*.wavcs0g|]}t|vrt|vrtj|vr|qSr)r) EXCEPT_FOLDERrrrrwexcludesrrr}s  z+SPEECHCOMMANDS.__init__..csr>r%r?rArrrrCrDcSs g|] }t|vrt|vr|qSr)r)rErFrrrrs ) ValueErrorrrrfspath_archivebasenamersplit_pathisdirisfile _CHECKSUMSgetrr exists RuntimeErrorr#_walkersetsortedrglob) selfrr4r5r6r7base_url ext_archiverMarchivechecksumwalkerrrHr__init__HsH         zSPEECHCOMMANDS.__init__ncCs|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 )rVr2rL)rZrafileidrrr 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)rcr rL)rZrametadatawaveformrrr __getitem__s zSPEECHCOMMANDS.__getitem__cCs t|jSr%)lenrV)rZrrr__len__s zSPEECHCOMMANDS.__len__)__name__ __module__ __qualname____doc__URLFOLDER_IN_ARCHIVErr@rboolrr`r*rrcrrgrirrrrr32s,  > r3)rpathlibrtypingrrrtorchrtorch.utils.datartorchaudio._internalrtorchaudio.datasets.utilsr r rornr)rEr+rRr#r@r*r2r3rrrrs$    $