o siS$@sTddlmZddlZddlZddlZddlZddlZGdddejj j Z e Z dS))PathNc @s\eZdZdZdZgdddddddddd d d f d d ZddZddZddZddZ dS)MUSDB18Dataseta MUSDB18 music separation dataset The dataset consists of 150 full lengths music tracks (~10h duration) of different genres along with their isolated stems: `drums`, `bass`, `vocals` and `others`. Out-of-the-box, asteroid does only support MUSDB18-HQ which comes as uncompressed WAV files. To use the MUSDB18, please convert it to WAV first: - MUSDB18 HQ: https://zenodo.org/record/3338373 - MUSDB18 https://zenodo.org/record/1117372 .. note:: The datasets are hosted on Zenodo and require that users request access, since the tracks can only be used for academic purposes. We manually check this requests. This dataset asssumes music tracks in (sub)folders where each folder has a fixed number of sources (defaults to 4). For each track, a list of `sources` and a common `suffix` can be specified. A linear mix is performed on the fly by summing up the sources Due to the fact that all tracks comprise the exact same set of sources, random track mixing can be used can be used, where sources from different tracks are mixed together. Folder Structure: >>> #train/1/vocals.wav ---------| >>> #train/1/drums.wav ----------+--> input (mix), output[target] >>> #train/1/bass.wav -----------| >>> #train/1/other.wav ---------/ Args: root (str): Root path of dataset sources (:obj:`list` of :obj:`str`, optional): List of source names that composes the mixture. Defaults to MUSDB18 4 stem scenario: `vocals`, `drums`, `bass`, `other`. targets (list or None, optional): List of source names to be used as targets. If None, a dict with the 4 stems is returned. If e.g [`vocals`, `drums`], a tensor with stacked `vocals` and `drums` is returned instead of a dict. Defaults to None. suffix (str, optional): Filename suffix, defaults to `.wav`. split (str, optional): Dataset subfolder, defaults to `train`. subset (:obj:`list` of :obj:`str`, optional): Selects a specific of list of tracks to be loaded, defaults to `None` (loads all tracks). segment (float, optional): Duration of segments in seconds, defaults to ``None`` which loads the full-length audio tracks. samples_per_track (int, optional): Number of samples yielded from each track, can be used to increase dataset size, defaults to `1`. random_segments (boolean, optional): Enables random offset for track segments. random_track_mix boolean: enables mixing of random sources from different tracks to assemble mix. source_augmentations (:obj:`list` of :obj:`callable`): list of augmentation function names, defaults to no-op augmentations (input = output) sample_rate (int, optional): Samplerate of files in dataset. Attributes: root (str): Root path of dataset sources (:obj:`list` of :obj:`str`, optional): List of source names. Defaults to MUSDB18 4 stem scenario: `vocals`, `drums`, `bass`, `other`. suffix (str, optional): Filename suffix, defaults to `.wav`. split (str, optional): Dataset subfolder, defaults to `train`. subset (:obj:`list` of :obj:`str`, optional): Selects a specific of list of tracks to be loaded, defaults to `None` (loads all tracks). segment (float, optional): Duration of segments in seconds, defaults to ``None`` which loads the full-length audio tracks. samples_per_track (int, optional): Number of samples yielded from each track, can be used to increase dataset size, defaults to `1`. random_segments (boolean, optional): Enables random offset for track segments. random_track_mix boolean: enables mixing of random sources from different tracks to assemble mix. source_augmentations (:obj:`list` of :obj:`callable`): list of augmentation function names, defaults to no-op augmentations (input = output) sample_rate (int, optional): Samplerate of files in dataset. tracks (:obj:`list` of :obj:`Dict`): List of track metadata References "The 2018 Signal Separation Evaluation Campaign" Stoter et al. 2018. MUSDB18)vocalsbassdrumsotherNz.wavtrainFcCs|SN)audior r Q/home/ubuntu/.local/lib/python3.10/site-packages/asteroid/data/musdb18_dataset.pyjszMUSDB18Dataset.iDc Cspt||_||_| |_||_| |_| |_| |_||_ ||_ ||_ ||_ ||_ t||_|js6tddS)NzNo tracks found.)r expanduserrootsplit sample_ratesegmentrandom_track_mixrandom_segmentssource_augmentationssourcestargetssuffixsubsetsamples_per_tracklist get_trackstracks RuntimeError) selfrrrrrrrrrrrrr r r__init__^s zMUSDB18Dataset.__init__c sFi}|j}jrtdj|dj}nd}jD]a}jr>tt t j}jr>tdj|dj}t |j }jrS|t jj }nd}t jtj|d|jd||d\}} tj|jtjd}|}|||<qtt|d} jrtjfdd|Ddd }| |fS) Nr min_durationpathT) always_2dstartstop)dtypecsg|] \}}|jvr|qSr )r).0srcwavr!r r sz.MUSDB18Dataset.__getitem__..)dim)rrrandomuniformrrrrchoicerangelenintrsfreadr with_suffixrtorchtensorTfloatrstackrvaluessumritems) r!index audio_sourcestrack_idr&source start_sample stop_sampler _ audio_mixr r,r __getitem__~s:     zMUSDB18Dataset.__getitem__cCst|j|jSr )r3rrr,r r r__len__szMUSDB18Dataset.__len__c#stjj}t|D]crrjrjjvrqfddjD}t dd|Ds9t dqt t t j|}t fdd|DsRt dqjdurltd d|D}|jkrk|d Vqdd VqdS) zLoads input and output trackscsg|] }|jqSr )r)r)sr! track_pathr rr-sz-MUSDB18Dataset.get_tracks..css|]}|VqdSr )exists)r)spr r r sz,MUSDB18Dataset.get_tracks..z(Exclude track due to non-existing sourcec3s|] }|jjkVqdSr ) sampleraterr)ir,r rrOsz+Exclude track due to different sample rate Ncss|]}|jVqdSr )durationrQr r rrOs)r$r#)rrrtqdmiterdiris_dirrstemrallprintrmapr5informin)r!p source_pathsinfosr#r rKrrs,      zMUSDB18Dataset.get_trackscCs&t}|j|d<d|d<tg|d<|S)zGet dataset infos (for publishing models). Returns: dict, dataset infos with keys `dataset`, `task` and `licences`. dataset enhancementtasklicenses)dict dataset_name musdb_license)r!r_r r r get_infoss   zMUSDB18Dataset.get_infos) __name__ __module__ __qualname____doc__rer"rHrIrrgr r r rr s&R  3 r)pathlibrtorch.utils.datar8r/rT soundfiler5utilsdataDatasetrrdrfr r r rs  U