How to use the mirdata.utils.LargeData function in mirdata

To help you get started, we’ve selected a few mirdata examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github mir-dataset-loaders / mirdata / mirdata / medleydb_pitch.py View on Github external
def _load_metadata(data_home):
    metadata_path = os.path.join(data_home, 'medleydb_pitch_metadata.json')

    if not os.path.exists(metadata_path):
        logging.info('Metadata file {} not found.'.format(metadata_path))
        return None

    with open(metadata_path, 'r') as fhandle:
        metadata = json.load(fhandle)

    metadata['data_home'] = data_home
    return metadata


DATA = utils.LargeData('medleydb_pitch_index.json', _load_metadata)


class Track(track.Track):
    """medleydb_pitch Track class

    Args:
        track_id (str): track id of the track
        data_home (str): Local path where the dataset is stored. default=None
            If `None`, looks for the data in the default directory, `~/mir_datasets`

    Attributes:
        artist (str): artist
        audio_path (str): path to the audio file
        genre (str): genre
        instrument (str): instrument of the track
        pitch_path (str): path to the pitch annotation file
github mir-dataset-loaders / mirdata / mirdata / orchset.py View on Github external
'contains_strings': tf_dict[line[4]],
            'contains_brass': tf_dict[line[5]],
            'only_strings': tf_dict[line[6]],
            'only_winds': tf_dict[line[7]],
            'only_brass': tf_dict[line[8]],
            'composer': id_split[0],
            'work': '-'.join(id_split[1:-1]),
            'excerpt': id_split[-1][2:],
        }

    metadata_index['data_home'] = data_home

    return metadata_index


DATA = utils.LargeData('orchset_index.json', _load_metadata)


class Track(track.Track):
    """orchset Track class

    Args:
        track_id (str): track id of the track
        data_home (str): Local path where the dataset is stored. default=None
            If `None`, looks for the data in the default directory, `~/mir_datasets`

    Attributes:
        alternating_melody (bool): True if the melody alternates between instruments
        audio_path_mono (str): path to the mono audio file
        audio_path_stereo (str): path to the stereo audio file
        composer (str): the work's composer
        contains_brass (bool): True if the track contains any brass instrument
github mir-dataset-loaders / mirdata / mirdata / dali.py View on Github external
DATASET_DIR = 'DALI'


def _load_metadata(data_home):
    metadata_path = os.path.join(data_home, os.path.join('dali_metadata.json'))
    if not os.path.exists(metadata_path):
        logging.info('Metadata file {} not found.'.format(metadata_path))
        return None
    with open(metadata_path, 'r') as fhandle:
        metadata_index = json.load(fhandle)

    metadata_index['data_home'] = data_home
    return metadata_index


DATA = utils.LargeData('dali_index.json', _load_metadata)


class Track(track.Track):
    """DALI melody Track class

    Args:
        track_id (str): track id of the track
        data_home (str): Local path where the dataset is stored.
            If `None`, looks for the data in the default directory, `~/mir_datasets`

    Attributes:
        album (str): the track's album
        annotation_path (str): path to the track's annotation file
        artist (str): the track's artist
        audio_path (str): path to the track's audio file
        audio_url (str): youtube ID
github mir-dataset-loaders / mirdata / mirdata / guitarset.py View on Github external
)
AUDIO_MIX_REMOTE = download_utils.RemoteFileMetadata(
    filename='audio_mono-pickup_mix.zip',
    url='https://zenodo.org/record/3371780/files/audio_mono-pickup_mix.zip?download=1',
    checksum='aecce79f425a44e2055e46f680e10f6a',
    destination_dir='audio_mono-pickup_mix',
)
_STYLE_DICT = {
    'Jazz': 'Jazz',
    'BN': 'Bossa Nova',
    'Rock': 'Rock',
    'SS': 'Singer-Songwriter',
    'Funk': 'Funk',
}
_GUITAR_STRINGS = ['E', 'A', 'D', 'G', 'B', 'e']
DATA = utils.LargeData('guitarset_index.json')


class Track(track.Track):
    """guitarset Track class

    Args:
        track_id (str): track id of the track
        data_home (str): Local path where the dataset is stored. default=None
            If `None`, looks for the data in the default directory, `~/mir_datasets`

    Attributes:
        audio_hex_cln_path (str): path to the debleeded hex wave file
        audio_hex_path (str): path to the original hex wave file
        audio_mic_path (str): path to the mono wave via microphone
        audio_mix_path (str): path to the mono wave via downmixing hex pickup
        jams_path (str): path to the jams file
github mir-dataset-loaders / mirdata / mirdata / rwc_jazz.py View on Github external
'piece_number': line[0],
            'suffix': line[1],
            'track_number': line[2],
            'title': line[3],
            'artist': line[4],
            'duration': _duration_to_sec(line[5]),
            'variation': line[6],
            'instruments': line[7],
        }

    metadata_index['data_home'] = data_home

    return metadata_index


DATA = utils.LargeData('rwc_jazz_index.json', _load_metadata)


class Track(track.Track):
    """rwc_jazz Track class

    Args:
        track_id (str): track id of the track
        data_home (str): Local path where the dataset is stored. default=None
            If `None`, looks for the data in the default directory, `~/mir_datasets`

    Attributes:
        artist (str): Artist name
        audio_path (str): path of the audio file
        beats_path (str): path of the beat annotation file
        duration (float): Duration of the track in seconds
        instruments (str): list of used instruments.
github mir-dataset-loaders / mirdata / mirdata / ikala.py View on Github external
return None

    with open(id_map_path, 'r') as fhandle:
        reader = csv.reader(fhandle, delimiter='\t')
        singer_map = {}
        for line in reader:
            if line[0] == 'singer':
                continue
            singer_map[line[1]] = line[0]

    singer_map['data_home'] = data_home

    return singer_map


DATA = utils.LargeData('ikala_index.json', _load_metadata)


class Track(track.Track):
    """ikala Track class

    Args:
        track_id (str): track id of the track
        data_home (str): Local path where the dataset is stored. default=None
            If `None`, looks for the data in the default directory, `~/mir_datasets`

    Attributes:
        audio_path (str): path to the track's audio file
        f0_path (str): path to the track's f0 annotation file
        lyrics_path (str): path to the track's lyric annotation file
        section (str): section. Either 'verse' or 'chorus'
        singer_id (str): singer id
github mir-dataset-loaders / mirdata / mirdata / beatles.py View on Github external
import os

from mirdata import download_utils
from mirdata import jams_utils
from mirdata import track
from mirdata import utils

DATASET_DIR = 'Beatles'
ANNOTATIONS_REMOTE = download_utils.RemoteFileMetadata(
    filename='The Beatles Annotations.tar.gz',
    url='http://isophonics.net/files/annotations/The%20Beatles%20Annotations.tar.gz',
    checksum='62425c552d37c6bb655a78e4603828cc',
    destination_dir='annotations',
)

DATA = utils.LargeData('beatles_index.json')


class Track(track.Track):
    """Beatles track class

    Args:
        track_id (str): track id of the track
        data_home (str): Local path where the dataset is stored.
            If `None`, looks for the data in the default directory, `~/mir_datasets`

    Attributes:
        audio_path (str): track audio path
        beats_path (str): beat annotation path
        chords_path (str): chord annotation path
        keys_path (str): key annotation path
        sections_path (str): sections annotation path
github mir-dataset-loaders / mirdata / mirdata / groove_midi.py View on Github external
'style': str(style),
                'tempo': int(bpm),
                'beat_type': str(beat_type),
                'time_signature': str(time_signature),
                'midi_filename': str(midi_filename),
                'audio_filename': str(audio_filename),
                'duration': float(duration),
                'split': str(split),
            }

    metadata_index['data_home'] = data_home

    return metadata_index


DATA = utils.LargeData('groove_midi_index.json', _load_metadata)


class Track(track.Track):
    """Groove MIDI Track class

    Args:
        track_id (str): track id of the track
        data_home (str): Local path where the dataset is stored. default=None
            If `None`, looks for the data in the default directory, `~/mir_datasets`

    Attributes:
        drummer (str): Drummer id of the track (ex. 'drummer1')
        session (str): Type of session  (ex. 'session1', 'eval_session')
        track_id (str): track id of the track (ex. 'drummer1/eval_session/1')
        style (str): Style (genre, groove type) of the track (ex. 'funk/groove1')
        tempo (int): Track tempo in beats per minute (ex. 138)