How to use the mirdata.download_utils 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 / rwc_popular.py View on Github external
from mirdata import download_utils
from mirdata import jams_utils
from mirdata import track
from mirdata import utils

# these functions are identical for all rwc datasets
from mirdata.rwc_classical import (
    load_beats,
    load_sections,
    load_audio,
    _duration_to_sec,
)

REMOTES = {
    'metadata': download_utils.RemoteFileMetadata(
        filename='rwc-p.csv',
        url='https://github.com/magdalenafuentes/metadata/archive/master.zip',
        checksum='7dbe87fedbaaa1f348625a2af1d78030',
        destination_dir=None,
    ),
    'annotations_beat': download_utils.RemoteFileMetadata(
        filename='AIST.RWC-MDB-P-2001.BEAT.zip',
        url='https://staff.aist.go.jp/m.goto/RWC-MDB/AIST-Annotation/AIST.RWC-MDB-P-2001.BEAT.zip',
        checksum='3858aa989535bd7196b3cd07b512b5b6',
        destination_dir='annotations',
    ),
    'annotations_sections': download_utils.RemoteFileMetadata(
        filename='AIST.RWC-MDB-P-2001.CHORUS.zip',
        url='https://staff.aist.go.jp/m.goto/RWC-MDB/AIST-Annotation/AIST.RWC-MDB-P-2001.CHORUS.zip',
        checksum='f76b3a32701fbd9bf78baa608f692a77',
        destination_dir='annotations',
github mir-dataset-loaders / mirdata / mirdata / medleydb_melody.py View on Github external
if data_home is None:
        data_home = utils.get_default_dataset_path(DATASET_DIR)

    info_message = """
        To download this dataset, visit:
        https://zenodo.org/record/2628782#.XKZdABNKh24
        and request access.

        Once downloaded, unzip the file MedleyDB-Melody.zip
        and copy the result to:
        {data_home}
    """.format(
        data_home=data_home
    )

    download_utils.downloader(data_home, info_message=info_message)
github mir-dataset-loaders / mirdata / mirdata / salami.py View on Github external
if data_home is None:
        data_home = utils.get_default_dataset_path(DATASET_DIR)

    info_message = """
        Unfortunately the audio files of the Salami dataset are not available
        for download. If you have the Salami dataset, place the contents into a
        folder called Salami with the following structure:
            > Salami/
                > salami-data-public-hierarchy-corrections/
                > audio/
        and copy the Salami folder to {}
    """.format(
        data_home
    )

    download_utils.downloader(
        data_home,
        remotes=REMOTES,
        info_message=info_message,
        force_overwrite=force_overwrite,
        cleanup=cleanup,
    )
github mir-dataset-loaders / mirdata / mirdata / orchset.py View on Github external
import csv
import glob
import librosa
import logging
import numpy as np
import os
import shutil

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


REMOTE = download_utils.RemoteFileMetadata(
    filename='Orchset_dataset_0.zip',
    url='https://zenodo.org/record/1289786/files/Orchset_dataset_0.zip?download=1',
    checksum='cf6fe52d64624f61ee116c752fb318ca',
    destination_dir=None,
)

DATASET_DIR = 'Orchset'


def _load_metadata(data_home):

    predominant_inst_path = os.path.join(
        data_home, 'Orchset - Predominant Melodic Instruments.csv'
    )

    if not os.path.exists(predominant_inst_path):
github mir-dataset-loaders / mirdata / mirdata / guitarset.py View on Github external
checksum='b39b78e63d3446f2e54ddb7a54df9b10',
    destination_dir='annotation',
)
AUDIO_HEX_CLN_REMOTE = download_utils.RemoteFileMetadata(
    filename='audio_hex-pickup_debleeded.zip',
    url='https://zenodo.org/record/3371780/files/audio_hex-pickup_debleeded.zip?download=1',
    checksum='c31d97279464c9a67e640cb9061fb0c6',
    destination_dir='audio_hex-pickup_debleeded',
)
AUDIO_HEX_REMOTE = download_utils.RemoteFileMetadata(
    filename='audio_hex-pickup_original.zip',
    url='https://zenodo.org/record/3371780/files/audio_hex-pickup_original.zip?download=1',
    checksum='f9911bf217cb40e9e68edf3726ef86cc',
    destination_dir='audio_hex-pickup_original',
)
AUDIO_MIC_REMOTE = download_utils.RemoteFileMetadata(
    filename='audio_mono-mic.zip',
    url='https://zenodo.org/record/3371780/files/audio_mono-mic.zip?download=1',
    checksum='275966d6610ac34999b58426beb119c3',
    destination_dir='audio_mono-mic',
)
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',
github mir-dataset-loaders / mirdata / mirdata / medley_solos_db.py View on Github external
def download(data_home=None):
    """Download Medley-solos-DB.

    Args:
        data_home (str): Local path where the dataset is stored.
            If `None`, looks for the data in the default directory, `~/mir_datasets`
    """
    if data_home is None:
        data_home = utils.get_default_dataset_path(DATASET_DIR)

    download_utils.downloader(
        data_home,
        tar_downloads=[AUDIO_REMOTE],
        file_downloads=[ANNOTATION_REMOTE],
        cleanup=True,
    )
github mir-dataset-loaders / mirdata / mirdata / guitarset.py View on Github external
import jams
import librosa
import logging
import numpy as np
import os

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


DATASET_DIR = 'GuitarSet'

ANNOTATION_REMOTE = download_utils.RemoteFileMetadata(
    filename='annotation.zip',
    url='https://zenodo.org/record/3371780/files/annotation.zip?download=1',
    checksum='b39b78e63d3446f2e54ddb7a54df9b10',
    destination_dir='annotation',
)
AUDIO_HEX_CLN_REMOTE = download_utils.RemoteFileMetadata(
    filename='audio_hex-pickup_debleeded.zip',
    url='https://zenodo.org/record/3371780/files/audio_hex-pickup_debleeded.zip?download=1',
    checksum='c31d97279464c9a67e640cb9061fb0c6',
    destination_dir='audio_hex-pickup_debleeded',
)
AUDIO_HEX_REMOTE = download_utils.RemoteFileMetadata(
    filename='audio_hex-pickup_original.zip',
    url='https://zenodo.org/record/3371780/files/audio_hex-pickup_original.zip?download=1',
    checksum='f9911bf217cb40e9e68edf3726ef86cc',
    destination_dir='audio_hex-pickup_original',
github mir-dataset-loaders / mirdata / mirdata / ikala.py View on Github external
import csv
import os
import librosa
import logging
import numpy as np

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


DATASET_DIR = 'iKala'
TIME_STEP = 0.032  # seconds
REMOTES = {
    'metadata': download_utils.RemoteFileMetadata(
        filename='id_mapping.txt',
        url='http://mac.citi.sinica.edu.tw/ikala/id_mapping.txt',
        checksum='81097b587804ce93e56c7a331ba06abc',
        destination_dir=None,
    )
}


def _load_metadata(data_home):
    if data_home is None:
        data_home = utils.get_default_dataset_path(DATASET_DIR)

    id_map_path = os.path.join(data_home, 'id_mapping.txt')
    if not os.path.exists(id_map_path):
        logging.info(
            'Metadata file {} not found.'.format(id_map_path)
github mir-dataset-loaders / mirdata / mirdata / rwc_genre.py View on Github external
import mirdata.utils as utils
import mirdata.download_utils as download_utils
import mirdata.jams_utils as jams_utils

# these functions are identical for all rwc datasets
from mirdata.rwc_classical import _load_beats, _load_sections, _duration_to_sec

METADATA_REMOTE = download_utils.RemoteFileMetadata(
    filename='rwc-g.csv',
    url='https://github.com/magdalenafuentes/metadata/archive/master.zip',
    checksum='7dbe87fedbaaa1f348625a2af1d78030',
    destination_dir=None,
)
DATASET_DIR = 'RWC-Genre'
ANNOTATIONS_REMOTE_1 = download_utils.RemoteFileMetadata(
    filename='AIST.RWC-MDB-G-2001.BEAT.zip',
    url='https://staff.aist.go.jp/m.goto/RWC-MDB/AIST-Annotation/AIST.RWC-MDB-G-2001.BEAT.zip',
    checksum='66427ce5f4485088c6d9bc5f7394f65f',
    destination_dir='annotations',
)
ANNOTATIONS_REMOTE_2 = download_utils.RemoteFileMetadata(
    filename='AIST.RWC-MDB-G-2001.CHORUS.zip',
    url='https://staff.aist.go.jp/m.goto/RWC-MDB/AIST-Annotation/AIST.RWC-MDB-G-2001.CHORUS.zip',
    checksum='e9fe612a0ddc7a83f3c1d17fb5fec32a',
    destination_dir='annotations',
)


def _load_metadata(data_home):

    metadata_path = os.path.join(data_home, 'metadata-master', 'rwc-g.csv')
github mir-dataset-loaders / mirdata / mirdata / salami.py View on Github external
"""
import csv
import librosa
import logging
import numpy as np
import os

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

DATASET_DIR = 'Salami'

REMOTES = {
    'annotations': download_utils.RemoteFileMetadata(
        filename='salami-data-public-hierarchy-corrections.zip',
        url='https://github.com/bmcfee/salami-data-public/archive/hierarchy-corrections.zip',
        checksum='194add2601c09a7279a7433288de81fd',
        destination_dir=None,
    )
}


def _load_metadata(data_home):

    metadata_path = os.path.join(
        data_home,
        os.path.join(
            'salami-data-public-hierarchy-corrections', 'metadata', 'metadata.csv'
        ),
    )