Unofficial PyTorch dataset for Slakh
Project description
Slakh PyTorch Dataset
Unofficial PyTorch dataset for Slakh.
This project is a work in progress, expect breaking changes!
Roadmap
Automatic music transcription (AMT) usecase with audio and labels
- Specify dataset split (
original
,splits_v2
,redux
) - Add new splits (
redux_no_pitch_bend
, ...) (Should also be filed upstream) (implemented byskip_pitch_bend_tracks
) - Load audio
mix.flac
(all the instruments comined) - Load individual audio mixes (need to combine audio in a streaming fashion)
- Specify
train
,validation
ortest
group - Choose sequence length
- Reproducable load sequences (usefull for validation group to get consistent results)
- Add more instruments (
eletric-bass
,piano
,guitar
, ...) - Choose between having audio in memory or stream from disk (solved by
max_files_in_memory
) - Add to pip
Audio source separation usecase with different audio mixes
- List to come
Usage
-
Download the Slakh dataset (see the official website). It's about 100GB compressed so expect using some time on this point.
-
Install the Python package with pip:
pip install slakh-dataset
-
Convert the audio to 16 kHz (see https://github.com/ethman/slakh-utils)
-
You can use the dataset (AMT usecase):
from torch.utils.data import DataLoader
from slakh_dataset import SlakhAmtDataset
dataset = SlakhAmtDataset(
path='path/to/slakh-16khz-folder'
split='redux', # 'splits_v2','redux-no-pitch-bend'
audio='mix.flac', # 'individual'
label_instruments='electric-bass', # or `label_midi_programs`
# label_midi_programs=[33, 34, 35, 36, 37],
groups=['train'],
skip_pitch_bend_tracks=True,
sequence_length=327680,
max_files_in_memory=200,
)
batch_size = 8
loader = DataLoader(dataset, batch_size, shuffle=True, drop_last=True)
# train model on dataset...
Acknowledgement
-
This code is based on the dataset in Onset and Frames by Jong Wook Kim which is MIT Lisenced.
-
Slakh http://www.slakh.com/
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
slakh-dataset-0.1.24.tar.gz
(49.2 kB
view hashes)
Built Distribution
Close
Hashes for slakh_dataset-0.1.24-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | afd47073705c0b11c75027bb97c510ba3dd6fa05bcf7fc7762d4232a63cff742 |
|
MD5 | deabb90691ed094ede67e6b5101a418f |
|
BLAKE2b-256 | 17c6dc4166d77f1cad74d24f5dc03f42a3ad9559aff4b4229c0ce3075be85fd8 |