Bugfix release: fixing sample rate conversion support

This releases fixes the ability to get musdb18 in a different sample rate. e.g mus = musdb.DB(download=True, subsets="test", sample_rate=16000) does now correctly resample the audio on-the-fly

Switch to github release location for 7s previews

Downloading the preview dataset from zenodo was too slow, so we switched to gh releases

musdb v0.4.0

• fix a problem that was producing a wrong train test split #60
• update to newest version of stempeg resulting in 20-30% faster loading times when using compressed mp4 files #64
• smaller code clean ups #66 #67 #68 #71

Thanks to @TE-StefanUhlich @hagenw @csukuangfj

Bugfix release to update stempeg to version 0.1.7

This releases upgrades the stempeg dependency to 0.1.7 to address a bug that could occur when using the chunking functionality in musdb.

musdb 0.3.0: a better fit for deep learning datasets

New musdb is released which addresses a few things related to when using musdb inside your deep learning framework.

New features

• musdb.DB() directly loads the list of tracks. No need to call load_musdb_tracks.
• iterating over the track is simplified since the musdb.DB object is iterable and supports indexing
• musdb.tools now has a tool to convert a stems dataset to wav (or flac) automatically.
• we now provide a predefined train/validation split to foster reproducible research.
• musdb now supports chunking of the audio (both via stempeg for stems and soundfile for wavs) to efficiently load only parts of the audio
• A 7 seconds preview version of the musdb18 dataset is automatically downloaded and can be used on the fly. (this is fun for jupyter/colab!).

Incompatible changes

• support for python 2.7 was dropped
• musdb.run was removed since it was not used a lot and people used their own methods to do multiprocessing over different tracks.

Fixing test function and allow to np.float32 as output dtype

Addressing #10

Thanks to @f90

Improve `test()` function and fix bugs

Addressing #6 and #8

Thanks

@StefanUhlich for fixing the filename bug.

Bugfixes

Addresses #1, #2, #3, #4

Additionally supports

• track.duration: that returns the duration in seconds

dsd100 -> musdb

• Change file format to support stems
• remove evaluation and parsing of ids to simplify the process for users