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
0.4.1
Downloading the preview dataset from zenodo was too slow, so we switched to gh releases
0.4.0
* 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
0.3.1
This releases upgrades the `stempeg` dependency to 0.1.7 to [address a bug](https://github.com/faroit/stempeg/pull/21) that could occur when using the chunking functionality in musdb.
0.3.0
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.