Openunmix

- fixes broken zenodo urls
- supports `wiener_win_len` in hubmodels (see https://github.com/sigsep/open-unmix-pytorch/issues/106)
- update to python 3.9 and test most recent torch version
- speed up unit tests

What's Changed
* Fix_stft_istft_window_parameters by faroit in https://github.com/sigsep/open-unmix-pytorch/pull/107
* remove 3.6 by faroit in https://github.com/sigsep/open-unmix-pytorch/pull/117
* Fixed issue 115 with broken --help option by TobiasB22 in https://github.com/sigsep/open-unmix-pytorch/pull/116
* Bump numpy from 1.21.2 to 1.22.0 in /scripts by dependabot in https://github.com/sigsep/open-unmix-pytorch/pull/120
* Bump joblib from 1.0.1 to 1.2.0 in /scripts by dependabot in https://github.com/sigsep/open-unmix-pytorch/pull/126
* The default option for --is-wav is False by satvik-venkatesh in https://github.com/sigsep/open-unmix-pytorch/pull/130
* Set unidirectional flag by satvik-venkatesh in https://github.com/sigsep/open-unmix-pytorch/pull/131
* Bump gitpython from 3.1.18 to 3.1.34 in /scripts by dependabot in https://github.com/sigsep/open-unmix-pytorch/pull/136
* Bump scipy from 1.7.1 to 1.10.0 in /scripts by dependabot in https://github.com/sigsep/open-unmix-pytorch/pull/134
* Bump future from 0.18.2 to 0.18.3 in /scripts by dependabot in https://github.com/sigsep/open-unmix-pytorch/pull/145
* Bump gitpython from 3.1.34 to 3.1.41 in /scripts by dependabot in https://github.com/sigsep/open-unmix-pytorch/pull/146
* openunmix v1.3.0: update zendo links by faroit in https://github.com/sigsep/open-unmix-pytorch/pull/144

New Contributors
* TobiasB22 made their first contribution in https://github.com/sigsep/open-unmix-pytorch/pull/116
* dependabot made their first contribution in https://github.com/sigsep/open-unmix-pytorch/pull/120
* satvik-venkatesh made their first contribution in https://github.com/sigsep/open-unmix-pytorch/pull/130

**Full Changelog**: https://github.com/sigsep/open-unmix-pytorch/compare/v1.2.1...v1.3.0

New features

* training script also allows to select a pre-trained model to be fine-tuned using the `--model` parameter 103
* a commandline progress bar has been added to see the progress for multiple tracks being separated 102

Breaking changes

* `umxl` is now selected as the new default model for inference using the commandline and the python API 97
* training argument `--model` has been renamed to `--checkpoint`.

Bug fixes

* addresses backend compatibility issues with sox_io on windows 93

We are excited to announce a new pre-trained open-unmix model trained on hundreds of hours of extra training data which significantly boosts performance and generalization. Note that this model can only be used for non-commercial applications.

Bugfix release

* fixed missing dependency (tqdm) for cli-only package 81

New Features

* added support for pytorch 1.8.0 and torchaudio 0.8.0, unfortunately this means that support for torchaudio <0.7.0 has been dropped. 79

New Features

* added implementation of differentiable wiener filters, removing norbert redundancy
* added more flexible encoder/decoder transform architecture
* updated to codebase to pytorch ~~1.4.0~~, ~~1.5.0~~, ~~1.5.1~~, 1.6.0, 1.7.0
* added a `force_stereo` augmentation to address heterogeneous datasets of mixed channels 41
* added type hint annotations
* restructured code as a python package 46 via 60
* update to musdb 0.4.0 and museval 0.4.0
* added test for onnx export
* added `stempeg` based audio inference backend to improve reading and writing of compressed audio
* switch from travis to github actions (thanks to mpariente)
* update docs

Bug Fixes

* address issue with dataset statistic calculation 33
* fixes glob(*) behaviour which is known to not be deterministic and can cause [non-reproducible behavior](https://pubs.acs.org/doi/10.1021/acs.orglett.9b03216)
* uses centered audio segments for `sourcefolder` dataset

Thanks

Thanks to aliutkus, Baldwin-disso, keunwoochoi for the contributions.
Special thanks to mpariente for the awesome asteroid code base.