Torch>=1.8 only, better beamforming and MDX challenge baseline
The next release (0.5.1) will add support to PyTorch-Lightning 1.3.0 which broke our CI.
Highlights
- Beamforming modules are now more stable (computed in double by default), have been renamed and extended.
- The baseline for the Music Demixing Challenge has been released 🎉
Changelog
Breaking
Added
- [src] Beamforming: Souden MVDR and optimal channel selection (#484)
- [src&egs] X-UMX Official baseline for Music Demixing Challenge (#490)
Changed
- [src] Compute linalg beamforming ops in double (#482)
- [src] Improve Beamforming naming and add TODOs (#483)
- [src] Beamforming: enable forcing float linalg ops (#485)
- [docs] Update instructions for pretrained model sharing (#489)
- [install] Bump lightning version under 1.3.0 (#493)
Fixed
- [nb] Fix shape in 00_GettingStarted.ipynb (#478)
- [src] Stabilize GEV beamformer (#479)
- [src] Beamforming: fix doc references
Thanks to @quancs @r-sawata @popcornell and @faroit for their contributions