Builtin multichannel model & LibriMix recipes

Highlight

• Deprecated: Not feeding sample_rate to BaseModel is deprecated, and it will raise an error in the future release.
• BaseModel now takes a in_channels argument which will be used in separate and the asteroid-infer CLI.
  This makes it now possible to share multichannel models on the hub (for example)
• The first fully supported multichannel model is FasNetTAC thanks to @popcornell ! 🎉
• Use huggingface_hub instead of "our own" code for interfacing with the Hub.

Changelog

Breaking

• [src] Make sample_rate positional in BaseModel (#431)

Added

• [src&egs] ESPNet in LibriMix recipe 🎉 (#329)
• [cli] Add --device to asteroid-infer (#375)
• [src] Add stft_n_filters to BaseDCUNet (#406)
• [src&tests] Add MetricTracker (#394)
• [egs] Librimix recipes for all models (#418)
• [src] Track transcriptions in WerTracker (#414)
• [docs] Add note about System Lightning hooks (#428)
• [src] Support Multichannel models (#427)
• [src&egs] Add FasNetTAC model, dataset and recipe (#306)
• [src] Add mulcat option to DPRNN (#416)

Changed

• [src&install] Drop librosa and refactor requirements files (#386)
• [src] Remove unused hooks (#424)
• [hub] Use huggingface_hub deps, remove inlined HF code (#409)

Fixed

• [egs] Pass samplerate to model (#407)
• [src] Fix Large-DCUNet-20 arch (#405)
• [src] Fix inconsistent devices for tensors (#417)
• [egs] Fix model saving path in DeepClustering recipes(#398)
• [src] Fix unpassed SR in TasNet and SudoRMRF (#433)
• [egs] Fix reshaping issue in AVSpeech (#441)