⬆️ Upgrade ⬆️

Changes documented in #682 :

• Remove the optimizer_idx in lr_scheduler_step in System.
• Replace torch.symeigh by torch.linalg.eigh in beamforming.py
• Disable X-UMX as it uses torch1.x STFT : @r-sawata do you want to fix it ?
• Replace on_*_end with on_training_*_end
• Replace torch.testing.assert_allclose with torch.testing.assert_close.

Happy coding 🙃

Release before moving to asteroid 0.7.x with torch and lightning upgrades.

Breaking

• [install] Limit torch and pytorch-lightning to 1.x (#671)

Added

• [egs] Raise error if storage_dir not specified in LibriMix recipes (#626)
• [egs] Create Multi-Decoder DPRNN README.md (#632)
• [egs] Update Multi-Decoder DPRNN with inference function on a single file out-of-the-box (#653)
• [egs] Add a new pre-trained model (X-UMXL) (#665)
• [egs] Add a notebook demo, separate.py script for MD-DPRNN. Easier use from_pretrained (#668)

Changed

• [src] Use torch.linalg for solve and cholesky (#623)
• [install] Remove torchmetrics version limit
• [CI] Lint with black 22.3.0 and fix linting CI python3.*8 (#624)

Fixed

• [hub] Upgrade deprecated huggingface_hub.cached_download (#645)
• [src] Fix cumulative normalization (#649)
• [src] Fix argparse key based on Python version (#628) (#657)
• [ci] Fix tests in continuous integration (#672)

Many thanks to all the contributors @actuallyaswin, @mystlee, @JunzheJosephZhu, @jbartolewska, @LeonieBorne, @mattiadg, @r-sawata and @zmolikova ! 💪 🤩 🙏

Yes. That's it. Only Pytorch-Lightning support.

From 1.5.0 to the latest versions.

So changing to the new Trainer API with the new accelerator, strategy and devices arguments.

Thanks to @paulfd to push me to do it 💪

Minor patch release before 0.6.0 that will upgrade pytorch-lightning version.

Added

• [egs&tests] MixIT loss function (#595)

Changed

• [docs] Update RTD version to 0.5.1

Fixed

• [src] Fix FasNetTAC loading (#586)
• [src] Fix device in padding for sudormrf. Fix #598 (#603)
• [docs] Fix deep_clustering_loss docs example (#607)
• [src] Remove torch.complex32 usage for torch 1.11.0 (#609)
• [egs] Fix package install script for WHAMR! (#613)
• [src] Fix shape mismatching in SuDORMRF's masknn (#618)
• [CI] Fix CI Restrict torchmetrics version to under 0.8.0 (#619)
• [docs] Fix docs Restrict jinja2>=3.0.0,<3.1.0 (#620)

Thanks to @jc5201, @z-wony, @JorisCos, @ben-freist, @nicocasaisd and @zmolikova for their awesome contributions 🔥 💪 🙏

Highlights

• New ConvTasNet-based VAD on the Libri_VAD dataset 🚀
• Fixed and improved GEVD beamformer
• Multi-Decoder DPRNN recipe

Changelog

Added

• [src&egs] Add VAD in Asteroid 🎉 (#558)
• [src&tests] Add GEVD beamformer (#520)
• [hub] Add library version and name for Hugging Face download stats (#524)
• [egs] Add recipe for Multi-Decoder DPRNN (#463)
• [egs] Enable WER eval with GPU (#541)
• [egs] Add readme and pretrained model to FaSNet recipe (#561)

Changed

• [src] Make cLN default in causal ConvTasNet (#511)
• [install] Pin pytorch-optimizer version to support RAdam (#568)

Fixed

• [src] Prevent complex eigen values in gev (#519)
• [src] Fix default norm_type for causal ConvTasNet (#503)
• [egs] Fixed bug in X-UMX (#521)
• [nbs] asteroid.filterbanks to asteroid_filterbanks (#526)
• [nbs] Fix typos in notebooks/02_Filterbank.ipynb (#527)
• [install] Fix PL version <1.5.0 (#576)

Thanks to @ldelebec @hihunjin @nobel861017 @ben-freist @r-sawata @osanseviero @JunzheJosephZhu and @JorisCos for their awesome contributions 🔥 💪 🙏

Nothing more, nothing less 🙃
Check the release below for the most recent release notes.

⚠️ This release drops support for PyTorch under 1.8 and restricts PyTorch-Lightning under 1.3.
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

• [src&tests] Remove all deprecated code (#474)
• [all] Drop support for torch<1.8.0 (#476)

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

⚠️ Warning ⚠️ this is the last release that supports torch<1.8.

From asteroid 0.5.0 onwards, only torch>=1.8.0 will be supported. The main reason being the complex support, the fft and linalg packages.

Highligths

• We now have end to end beamforming modules! 🎉 Multichannel recipes will follow.

Changelog

• [src] Fix padding in DCUNet ConvTranspose2d (#466)
• [src&tests] Causal TDConvNet and ConvTasNet (#465)
• [tests] Fix test from #465 (#467)
• [docs] Fix wrong doclinks (#469)
• [docs] Fix docs (links and errors) (#470)
• [src&tests] Add beamforming modules 🎉 (#468)

Large thanks to the contributors ! 🙃

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)

Highlights

• Finally upgrade to Lightning 1.x. Have a look at their docs to see what's new! In particular, callbacks and logging have changed a bit, for the better 😉
• Migration from the Zenodo hub to the HuggingFace's model hub, we even have a tag and a Use in Asteroid button, this is great! 🤩 Huge thanks to the HuggingFace team and @julien-c in particular. 🙏

Changelog

Added

• [hub] Support for huggingface model hub 🎉 (#377)
• [hub] List asteroid models HF's hub (#382)
• [install] Deduplicate version number (#388)

Changed

• [docs] Migrate to asteroid-team (#369)
• [src] Import BaseModel from .models
• [src] Upgrade Lightning to 1.x (#371)

Fixed

• [install] Fix old STFT model loading (thanks @popcornell)
• [hub] Fix torch.hub tests Add new dependencies from #377
• [src] bug in attention.py due to mha input shape (#381)
• [src] Hopefully fixes DPTNet this time (#383)
• [src] Remove call to super().training_step() (#395)

Thanks to all the contributors: @jonashaag, @popcornell, @julien-c, @iver56, @lubacien, @cliffzhao and the issue creators and bug-reporters 🙏

Highlights

• Full TorchScript support for all asteroid models, unit tested for consistency 🚀
• Outsource all filterbanks to asteroid-filterbanks with a new MelGramFB, a STFT that matches torch.stft and new hooks for more extensibility!
• Direct links to GitHub code from the docs 🎉
• Add Hungarian algorithm in PITLossWrapper + new MixITWrapper and SinkPITLossWrapper ⚡
• Better CI with tests against 1.6.0, 1.7.0 and torch-nightly.

Backwards Incompatible Changes

• filters in Filterbank is now a method instead of a property, for TorchScript support (#237).
• PITLossWrapper method best_perm_from_perm_avg_loss, find_best_perm now return batch indices of the best permutation, to match with the new hungarian algorithm and facilitate outside use of those methods (#243).
• Models that were saved without sample_rate argument won't be loadable anymore. Use asteroid-register-sr to register the sample rate of the model (#285).
• We finally removed the losses (#343 ) and blocks (#344) that were deprecated since 0.2.0.
• Remove kernel_size argument from TDConvNet (deprecated since v0.2.1) (#368).

Deprecation

• BaseModel._separate is deprecated in favour of BaseModel.forward_wav (#337).
• asteroid.filterbanks has been outsourced to asteroid-filterbanks (#346). Use from asteroid_filterbanks import instead of from asteroid.filterbanks import from now.
• Several deprecation cycles have been engaged in asteroid-filterbanks.transforms:
  • take_reim will be removed.
  • take_mag is deprecated in favour of mag.
  • take_cat is deprecated in favour of magreim.
  • from_mag_and_phase is deprecated in favour of from_magphase.
• asteroid.complex_nn.as_torch_complex has been deprecated and will be removed. Use torch.view_as_complex, torch_complex_from_magphase, torch_complex_from_reim or asteroid_filterbanks.transforms.from_torch_complex instead (#358).

Changelog

Breaking

[src] BC-breaking: Load models without sample_rate (#285)
[src] Remove deprecated losses (#343)
[src] Remove deprecated blocks (#344)
[src] BaseEncoderMaskerDecoder: remove old hooks (#309)
[src] Remove deprecated kernel_size in TDConvNet (#368)

Added

[src&tests] Add sample_rate property (float) in BaseModel. (#274)
[src] Add sample_rate argument to all supported models. (#284)
[src&tests] Automatic resampling in separate + CLI. (#283)
[src & tests] 🎉 TorchScript support 🎉 (#237)
[src & tests] Add Hungarian matcher to solve LSA in PITLossWrapper (#243)
[src&tests] Add jitable_shape and use it in EncMaskDec forward (#288)
[src&tests] Add shape checks to SDR and MSE losses (#299)
[docs] Add loss plot in the FAQ (#314)
[src] New asteroid.show_available_models (#313)
[egs] DAMP-VSEP vocal separation using ConvTasNet (#298)
[docs] DAMP-VSEP in the docs ! (#317)
[src&test] Add Sinkhorn PIT loss (#302)
[src] Add MixITWrapper loss (#320)
[egs] Add MixIT example recipe (#328)
[src] New Filterbank's hooks + add MelGram_FB (#334)
[src] New phase features and transforms (#333)
[src] Better names in asteroid.filterbanks.transforms (#342)
[src] Add asteroid-versions script to print installed versions (#349)
[install] Add conda environment.yml (#354)
[src] Add ebased_vad and deltas (#355)

Changed

[src&tests] Make get_metrics robust against metrics failures (#275)
[egs] Don't override print() with pprint (#281)
[src] Refactor BaseEncoderMaskerDecoder.forward (#307)
[src&tests] Refactor DeMask for consistency (#304)
[docs] Replace GettingStarted notebook (#319)
[src] BaseModel takes sample_rate argument (#336)
[src&egs] Transition to asteroid_filterbanks (#346)
[src] Rename _separate to forward_wav (#337)
[docs] Build docs with 3.8
[docs] Links to GitHub code from the docs 🎉 (#363)
[CI&hub] TorchHub integration tests (#362)

Fixed

[egs] Fix #277 DNS Challenge baseline's run.sh
[docs] Fix Reference and Example blocks in docs (#297)
[src] Fix #300: skip connection on good device (#301)
[src] DCUNet: Replace old hooks by new ones (#308)
[src] Fix schedulers serialization (#326)
[src] Improve Filterbank.forward error message (#327)
[egs] Fix: replace DPRNNTasNet with DPTNet (#331)
[src&jit] Fix DCCRN and DCUNet-Large (#276)
[CI] Catch warnings we expect (#351)
[src] Fix #279 OLA support for separate() and asteroid-infer (#305)
[docs] Docs fixes and improvements (#340)
[docs] Fix CLI output in docs (#357)
[src&tests] Fix complex and add tests (#358)
[docs] Fix docstrings (#365)
[src] Fix #360 Correct DCCRN RNN (#364)

A large thanks to all contributors for this release :
@popcornell @jonashaag @michelolzam @faroit @mhu-coder @JorisCos @groadabike @giorgiacantisani @tachi-hi @SouppuoS @sunits @guiruli08650129 @mcernak @zmolikova & @hbredin 🥰
(ping me if you got forgotten, I'll add you back, and sorry in advance 😉 )

Since v0.3.4, pytorch_lightning released 1.0 which is incompatible. This release only limits lightning's version so that the install is compatible with the source code.

Highlights

• Fixed compatibility issue of pretrained models between v0.3.0 and v0.3.3 thanks to @groadabike (issue #255, #258)
• Fixed chunk reordering in LambdaOverlapAdd.
• BaseEncoderMaskerDecoder (formerly BaseTasNet) now has model hooks for easier extensibility (thanks to @jonashaag) : postprocess_encoded, postprocess_masks, postprocess_masked, postprocess_decoded`
• Brand new complex ops and NNs thanks to @jonashaag !
• New supported models: DCUNet (paper)and DCCRNet (paper)

Note : Next release (0.4.0) will have some small backward breaking changes, to support TorchScript and improve our PITLossWrapper.

Changelog

Added

[hub] Add tmirzaev's model in the string-retrievable ones.
[src] BaseTasNet -> BaseEncoderMaskerDecoder + add model hooks (#266)
[src & tests] New complex ops + Add DCUNet and DCCRNet (#224)
[src&tests] Improve scheduler's docs + add plot method (#268)

Changed

[hub] Add software version section in published models (#261)
[docs] Add issue #250 to FAQ (#260)
[black] Update black to 20.8b1 (#265)
[black] Fix black 20.8b1 update (#267)
[black] Update to 20.8b1 + always lint

Fixed

[egs] Fix declared unused variables in DeMask (#248)
[docs] Update article citation.
[src] Restore linear activation as default in ConvTasNet and DPRNN (#258)
[src] Fix uncalled optimizer in System without LR schedule (#259)
[src] Fix bug for DPTNetScheduler (#262)
[src] Fix LambdaOverlapAdd and improve docs (#271)

Thanks to our awesome contributors @popcornell @jonashaag @faroit @groadabike !

Highlights

• Refactored base models to ease publishing and loading
• Improve Asteroid extensibility (without -e install) with register/get logic.
• asteroid-infer CLI for easy enhancement/separation
• DeMask recipe + pretrained model
• Upgrade to lightning 0.8.1+
• Brand new docs ! (thanks @michelolzam)
• Brand new landing page ! (thanks @michelolzam)

Changelog

Added

• [hub] Add DeMask to hubconf (#242)
• [models] Add 16k popcornell/DPRNNTasNet_WHAM_enhancesingle enhancement
• [src & egs] Add DeMask: Surgical mask speech enhancement recipes (#235)
• [models] Add pretrained DeMask name to URL mapping
• [src & egs] PyTorchLightning upgrade to 0.9.0 (stable from 0.8.1 on) (#217)
• [CLI] Add asteroid-infer CLI to enhance/separate from the command line (#236)
• [docs] New docs theme ! (#230)
• [tests] Improve tests for new model interface (#234)
• [docs] Add license info to FUSS Dataset
• [src] Cleaner try/except/else in base_models.py (thanks @jonashaag)
• [src] Add LibriMix.loaders_from_mini in librimix_dataset.py (#229)
• [src] Add register command to gettable modules (#231)
• [models] Add groadabike's pretrained model's URL (#228)
• [src] Import MultiScale spectral loss in init.py
• [docs] Include new notebook: follow up of #221 (#226)
• [src] Add LambdaOverlapAdd usage example (#221)

Changed

• [src] Improve BaseModel.separate (#236 follow up) (#238)
• [hub] Remove args in hub models, don't accept positional args after kwargs
• [src] Refactor BaseTasnNet in two: better loadable/serializable models (#232)

Fixed

• [CLI] Fix large output volume in asteroid-infer
• [docs] Fix theme installation, grunt build and import errors in docs (#240)
• [tests] Fix wrong separate method in model tests (#241)
• [src] Recipe name in publisher + dataset name fix (#239)

Highlights

• New supported models:
  • DualPathTransformer Network (DPTNet).
  • SuDORMRF Network.
  • LSTM TasNet accessible from hub.
  • TDCNpp masking network.
• Batch-wise schedulers (very useful for transformers) are now available.
• LambdaOverlapAdd to easily process long files.
• Add SMS_WSJ Dataset.
• Add FUSS Dataset.
• Consistent codestyle with black and more extensive testing
• Redable docs ! [latest][0.3.1]

Note: Next releases will be based on pytorch-lightning>=0.8.0.

Changelog

Added

• [tests] Add scheduler tests (#220)
• [docs] Add schedulers, activations docs and improve datasets' docs (#219)
• [docs] Add DSP section to docs (#218)
• [docs] Add FUSSdataset to docs
• [docs] Add schedulers in docs
• [docs] Add activations to docs
• [src] Add FUSS dataset from FUSS PR (#215)
• [src & tests] Add TDCN++ to masknn (#214)
• [hub] Add LSTMTasNet/DPTNet/SuDORMRFNet to torch.hub! (#210)
• [src & tests] Add LSTMTasNet to serializable models (#209)
• [src] Continuous Speech separation with LambdaOverlapAdd (#193)
• [src] Continuous Speech separation with OverlappadWrapper (#191)
• [src & tests] Add SuDoRM-RF model & online mixing collate function (#174)
• [src, tests & egs] Batchwise learning rate schedulers + DPProcessing + Dual Path Transformer Network + recipe (#200)
• [docs] Add black code-style
• [hub] Add Brij's LibriMix enhancement model
• [src] Adds Dataset for SmsWsj (#179)
• [docs] STOI loss example: Add sample rate (#189)
• [src & tests] Add feature-wise global layernorm (#170)

Changed

• [src & tests] Split SuDORMRF architectures in encoder/masker/decoder (#208)
• [src] Code-style + docs
• [src & tests] (BWI) Gather DSP methods in dsp folder (#194)
• [egs] EarlyStopping Patience to 30 instead of 10. (#178)

Fixed

• [src] Fix docs append problem in STOI.
• [black] Apply black to recipes (#216)
• [tests & CI] Fix tests for publishing (#211)
• [notebooks] Fix notebooks (#206)
• [src & tests] Fix serialization issues introduced in previous PR + some docs (#204)
• [egs] Remove file librimix/model.py as model is imported from asteroid.models (#176)
• [egs] Dynamic Mixing fix (#173)
• [instal] Fix pytorch-lightning dependency (#159)
• [egs] Fix empty audio, multi gpu and reduced storage issues in avspeech (#169)
• [egs] Fix style in model.py
• [egs] Fix bugs in generating wsj0-mix dataset with wv1 (#166)
• [egs] Fix wrong rel path in wham/DPRNN prepare_data.sh (#167)
• [egs] Fix clipping problems when saving estimate wav file for Wham ConvTasNet (#160)

Backward incompatible changes

• Move mixture_consistency in dsp folder.

Use 0.3.2 instead.

Backward incompatible changes

• System is not imported from asteroid/__init__.py. This way, torch.hub doesn't need pytorch-lightning to load models. Replace your from asteroid import System calls by from asteroid.engine.system import System
• Refactor utils files into asteroid/utils folder (#120).
  The only not backward compatible behavior is when we try to import a function from torch_utils e.g from asteroid.torch_utils import pad_x_to_y. Instead, we can use from asteroid import torch_utils; torch_utils.pad_x_to_y(...)

Added

[src & egs] Publishing pretrained models !! (wham/ConvTasNet) (#125)
[src] Add License info on all (but MUSDB) supported datasets (#130)
[src & egs] Kinect-WSJ Dataset and Single channel DC Recipe (#131)
[src] Add licenses info and dataset name for model publishing
[docs] Add getting started notebook
[docs] Add notebook summary table
[egs] Enable pretrained models sharing on LibriMix (#132)
[egs] Enable wham/DPRNN model sharing (#135)
[model_cards] Add message to create model card after publishing
[model_cards] Add ConvTasNet_LibriMix_sepnoisy.md model card (Thanks @JorisCos)
[src & egs] Adding AVSpeech AudioVisual source separation (#127)
[src] Instantiate LibriMix from download with class method (#144)
[src] Add show_available_models in asteroid init
[src & tests] Bidirectional residual RNN (#146)
[src & tests] Support filenames at the input of separate (#154)

Changed

[src & hub] Remove System to reduce torch.hub deps (back to #112)
[src & tests & egs] Refactor utils files into folder (#120)
[egs] GPU id defaults to $CUDA_VISIBLE_DEVICES in all recipes (#128)
[egs] set -e in all recipes to exit or errors (#129)
[egs] Remove gpus args in all train.py (--id controls that in run.sh) (#134)
[hub] Change dataset name in LibriMix (fix)
[src] Add targets argument (to stack sources) to MUSDB18 (#143)
[notebooks] Rename examples to notebooks
[src] Enable using Zenodo without api_key argument (set ACCESS_TOKEN env variable)

Deprecated

[src] Deprecate inputs_and_masks.py (#117)
[src] Deprecate PITLossWrapper mode argument (#119)

Fixed

[src] Fix PMSQE loss (NAN backward + device placement) (#121)
[egs] Fix checkpoint.best_k_models in new PL version (#123)
[egs] Fix: remove shuffle=True in validation Loader (lightning error) (#124)
[egs] Corrections on LibriMix eval and train and evals scripts (#137)
[egs] Fix wavfiles saving in eval.py for enh_single and enh_both tasks (closes #139)
[egs] Fix wavfiles saving in eval.py for enh tasks (estimates)
[egs] Fix #139 : correct squeeze for enhancement tasks (#142)
[egs] Fix librimix run.sh and eval.py (#148)

Summary

• New datasets: LibriMix, wsj0-mix, MUSDB18 and FUSS.
• New recipes: DPRNN, TwoStep separation, Deep clustering, Chimera++
• asteroid.models + hubconf.py: Model definitions without installing Asteroid.

Added

• [src] Add dataset_name attribute to all data.Dataset (#113) (@mpariente)
• [hub] Add hubconf.py: load asteroid models without install ! (#112) (@mpariente)
• [src] Add support to the MUSDB18 dataset (#110) (@faroit)
• [src & tests] Importable models: ConvTasNet and DPRNNTasNet (#109) (@mpariente)
• [egs] Deep clustering/Chimera++ recipe (#96) (@mpariente)
• [src & egs] Source changes towards deep clustering recipe (#95) (@mpariente)
• [docs] Add training logic figure (#94) (@mpariente)
• [install] Include PMSQE matrices in setup.py (@mpariente)
• [src & egs] DPRNN architecture change + replicated results (#93) (@mpariente)
• [egs] Two step recipe : update results (#91) (@etzinis)
• [src & tests] Add multi-phase gammatone filterbank (#89) (@dditter)
• [src] Stabilize consistency constraint (@mpariente)
• [src] LibriMix dataset importable from data (@mpariente)
• [src & egs] LibriMix dataset support and ConvTasnet recipe (#87) (@JorisCos)
• [egs] Dynamic mixing for Wham (#80) (@popcornell)
• [egs] Add FUSS data preparation files (#86) (@michelolzam)
• [src & tests] Implement MISI (#85) (@mpariente)
• [src] ConvTasnetv1 available : no skip option to TDCN (#82) (@mpariente)
• [src & tests] Implement GriffinLim (#83) (@mpariente)
• [docs] Add reduce example in PITLossWrapper (@mpariente)
• [src & tests] Generalize ! Implement pairwise losses reduce function (#81) (@mpariente)
• [src & tests] Add support for STOI loss (#79) (@mpariente)
• [src] Support padding and output_padding in Encoder and Decoder (#78) (@mpariente)
• [src & tests] Added mixture consistency constraints (#77) (@mpariente)
• [logo] Add white-themed asteroid logo (@mpariente)
• [egs] Add Two step source separation recipe (#67) (@etzinis)
• [src] Add train kwarg in System's common_step for easier subclassing. (@mpariente)
• [egs] Upload Tasnet WHAMR results (@mpariente)
• [src & tests] Add PMSQE loss in asteroid (#65) (@mdjuamart)
• [src] Add Ranger in supported optimizers (@mpariente)

Changed

• [src & tests] Depend on torch_optimizer for optimizers (#116) (@mpariente)
• [src & tests] Upgrade pytorch-lightning to >= 0.7.3 (#115) (@mpariente)
• [src] Reverts part of #112 (0.2.1 should be fully backward compatible) (@mpariente)
• [src] Change .pth convention for asteroid-models (#111) (@mpariente)
• [src] Split blocks in convolutional and recurrent (#107) (@mpariente)
• [install] Update pb_bss_eval to zero-mean si-sdr (@mpariente)
• [egs] Remove python installs in recipes (#100) (@mpariente)
• [egs] Remove abs path in recipes (#99) (@mpariente)
• [egs] Add DC requirements.txt (@mpariente)
• [egs] Remove file headers (@mpariente)
• [src] Remove Chimerapp from blocks.py (#98) (@mpariente)
• [egs] Better logging : copy logs to expdir (#102) (@mpariente)
• [src] Delete wav.py (@mpariente)
• [egs] Delete unused file (@mpariente)
• [ci] Restore old travis.yml (reverts part of #61) (@mpariente)
• [egs] Utils symlink sms_wsj (@mpariente)
• [egs] Utils symlink wham/TwoStep (@mpariente)
• [egs] Utils symlink wham/DPRNN (@mpariente)
• [egs] Utils symlink LibriMix (@mpariente)
• [src & egs] Replace WSJ0-mix Dataset (#97) (@mpariente)

Deprecated

• [src] Deprecate kernel_size arg for conv_kernel_size in TDConvNet (#108) (@mpariente)
• [src] Deprecate masknn.blocks (splited) (#107) (@mpariente)

Fixed

• [src] Fix docstring after #108 (@mpariente)
• [egs] Replace PITLossWrapper arg mode by pit_from (#103) (@mpariente)
• [src] Return config in DPRNN.get_config() (@mpariente)
• [egs] Fix typo in LibriMix import (@mpariente)
• [egs] Twostep recipe small fixes (#74) (@mpariente)
• [egs] Fixed mode overwriting in all wham recipes (#76) (@Ariel12321)
• [egs] Fixed mode overwriting in ConvTasNet recipe (#75) (@Ariel12321)
• Fix build erros (Pin sphinx < 3.0) (#72) (@mpariente)
• Fixing paths for wham scripts and unziping command for noise (#66) (@etzinis)
• Fix whamr_dataset.py, map reverb to anechoic (@mpariente)
• Important fix : WHAMR tasks include dereverberation ! (@mpariente)

Big thanks to all contributors @popcornell @etzinis @michelolzam @Ariel12321 @faroit @dditter @mdjuamart @sunits 😃

Mainly, this release is to downgrade pytorch-lightning to 0.6.0 as we were having some performance problems with 0.7.1 (#58).
We also incorporate metrics calculation in Asteroid, though pb_bss_eval which is a sub-package of pb_bss available on PyPI.

New

• WHAMR support + and Tasnet recipe (#54)
• Add BatchNorm wrapper that handles 2D, 3D and 4D cases. retrievable from string bN. (#60)
• get_metrics method and strict dependency on pb_bss_eval (#57) (#62)

Bug fixes

• Fix PITLossWrapper usage on GPU (#55)

New features

• Better argparse interface with dictionary.
• STFT is now prefectly invertible with default values. Also perfect_synthesis_window enables perfect synthesis with a large range if windows for even overlaps.
• Encoder and Decoder now support arbitrary number of input dimensions.
• More support for complex numbers (angle, magnitude, interface to numpy and torchaudio)
• Add SingleSrcMultiScaleSpectralLoss from DDSP (magenta)
• Huge improvements on tests and coverage

New recipes

• ConvTasnet full recipe on WHAM
• DPRNN full recipe on WHAM
• Full DNS Challenge (microsoft) baseline.
• Deep clustering and Chimera++ recipe on WSJ0-2mix (ongoing)
• WHAMR dataset support.

Breaking change

• Encoder looses its post_process_inputs and apply_mask methods which were not really useful. We consider it is better the user applies these methods knowingly

Big thanks to the contributors on this release @popcornell @sunits @JorisCos