Formed in 2009, the Archive Team (not to be confused with the archive.org Archive-It Team) is a rogue archivist collective dedicated to saving copies of rapidly dying or deleted websites for the sake of history and digital heritage. The group is 100% composed of volunteers and interested parties, and has expanded into a large amount of related projects for saving online and digital history.
mpariente
Follow
Create your own GitHub profile
Sign up for your own profile on GitHub, the best place to host code, manage projects, and build software alongside 50 million developers.
Sign up
Popular repositories
-
-
Forked from lessw2020/Ranger-Deep-Learning-Optimizer
Ranger - a synergistic optimizer using RAdam (Rectified Adam) and LookAhead in one codebase
-
Forked from fgnt/pb_bss
Collection of EM algorithms for blind source separation of audio signals
-
1,294 contributions in the last year
Activity overview
Contributed to
mpariente/asteroid,
mpariente/pytorch_stoi,
asteroid-team/pytorch_stoi
and 5 other
repositories
Contribution activity
November 1, 2020
mpariente has no activity
yet for this period.
October 2020
- mpariente/torch_mir_eval Python
Created a pull request in mpariente/asteroid that received 17 comments
[src&tests] Add sample_rate in `BaseEncoderMaskerDecoder`
We need a way to know what is the sampling rate supported by a model. That's one attempt to do it.
Should we enforce a samle_rate argument in the B…
+60
−21
•
17
comments
- [docs] Fix Reference and Example blocks in docs
- Revert "[install] Pin torchaudio 0.6.0 and torch 1.6.0 (#289)"
- Load models without sample_rate
- [src] Add sample_rate argument to all supported models.
- [src] Automatic resampling in separate.
- [src] Fix LambdaOverlapAdd
- [src&tests] Improve scheduler's docs + add plot method
- Add more shape checks to SDR and MSE losses
- [docs] Fix Reference and Example blocks in docs
- Rewrite forward of BaseEncoderMaskerDecoder to be more readable
- Add jit compatibility
- Make `get_metrics` robust against metrics failures
- [src & tests] Add Hungarian matcher to solve the linear sum assignement in PITLossWrapper
- [src&tests] Improve scheduler's docs + add plot method
- DCUNet and DCCRNet
- Split base model
Created an issue in JuanFMontesinos/torch_mir_eval that received 9 comments
Batch support & Backprop
First thanks a lot for the implementation, that's great ! Is there a plan to support batch computation? This would really be a game changer ! Regar…
9
comments
92
contributions
in private repositories
Oct 14 – Oct 29