Pariente Manuel
Pariente Manuel
Tests are taking a while longer than before. I just remove some combinations and reduce dimensions
The Mock object shouldn't be there.. [RTD](https://asteroid.readthedocs.io/en/v0.4.5/package_reference/dsp.html)  [Latest](https://asteroid-team.github.io/asteroid/package_reference/dsp.html) 
Samu (@popcornell) has been trying to replicate the results in the paper for a little while now, but couldn't get close to it. There might be some things that we...
## 🚀 Feature Include version compat tests for pretrained models (models from asteroid 0.3.0 still work as expected in 0.3.3). ### Motivation We can break things between versions and still...
For multi-GPU training, users might use `DataParallel` and `DistributedDataParallel`. And the augmentations should probably follow that as well, to avoid copying parameters from one device to another (and loosing more...
Hi, thanks for the implementation ! Are you considering writing a unit test again `sklearn`'s Kmeans?
Hi, thanks a bunch for this tool ! When working with speech mixtures, WER can take into account that words from each speaker might be picked up. There is a...
Hi @tky823, nice repo ! We'd welcome most of this code in Asteroid if you'd like to contribute :smiley: Would you? Cheers,
Might be much faster (and more precise) for longer FFT kernels. See [here](https://github.com/fkodom/fft-conv-pytorch).