-
Dear pyannote.audio contributors (@yinruiqing @pkorshunov @V-assim @Mymoza @GregGovit @hadware @diego-fustes @MarvinLvn),
I am planning to write a paper describing `pyannote.audio` and submit it to…
-
**Submitting author:** @ynop (Matthias Büchi)
**Repository:** https://github.com/ynop/audiomate
**Version:** v5.2.0
**Editor:** @terrytangyuan
**Reviewers:** @mulhod , @faroit
**Managing EiC:** Lore…
-
**Submitting author:** @romi1502 (Romain Hennequin)
**Repository:** https://github.com/deezer/spleeter
**Version:** v1.4.9
**Editor:** @terrytangyuan
**Reviewers:** @bmcfee , @faroit
**Managing EiC:…
-
Should ``predict(...)`` be consistent with hat x in Eq. (2) of [GAIN](https://www.biorxiv.org/content/10.1101/2020.06.09.141689v1) and ```x_gen_ = x_ + x_gen * (1 - mask)``` in ```train_disc(...)```?…
-
I am trying to train the VAD module on my own data. For starters, I only have one annotated utterance of about 10 minutes total duration. I cut down the number of nodes to [4,4] before labeling by han…