- r
Radak
04/30/2023, 11:55 PMCan someone switch Swae Lee over to the rappers category?https://cdn.discordapp.com/attachments/835971020569051216/1102382807025729607/IMG_4189.png▾
- w
Waltman13 (semi-active)
05/02/2023, 9:48 PMthe voice-to-voice section needs to be formatted better for when submitting models - w
Waltman13 (semi-active)
05/02/2023, 9:50 PMhttps://cdn.discordapp.com/attachments/835971020569051216/1103075948380815380/image.png▾
- g
Gabherelol
05/06/2023, 9:01 AMWhen you add a voice actors name to a voice, it will make a dataset of voices voiced by the actor and you can do stuff like predict what this actor could sound like, make a fresh voice they haven't done before just with a name of a character, etc - u
(Dawn) Will Draw Fictional Women
05/06/2023, 9:27 AMnope we cant do voice mixing - u
(Dawn) Will Draw Fictional Women
05/06/2023, 9:27 AMwe’ve tried - u
(Dawn) Will Draw Fictional Women
05/06/2023, 9:28 AMnot with tacotron at least - p
Perilous
05/08/2023, 7:07 PMNvidia Broadcast is the best noise and reverb cancelling I've seen for speech audios. However it's exclusive for nvidia cards that have tensor cores. I'd like to know if someone with good skills would be interested in doing a collab notebook for using the API for cleaning audio files. https://github.com/NVIDIA/MAXINE-AFX-SDK - d
Dyno
05/08/2023, 7:07 PMIf you have trouble using any notebooks, make sure you use the correct notebooks, which are linked in the #notebooks channel, as those notebooks are the most up-to-date ones. - g
Gabherelol
05/09/2023, 11:45 PMWe should add audio examples to SOVITS and RVChttps://cdn.discordapp.com/attachments/835971020569051216/1105641642146414662/17A32A29-87B4-4450-965C-43FEDF1651EA.png▾
- g
Gosmokeless28
05/10/2023, 4:29 AMThat would require some reference audio clips to be used automatically by uberduck. In which case, what reference audio clips should be used? - s
SpamZow (WoomyPearl)
05/11/2023, 11:12 AMUnlimited usage credits for new users once they create and submit a model - s
SpamZow (WoomyPearl)
05/11/2023, 11:12 AMRipped Pants from SpongeBob - s
SpamZow (WoomyPearl)
05/11/2023, 11:13 AM - t
tanooki426
05/11/2023, 7:08 PMSuggestion for contributors: Similar to FakeYou, contributors should be given access to custom Hifigans and be able to preview them with their models - u
(Dawn) Will Draw Fictional Women
05/15/2023, 11:19 AM1. not where you ask for support - u
(Dawn) Will Draw Fictional Women
05/15/2023, 11:20 AM2. pins in #841732367962210344 - h
Heavy and Medic TF2
05/15/2023, 11:33 AMOk - k
Kenny the Teddiursa
05/15/2023, 10:36 PMWhat if it made a actual voices like 15.ai and 11.ai? - g
Gosmokeless28
05/15/2023, 10:40 PMWhat do you mean by that? - k
Kenny the Teddiursa
05/15/2023, 10:40 PMWell, maybe it doesn't have strokes this time. - y
YTR76
05/22/2023, 2:15 AMCan y'all add VITS? We have sovits, but not the normal tts vits. cause justinjohn has this https://github.com/justinjohn0306/VITS-fast-fine-tuning - u
(Dawn) Will Draw Fictional Women
05/22/2023, 3:33 AMwe tried didnt work - u
(Dawn) Will Draw Fictional Women
05/22/2023, 3:34 AMno one could train a good model on it anyway - y
YTR76
05/22/2023, 3:56 AMok - r
Radak
05/28/2023, 1:46 AMCan someone fix this when ever I try to use the xxxtentacion ai on voice to voice it’s just keeps going to grimes and for some reason there’s two xxxtentacion ai models on voice to voice and neither of them work see - g
Gosmokeless28
05/28/2023, 2:14 AMMaybe one of them has the same bot command as another one - g
Gosmokeless28
05/28/2023, 2:16 AM@Radak What's the name of the XXXTentacion voice model you're trying to use? - r
Radak
05/28/2023, 3:06 AMIt’s the default sovits voice to voice one the aggressive one is only on text to speech but the aggressive XXXTENTACION model still works on tts - r
Radak
05/28/2023, 3:14 AMFor a person named jumpy chamber, made the aggressive X model for voice to voice