hey | AI HUB | Page 1

crimson wharf Jan 17, 2024, 10:01 AM

#

how many and how long each wav file of vocal should be long for making custom model

terse crane Jan 17, 2024, 10:05 AM

#

Above 5 mins is enough, though you can try and get to 30-45mins dataset. You can just stack the voicelines in one file and it trains just fine

#

you may consult

#

-audio

sturdy runeBOT Jan 17, 2024, 10:05 AM

#

📚 Audio Guides

Perfecting Audio Isolation on Low-End Rigs: A Practical Guide, by Litsa The Dancer and Faze Masta Google Docs
Gathering and Isolating Audio, by SCRFilms Google Docs
How to make a good model All-In-One guide, by LUSBERT Rentry
Creating Datasets for RVC using iZotope RX, by LUSBERT Rentry
Vocal Mixing Tutorial, by Roomie YouTube

🛠️ Tools

crimson wharf Jan 17, 2024, 10:08 AM

#

thx

crimson wharf Jan 17, 2024, 11:08 AM

#

10-20 sec vids each for 10 min is ok?

#

or it need be same lenght each vid

muted lotusBOT Jan 17, 2024, 11:19 AM

#

Ayo? @crimson wharf level 3 !!! lfg

crimson wharf Jan 17, 2024, 11:19 AM

#

btw this is from 2 different song same person it sound diff is that ok?

terse crane Jan 17, 2024, 11:27 AM

#

Hmm, I think it should be fine, though you should denoise more via the Karaoke models, noise gate, cut out the noisy parts with tools like Audacity

#hey