Description
NOT MINE Dataset and Trained By <
Comments
Sample:
damn that 808 so fucking strong
quality is ass so i might redo it but ts my first model
use adobe podcast to remove the hissing and noise
I await that brother. I promoted you to Model Maker status today.
ive actually made one other model since and finishing another rn
the main problem is the dataset quality i think so i have to get that figured out
dm me dataset
alright
For dataset run UVR over your dataset twice and then EQ it with FL Studio
alright
thanks for the advice
what would the recommended epochs for a 15 minute dataset be?
1000
most of my datasets are 10 minutes to 11
and i always train to 1k
how long does that usually take you?
i recommend training models right before you go to sleep
allows me to train 2-4 a day
or right before you leave the house
alright ill keep that in mind
ive been training to 200-400 usually
and my results are pretty decent
waste of training tbh
just train to 1k
its always worth the wait
Add a comment
Samples
1. Singing
Male
English
2. Singing
Female
English
3. Singing (Dry)
Female
English
4. Singing (High)
Female
English
5. Singing 2
Male
English
6. Singing (Dry)
Male
English
7. Singing (Dry, High)
Male
English
Pitch
Weekly Metrics
Users also tried
More to explore
Loading more