Description
Hey I made my first model, and it turned out great imo. But with big help from Trained on an unintentionally large dataset, around 50 minutes of voice-lines from the game.
Comments
Nah, this is undertrained still. <:skullsob:1093200088261734420>
Nah. Sounds just like her.
Sample files aren't working for me so I'm gunna reup
Well, you're right but 80 Epochs aren't enough for a big dataset like the one you used for this Loba model.
Was more than enough actually it's definitely a little overtrained but thanks for your input
My Canserbero model with 25 mins of Dataset took 480 Epochs to train properly avoiding overtrain.
Bro make your own get outta here
I heard you
🤨
No static +sounds like her You don't need hundreds of epochs for a good model.
Add a comment
Samples
Pitch
More to explore
Saiba Momoi (Blue Archive)

Ariana Grande AI

JENNIE of BLACKPINK [Strong Ver.]

Saiba Momoi (Blue Archive) (VA: Tokui Sora)

Hatsune Miku
SpongeBob SquarePants (Talking And Singing)
Takanashi Hoshino (from Blue Archive)

Satoru Gojo (JJK) [VA Yuichi Nakamura]

ENHYPEN Heeseung

Sunaokami Shiroko (Blue Archive)

Villager (Minecraft)

Mortis [Brawl stars]
Jungkook (BTS)

Tendou Arisu (Blue Archive)

Kanye West
Loading more