WebKit

Explore the Schizophrenic model, an Auditory Hallucination Simulation powered by the advanced RVC v2 technology. This unique AI voice model captures the complexity of auditory hallucinations, using sounds from sources such as The Game OFF and Imagine Dragon's 'Bones'. Perfect for creators looking to push boundaries and simulate distinctive audio experiences. Easily generate AI covers or text-to-speech with our powerful, user-friendly tools—no technical expertise required! Delve into the innovative world of AI music creation with us today.

I made the dataset from a YouTube AHS and The Game OFF shh soundtrack that has people speaking over it Dataset (im technically obligated to tell you to not listen to this if you have any mental problems but not like anyone cares): Bones - Imagine Dragons: < as for why its links and if you have any complaints either ask someone to re upload it or just easily open it in drive and if you wanna argue with me dont even bother cause i cant control this Discord CDN is blocked in Iran so i cant send images or Audio (dont you even dare say VPN, just search from:lusbert_ in:verified-chat VPN and read why i cant use VPN)

Schizophrenic model (Auditory Hallucination Simulation)

Schizophrenic model (Auditory Hallucination Simulation) 500 epoch RVC v2

lusbert_

https://www.youtube.com/watch?v=0vvU-Ajwbok

ye hi Ame <:smugai:1138015578238500985> 
its in the thing
this is the Bones by Imagine Dragons
 https://drive.google.com/file/d/1dmuFLuWu8iBRU1Yu-M9t9Ds1Ga2vgDgE/view?usp=sharing
even has those breaths and whispers in it 
obviously not the best but this is a meme model for crying out loud

i need VPN to send to Discord cause the CDN is blocked in iran and i got no VPN so im using google drive

21 epochs on GPT 16 epochs on SoVITS both batch size 3 dataset size 17 minutes and 11 seconds 44kHz ripped from Portal 2

Cave Johnson - JK Simmons | GPT-SoVITS

20 epochs for both GPT and SoVITS batch size 4 for both as well dataset size of 23 Minutes i had 1 hours and 11 minutes but that'd be too large for me sooo also im surprised it did really good with the robotic voice, unlike RVC atleast, i didnt make an RVC model of her myself but all i've heard is that GLaDOS with RVC sucks. but well this one is actually robotic. most likely cause its over trained but it doesnt sound bad from that. so its a win win <

GLaDOS | Portal 2 e20-GPT_e20-SoVITS

TLDR the SoVITS is 15e with GPT being 16e GPT is DPO trained < notes: (for people who wanna learn more stuff about my experience with GPT-SoVITS) dataset size is 21 minutes batch size 2 on GPT and SoVITS SoVITS Learning Rate 0.4 15 epochs sovits took around 40 minutes 16 epochs gpt 27 minutes with DPO saving freq 2 at first i trained GPT to 20 epochs but last epoch saved is e18 prob cause my saving freq was 3 so ye be sure to look out ofr that as well as for SoVITS model it was fine most likely since i trained to 15 epochs and not 20 so prob smth to do with if the modulo of epoch is 0 or not so like [epoch count]mod[saving freq] with mod being % in python so in my case where i trained to 20 epochs with saving freq of 3 20%3 which is 2 aka non 0, so thats BAD :3 so just make sure the mod is always 0 so that you train to the full epoch count i didnt like the model when i first trained without DPO so i retrained GPT model with DPO it also went from using 6GB VRAM to using 8GB this time it took 35 minutes also apparently in SOME cases the default pretrained GPT model is better, often where new words are said or the punctuation is different i'd say? but im not really sure

TF2 Spy | Dennis Bateman_e16-GPT_e15-SoVITS

### this is a re-upload cause *SOMEONE "accidentally"* deleted the <#1175430844685484042> channel < Epochs: 1000 Steps: 15,000 RVC v2 Batch Size 8 Dataset size: 6:27 minutes all infers are transpose 0 since the Announcer has a robotic sound effect you should also apply effects in some DAW like FL Studio

Aperture Labs Announcer - Portal 2, 1000e, 15000s

Aperture Labs Announcer - Portal 2 | RMVPE - v2, 1000e, 15000s

### this is a re-upload cause *SOMEONE "accidentally"* deleted the <#1175430844685484042> channel < Epochs: 2500 Steps: 20,000 RVC v2 Batch Size 16 Dataset size: 3:44 minutes all infers are transpose 0

Schizophrenic model (Auditory Hallucination Simulation)

Description

Samples

Armaan Malik Model

Poppy (Talking Model)

Taro Yamada (Yandere Simulator)

Bad Bunny

Emma (The Promised Neverland) (OLD MODEL)

No.7/SEVEN

Charlie Barley-Female voice changer model - 45 mins of data

Ayano Aishi (Yandere Simulator)

Lia (of ITZY) SOFT Singing model

James Hetfield three models

Kokona Haruka (Yandere Simulator)

tamar braxton "bluebird of happiness" era, (revamped model)

Roblox OOF sound effect model

Zownic the She-hog (SheZow x Sonic hybrid model)

Budo Masuta (Yandere Simulator)

Baldi's Basics models pack 500 - 250 - 200 eprochs

Atif Aslam Model

PomPom Model [My Singing Monsters]

Genka Kunahito (Yandere Simulator)

Ryoba Aishi (Michaela Laws) (Yandere Simulator)

Serj Tankian 4 models

Osana Najimi (Yandere Simulator)

Minnie Mouse DisneyLand Adventures Speaking Model

leomc123 (My own voice as a Ai model) Harverst64

yamu model

Norman (The Promised Neverland) (OLD MODEL)

literally the sound of colossals Model (My singing monsters)

DIO Model (JoJo's Bizarre Adventure Stardust Crusaders)

Higurashi Model Collection (Completed)

AZEALIA BANKS (Rap/Singing Model)

Stoowarb Model (My singing monsters)

Son Chaeyoung Rap Model (From Twice)

J-Ax, 2 models

Carter Pewterschmidt Model (Family Guy)

Andy Gibb (15TH MODEL LFGGGGGG)

Boing Model That Actually Isn't That Good

MLP [My Little Pony] Dragon Lord Ember @ ThunderShy Model

Bells Model Remastered (Macintosh)

Miyuji Shan (Yandere Simulator)

Singer from All The Single Furries, the worst model i've ever made

Teachers (Yandere Simulator)

Yuno Miles

No Text To Speech/NTTS /Kits Model

Suga (From BTS) (Rapping model)

Serj Tankian 4 models

British Toy Chica (Five Nights at Freddy's Shitpost Model)

Info-chan (Yandere Simulator)

Karen Carpenter | (Model + Dataset)

Eazy-E MODEL

TOP ERA/UNTIL I RETURN 1 - NBA YOUNGBOY MODEL