#🧬│ai-chat
1 messages · Page 172 of 1
Sooner or later ppl are gonna be using ciphers in the code or whatever
what do i do then
colab doesnt work and the other spaces that dont use colab take incredibly long to convert
im struggling here xd
Colab is busted now?
colab hasnt worked for me in a long time
Ayo? @dull timber level 2 !!! 
i was already kinda losing interest though so i didnt care that much then
png image of luigi screaming with the half life scream
@orchid sluice i forgor the command to the download
boush
@fathom crane tutorial for getting one https://youtu.be/xvFZjo5PgG0?si=90f1391s72CU7Y65
;.
nah its a rickroll link
i got rick rolled
.
its real
who
pill
Zard
hey guyssss if anyone used applio rvc v3 yet can you please let me know if there is AUTOMATIC Over Training Detection?
⠀
Settings for Nvidia GPUs 
F0 Det.: rmvpe (suggested for all series)
RTX 40-series: 80-96 chunk | +16384 extra
RTX 30-series: 96-112 chunk | +16384 extra
RTX 20-series: 112-128 chunk | +16384 extra
GTX 16-series: 128-192 chunk | +8192 extra
GTX 10-series: 128-192 chunk | +8192 extra
Advanced Settings
Protocol : Sio or Rest
Crossfade: 4096 start 0.2 end 0.8
Trancate: 300
Silencefront: Off
Protect: 0.5
RVC Quality: Low
⠀
⠀
Settings for AMD GPUs 
Don't forget that your models needs to be converted in ONNX!
F0 Det.: rmvpe_onnx (suggested for all series)
7xxx XT cards: 112-128 chunk | +16384 extra
6xxx XT cards: 128-192 chunk | +16384 extra
5xxx XT cards: 192-256 chunk | +8192 extra
RX 580: 192-256 chunk | +8192 extra
RX 570: 192-256 chunk | +8192 extra
RX 560: 256-384 chunk | +8192 extra
Advanced Settings
Protocol : Sio or Rest
Crossfade: 4096 start 0.2 end 0.8
Trancate: 300
Silencefront: Off
Protect: 0.5
RVC Quality: Low
⠀
⠀
Download for Nvidia GPUs 
Version 17b cuda
Download for AMD GPUs 
Version 17b directml
Download for Intel GPUs 
Version 17b directml
Download for Mac 
Version 17b Mac
⠀
@fleet ingot 
@lethal swan 
I need a Rick Astley voice model
-colab rvc
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HFv2, by r3gm Huggingface Spaces
- AICoverGen, by r3gm Huggingface Spaces
- Advanced RVC Inference, by r3gm Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
Ayo? @surreal ice level 1 !!! 
Halo, how can i make my own model, maybe some tutorial?
why isnt my virtual audio cable working
What do you use the voice models with? I saw some guy using it on YouTube and it has 0 delay?
tkinter
all u guys are in the wrong channel
Ayo? @scenic condor level 1 !!! 
do you guys know how to fix the problem where start_http instantly closes after opening
hello Everyone, I’m melodysongz. music producer artist manager, pleasehow can i get "burna boy" or Wizkid Model link
hello
what kind of help
hey
im jut getting started so can i just ask how do i use these voice models?
You download a voice changer (okada for example)
after that you get a .pth file and a index file
insert them into okada and boom
thanks g
hi
hi
⠀
Settings for Nvidia GPUs 
F0 Det.: rmvpe (suggested for all series)
RTX 40-series: 80-96 chunk | +16384 extra
RTX 30-series: 96-112 chunk | +16384 extra
RTX 20-series: 112-128 chunk | +16384 extra
GTX 16-series: 128-192 chunk | +8192 extra
GTX 10-series: 128-192 chunk | +8192 extra
Advanced Settings
Protocol : Sio or Rest
Crossfade: 4096 start 0.2 end 0.8
Trancate: 300
Silencefront: Off
Protect: 0.5
RVC Quality: Low
⠀
Ayo? @vernal bronze level 1 !!! 
just press the huggingface link to download the model and use it to your liking
its a zip
windows has a built-in extract thing
personally i prefer 7zip
is there no dark mode for Applio 🥹
yes htere is its literally on by default usually??
background fill color is set to white

Is your system light mode?
nope, dark
😀
i just wanted a mr saleh ai cover of him singing smells like teen spirit 
oops, dont refresh website when training or it dies
i like shit in the Hospital)))))))))
REAL
it doesnt
its still training it jsut doesnt show it anymroe
ye
me waiting for a response :
ye, what do you want to do? voice changer? make cover?
cover
Ayo? @vernal bronze level 2 !!! 
you can use covergen both local and online or any rvc gui stuff local
wha
do you have a gpu?
whats that
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HFv2, by r3gm Huggingface Spaces
- AICoverGen, by r3gm Huggingface Spaces
- Advanced RVC Inference, by r3gm Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
could someone herlp me in help chat? somehow that message appears on my colab. (the one i send)
use either one ofthe first 3 link
screenshot and which colab
uh check help chat
-colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HFv2, by r3gm Huggingface Spaces
- AICoverGen, by r3gm Huggingface Spaces
- Advanced RVC Inference, by r3gm Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces

Can someone explain why it taking so long to go to AIcover gen from colab
:<
can you share the colab link with applio's fixed version? 🫶🏻
good or bad idea? https://www.youtube.com/watch?v=reRWoosVKNc
Ayo? @devout hill level 1 !!! 
needs to install an older version of the thing it needs that colab updated
theres a way to make it faster by following the tutorial on the first cell
hey
Where's the tutorial
Ayo? @elder willow level 4 !!! 
Holy actual Guacomole
wait what does fallback enabled do again?
no need to install cuda 11
did they update onnxruntime?
uses the previous version of colab before they updated it
lets just say its a time machine :D
im fr thinking this is the crappest idea i made lol
Hello guy 🙂 I can't find the voice model of Squeezie (French Youtuber)
@elder willow hi 
Hello

Use the Colab in #🔍│help-w-okada pins
how do i make a voice changer
like a model
does anybody else get a RuntimeError: Event loop is closed while using Applio's tts?
it works, but that exception gets thrown every time (edit: nvm it fixed itself)
Hey hey! Fancy seeing you here!
yes
i provided massive datasets for all of the nekopara models that are listed lol
Something of a legend around here, eh?
Does anyone know a good way to get an LLM to write YouTube scripts without sounding like GPT?
no fucking way @indigo leaf
Ayo? @elder willow level 1 !!! 
ok i give up on the mr saleh ai cover 
Was he trying to do the same thing or something
Applio Precompiled is perfect for those who are too lazy to install all the dependencies at once.
well at least this time it'll work for people who want to make funny ai cover
wat
not kits 😭
YES
fucking kits 
how come RVC voice changers dont work for me? do i need to install something
doesnt work in what way
have you tried custom models?
nah idk how to get those to work
Ayo? @elder willow level 1 !!! 
im tryna figure it out rn actually 😭
i downloaded one, but idk how to acc get it on the app
extract the zip
on the app theres a edit button on the blue bar
then i click upload on a blank one right?
press then then press upload on any of the slots then on the model you put the pth file and index is the index file
alr, i use rvc right?
yes
why not kits
i got it in but it doesnt work
ye goodluck using voice changer on kits
no RVC's work for me, not even defaults
what voice changer
its bad and mostly paid
w-okada
ok
goodluck downlaoding your models from kits

do u know how to fix RVC voice changers not working?
hmm maybe you downloaded the wrong version?
i'm not advanced like all of y'all
Cute
the wrong version of W-okada?
try in #🔍│help-w-okada ig
ye theres different versions for different gpus
i didnt know that, i downloaded this
MMVCServerSIO_win_onnxgpu-cuda_v.1.5.3.17b
I'm in wrong generation 😭
whats your gpu?
3070
@forest quarryhalp
im mod for what its worth but i fell off
i was bigger back in like september idk

i like finding server mutuals in here though cuz its funny
from nce chud to ai hub chad
we dont have any
f
I still have them
yo
who has kero voice
kero voice https://www.youtube.com/watch?v=3kC0oabET30
how to get pls pls how to get
who has kussia voice?
how to use the model?
Hi all! I'm using a ready-made voice model from weights.gg via Mangio-RVC, but I get consistently bad results. Does anyone have any information about the best recommendations for improving the quality of the cover?
M? Change Tone of Voice?
mm
I changed the transpose settings but also got a bad result with lots of artifacts(
May I know Which Voice and Which Song?
Send me a DM
I use the voice of Russian singer Viktor Tsoi, I tried many songs in Russian, but never got a good result. link to the voice: https://www.weights.gg/en/models/clqe53agh002lc2xaqvu1j7h6
Ayo? @dapper goblet level 1 !!! 
Which song?
any Russian song) I haven't achieved results on any of them((
yo
@dapper goblet Проверь ЛС!
who knows if there is a similar community with useful links, guides, dipfakes bases?)
I'm not sure but I can teach you if necessary
-colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HFv2, by r3gm Huggingface Spaces
- AICoverGen, by r3gm Huggingface Spaces
- Advanced RVC Inference, by r3gm Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
Ayo? @elder willow level 1 !!! 
can someone help getting that voice model
Hi there
hii
hi 😉
Shi I wasn't active here for a long time
Is google colab still blocking everything related to rvc?
Well, after the September 8th bans, there hasn't been many other bans
So the colabs we list here are working, afaik
They block anything with a WebUI (e.g, Stable Diffusion)
Yes I mean it
that does still work
yo does anyone know a realistic female voice in here and that give me the name? i want to troll someone that is really annoying
Ayo? @left path level 1 !!! 
Searching for the perfect RVC e-girl voice model? 
Ain't no way this is real
if u only knew the amount of requests we get on the daily..
Why do people request this in a first place💀
Ayo? @uneven beacon level 2 !!! 
yes it is
any pop singers here
Okay this is actually mad funny
just as much as this is https://www.youtube.com/watch?v=xvFZjo5PgG0
they wanna be e-kittens
maybe even ask for money to desperate men
welcome to the internet
Can't you just take random female voice and toggle pitch on it?
Searching for the perfect RVC e-girl voice model? 
Okay what the flip
Idk if you can do it in real time voice changers but it seems easier to me than asking an e-girl model lmao
Yes you can toggle pitch with the "Tune" option in W-Okada
Does anyone know any good Angel Dust voice models I'm female and some of the Angel Dust voice models don't sound good with my voice?
Wicked I’m a ♥️♣️♦️
CREDITS
Music/Lyrics: ASTEROID (KIRA, monii, Johnny R)
Illust: Isamu
Movie: HISSYA / OKIKU
Special Thanks: Sena
SPOTIFY: https://open.spotify.com/album/65LLOqvUeS8QZC54G9vlqQ?si=tW5KOEjaRT2SGQVw8mHaRw
APPLE MUSIC: https://music.apple.com/de/album/wildcard-ep/1713029...
ez
?
?
HIStory era moment
hi
hai
hi
hai
rca?
all good already answered in #✨│ai-help
hi
Hello, why is the output of the models jerky?
Because most models go out of my way jerky and I think it's a shame.
btw does internet connect play a part in the voice changer?
Ayo? @elder willow level 2 !!! 
if you are running it locally then no
i have a decent PC and it sounds horrible 😭
my internet isnt very good so i thought thats the issue
it could just be the model
maybe, the default ones sound bot too
i hear like a little creepy mumbling noise 😭 like whispers
Models are interlingual or multilingual ?
Hello guys!
How fix that error in AI Voice Changer?
[Voice Changer] Waiting generate pipeline...
[Voice Changer] Pipeline is not initialized.
Just wait no ?
they can be multilingual but the accent won't sound great
I wait 20 minutes
Did you restart it?
Ayo? @worthy plinth level 2 !!! 
English model in French would work?
delete pretrain and model_dir folders n restart W-Okada
would sound kinda weird if you keep index
But what is the difference between the index and the weight file?
yes it works
with or without the index?
index is basically all the mannerisms of a person (accent, how they say certain phonemes, etc) into one file that can modify outputs.
the .pth is basically the voice itself
it'll sound weird with the index, probably
I haven't tried live voice changing so I don't know
But then you don't recognize the person anymore.
without the index
that depends if you have a similar accent or not
the closer your accent is the better the model will sound generally
nuh uh
you do lol
its still their voice
just without accent
ok but laughter isn't weird with the models?
Yo does anyone know why it doesnt give out anything in the output of training your model even do i did it the right way
it will most likely sounds weird
on most models cough and laughter sounds weird
I would like to try a model in a Valorant game but I don't want to get caught. Is this possible?
just dont laugh...
ok x)
or ig if your laugh is like "hahha" it should be fine
but if its a giggle kind of laugh it will probably break
do you know any good stable and multilingual models for testing?
nah
Can 4 gigs of vram survive rvc? 💀
hello! Are there any basic fine-tuning models to avoid the 2-hour wait?
2 hour wait?
What is bro using 
hi guys i'm trying to clone my own voice to an RVC model, is there anything specific i need to do? i mean if i create multiple audio files can i make those last like 1 hour or i need to divide those files for example in 1 minutes per audio files?, also do you suggest to record voice while reading something specific or trying to sing in order to register different tones, both high and lows?
No you don’t have to do that
Highs and lows yes
you just gotta record anything (make sure those have a lot of variations, in pitch especially), for like 15-30 mins
Singing and talking
then ur gonna do the basics in audacity (noise gate, trim silences)
google collab with a lot of epoch
Ayo? @worthy plinth level 3 !!! 
and u got your dataset
alright , thank you guys 😄
Use less epochs
I use a minimum of 800 epoch, otherwise the quality sucks, doesn't it?
but are there any fine-turning models?
More epochs does not mean better
There’s a big possibility it’s going to overtrain
yes, because it can overlearn, but with a large dataset you need a lot of time.
How long is it
I just plop in 300 and see what it spits out
(big Maybe on that one)
And change if it’s undertrained or overtrained if it is
(Also, true)
I've got one of 8 minutes but I usually aim for 1-2 hour.
Go for 500 🔥
Yeah u should go for 500 and check the graphs
This for every model imo
But, keep in mind, 1 hour datasets arent really worth it
Unless person has sooooo many variations
can we get a summary like with tensorflow dashboard?
-overtrain
All-In-One Guide on how to make a good model
This guide explains how the D and G files works and much more: https://rentry.org/RVC_making-models
Credits: LUSBERT 
Automated Overtraining Detection (AOD)
Will be available soon in #1159513888199540817
Credits: grvyscale
^^^
Nice. I'll have a look . ty ^^
can we make a model that manages laughter?
hi
hi
When ai can write text in photos efficiently 
x) never ok
Maybe... I'm not entirely sure
what graphics card would be needed to drive the model quickly at home?
Infer or train
Infer ?
Make cover
A100 is the best GPU for training
It’s just that no one can afford it

20 280 euro x)
hellooo
hi
can you give me the link to train the model (I've lost it) please
Colab?
yes
-colab
Suggestions for @worthy plinth
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HFv2, by r3gm Huggingface Spaces
- AICoverGen, by r3gm Huggingface Spaces
- Advanced RVC Inference, by r3gm Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
which one is it ? 1,2,3,4 or 5 x) ?
Hey I am completely fresh to this. How would I go about training my own voice model for free? I’ve tried following some tutorials online but run into error sof not receiving a url back
Hello Im fresh here
Online or locally?
RVC Disconnected
is applio v3 worth it to switch from v2 or should I wait until its more stable
ok ty
Ayo? @worthy plinth level 4 !!! 
Anime women aren't real
slide good voices
I'd suggest waiting
thanks
bro the audio sample looks trash 💀
Ayo? @elder willow level 1 !!! 
Online but not opposed locally if it’s straightforward
Both can be not straightforward at times
What’s your GPU
So I can see if you have the requirements for local training
(╯°□°)╯︵ ┻━┻
why is bro appling
apple 🍎
understandable
Yo where is the Joe Biden voice model
for you 🙏
Theres no Joe in #1175430844685484042
check https://weights.gg/
Alright thanks
3060 Laptop GPU
Ayo? @vale star level 1 !!! 
Can Anyone Tell Me The Best ai Song Cover Website
And Ai Voice Cloning?
Feel free to support me on Ko-fi: https://ko-fi.com/adamedmond
Uploading this first because DEATH cover got blocked many times, probably because of the music video thing so I'm doing the plan B video right now 👍
SVP distributed as well if anyone would like to try it out with other voicebank! Feel free to use it and don't forget to give credit w...
2nd most popular right now
Do You Know Any Ai Cover Song Voice Cloning Website?
RVC
I Use Mobile I Dont Have Pc?
Should be enough for local training
Do you need to make a cover or train a model
Would it be wrong to think we need an Idris Elba RVC AI somewhere on fakeyou.com?
Ok is it me or why has no one made a topaz enhancer online ??
Ayo? @versed salmon level 1 !!! 
falcons to win the super bowl
-colab
Suggestions for @terse goblet
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HFv2, by r3gm Huggingface Spaces
- AICoverGen, by r3gm Huggingface Spaces
- Advanced RVC Inference, by r3gm Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
hi how can i use voice models?
depends what you want to do with the voice model, live voice changing, ai cover of a song etc?
-local
- Applio-RVC-Fork, by IA Hispano GitHub
- Mangio-RVC-Fork, by Mangio621 Huggingface
- RVC Studio, by SayanoAI Huggingface
- AICoverGen, by SociallyIneptWeeb GitHub
- Replay, by Replay Team Website
- Original RVC, by the RVC-Project team GitHub
You can find more info on the #1159513888199540817 channel. If you can't find your answer, feel free to ask for help in #✨│ai-help. Credits to Faze Masta and Antasma for compiling these links.
For real-time or ai cover
live voice changing like changing my voice during a game to troll my friend
-realtime
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
First one
anyone have a backup of the robert plant model?
Check weights.gg
i did, the link is dead
there isnt a file with this name in okada
start_http.bat
Ayo? @lapis junco level 1 !!! 
Aight fuck it idk where else to put this, saw a sticker that was like "Don't fuck with ilaria" and I used to have some theme with that name on it, wondered if it still existed anywhere because I can't find it for shit
Also who tf is ilaria
what is there then
Nuh uh
Admin
start2.sh
start_docker.sh
start_v0.1.sh
something like this
oh you downloaded the mac version
-_-
sorry its not there, i found it listed somewhere but the google link was dead
Ayo? @meager bolt level 1 !!! 
Send a screenshot in DMs
read the guide: https://rentry.co/VoiceChangerGuide
This guide is back to receiving regular updates, however do not ping me for anything on it. The guide itself speaks for me. - Blanc
Other Links
Antasma's Local Error Fixes
Antasma's Colab guide
Sushi's useful Links - You need to follow this if you are on an AMD or INTEL ARC graphics card
Frequent...
where is the windows version?
the guide i just sent has download links for ur GPU
and, yes, for the windows versions
ok
is there a place to get the models that have been removed??
If the models removed it’s for a reason
i hear you, but i wonder if there is a place where these models reside???
The creators hard drive
Hello
sa
lol true
hey guys, ima be real i am clueless about all this, but im tryna make my voice sing songs, so like instead of The Weeknd singing “Save Your Tears” itd be my voice, this is possible right?
Yeah
If you make your own model yeah
Is there a guide to do this or a video cause ive hunted but the only one I found was out of date lol
-rvc
Full AI Voice Model Training Guide (Local)
Link: YouTube
Credits: Christopher Villanueva
Model training with Mainline RVC
Link: Rentry
credits: Raven (ravencutie21)
AICoverGen Colab Guide
Link: Google Docs
Credits: Eddy (Spanish Helper)
Create a model with RVC disconnected (colab)
Link: Google Docs
Credits: Angetyde
How To Make an AI Cover With Ilaria RVC
Link: Rentry
Credits: 👽 Julia (ailen2091)
^^^
I'd recommend trying the Colab model creation methods firs tho
If your PC is good you can do the local methods
what does RVC stand for? see it alot but never know the abbreviation
Retrieval-based Voice Conversion
sa
Ah thank you, so you recommend me creating my voice into a model, right?
Retrieval based Voice Conversion
Yeah
If you wanna make your voice sing songs, yes
I aint gonna lie this server is becoming wierd
it brought good voices but recently i'm just seeing anime voices everywhere xD
now if these people are getting paid then that is fair but i want some variety lol
What’s the best ai voice changer to use?
its just their choices lol
you can wait to see variety
Realtime or covers
Thx
No I’m saying do you want a voice changed for covers or realtime
fair enough!
Real-time
-realtime
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
Read the first one
that's what model makers care about ig
are we allowed to talk about any ai or just voice based ones?
Like??
like ai such as stable diffion or chatgpt? and such things.
For ChatGPT you can it just that your going to get punched for it
then i wont do it, i dont want to get punched.

anyways i just made a post in help-sd so hopefully i get a response, also how is everyone doing today?
pretty good ig
Alright, would it be “Create a model RVC disconnected (colab)”?
Ayo? @steady rain level 1 !!! 
Yeah, that would be a good one
-audios
woops
-audio
- 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
Youtube Downloaders
Audio Separation/Isolation
Appreciate this! Super clueless and interested to learn about it all :)
Some good dataset tutorials, mainly for audio isolation if needed
sometimes i hate only having 2ram graphics card.
You're welcome :)
Let me know if any errors occur in #✨│ai-help, will try to help ASAP
I have Intel HD Graphics 4000
is that good or bad? sorry im a noob with computers parts.
...it's integrated graphics
from 2012
yeh lol
you have an i3?
Ayo? @elder willow level 4 !!! 
i have a i3, 16 ram and 2vram.
kobold lite in terms of ai also it take sd on low setting 5 mins to generate 1 image.
nah i7 3rd gen
guys how can i find my RVCversion
i mean rvc v2 or rvc v1
whats ur zip file name
people tell me around 5 minuets for 1 image is terrible.
hi chat
MMVCServerSIO_win_onnxdirectML-cuda_v.1.5.3.17b.zip
welcome to the internet.
is there a reason why from epoch 82 to reach another epoch it takes a lot more than before? i'm on a 3080ti , trying to train on 300 epochs, 20 batch, saving every 25 epoch, now it takes like 10 minutes to do one epoch
it is very bad
what dimensions are you generating?
MMVCServerSIO_win_onnxdirectML-cuda_v.1.5.3.17b.zip
usally 512 x 512 and i usally use sd 1.5 models...
do you upscale?
no i have diffrent upscaler that is way faster and lightweight than sd.
ur probably using v2 then
v2
thanks ❤️
Ayo? @narrow pawn level 1 !!! 
i mean tbh not all people have good hardware
I know, but 5 minutes is bad compared to what you could get with 8gb vram
just like me
i literally take like 10-20 minutes to generate a single 512x768 image and upscale it via a 4x model on cpu
i use comfyui btw
Have you heard of lcm? also turn of real time generation preview thingy.
10-20 minutes on comfy?? damn
i cant stand comfy
yes i used that its very finnicky and hard to get good images on
on cpu
fair enough
i love comfyui a1111 sucks ass and is buggy
also fair
If I started before the v2 update, do I resume training in R02?
i plan on trying invoke ai.
also i get the same performance on cpu with comfyui and the directml fork of a1111
(i have an amd igpu)
that is interesting to say.
comfyui is just nicer to use to me imo
I tried using comfy but couldn't get it working so I am an auto1111 fanboy now lol
lemme show off my workflow rq
actually i downloaded few of RVC V2 female models but they have a long delay
can u recommend me some model with lower delay ( like the first default model )
do you have an amd gpu by any chance
delay is not dependent by model
it is dependent by ur settings and gpu
i think they might have amd since the default models are onnx by default
yes i have amd
So i should find onnx models?
-realtime
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
im not the best one to ask for realtime tbh
im more knowledgeable in rvc (AI covers) and that
you can use this dropdown
hey tbh i have basically no understanding about ai but i was hoping you guys could help me
basically my father passed away a long time ago and i got basically just 1 audio of his voice and i was wondering if there is a ai tool that could copy his voice good even with just 1 audio thx in advance
pls help
basically, pretrains help your model be trained. a good pretrain means models will be pretty good
i use "original" but what is difference with other ??
you could use elevenlabs for that
ov2 basically has better results in less epochs, but overtrains earlier.
600 is "less epochs" ?
Ayo? @hardy rapids level 5 !!! 
yaaaah purple !!
@feral halo
the new pretrains made by the community
yeah and ?
ov2 has faster training, but also overtrains earlier and can cause some issues according to some people
rin_e3 is basically "rvc v3" pretrains now
havent tested rin-e3 have u?
noooonono
you gotta get model maker
ok ok
it's like, what they imagine it could be basically
-upload
English guide
Link: https://rentry.org/fdg_guide_newer
Credits: FDG
Spanish Guide
Link: https://rentry.org/AI_Hub_guide_esp
Credits: Julia (ailen2091)
Hindi guide
Link: https://rentry.org/AI_hub_guide_hi
Credits: Enes
Turkish guide
Link: https://rentry.org/AI_hub_guide_tr
Credits: Enes
how ?
i'm french xD
submit in #1159514067187277865
look at guide above
and after i can get role and post in #1175430844685484042
after you get model maker you can post models yes
gn 
that looks semi-complex
i have no words becasue idk what to say.
looks good
one thing I couldn't do is load loras
thats the main reason I gave up
i have custom nodes to load stacks
but afaik you can do it with stock ones too
you ltierally just load like this
the tutorial u sent was very clear and i found the answer in under 1 min
thank u very much ❤️
comfy ui looks alot like unreal engine
or blender
I need to try again
its just working great
I couldn't find a good workflow online so Ill have to make my own
i like nodes because it involves doing logic stuff!!! and i like that !!
im simple person and i want simple things.
no worries bro
im gonna install invoke to try something new.
ive used it for so long Its all I know
on comfyui since i musing cpu i have access to all 16 gigs of ram
instead of only the 2 gb my igpu allocates to itself
hola
banjo
halo!
how to run?
Is the chat alive
Is it
hi
ai models
What’s a model
Is the index required for training?
you get index if you train it its the accent of the model and its not required for inference
And how can I calculate the number of epochs to do the training? (Before you start)
ppl are so soft these days lmao
deepfaked images of people is not that deep lmao
you cant really calculate it before it starts you gotta use tensorboard
But we can “train” the index, what is that anyway?
index is the accents
I understood that it was with overtraining but for me the value remains "constant", I have no overtraining or "decrease"
And can I post a French model?
what are you using to train
you gotta submit a model in #1159514067187277865 and if you get accepted you get the model maker role and you can post
How so ? I use the colab version
did you click refresh top right on tensorboard?
Ik
Yeah
At the beginning it's a big descent and everything else is stagnant
when it starts going back up
Afterwards I hope it's normal because I'm 50 epochs from the end
-overtrain
All-In-One Guide on how to make a good model
This guide explains how the D and G files works and much more: https://rentry.org/RVC_making-models
Credits: LUSBERT 
Automated Overtraining Detection (AOD)
Will be available soon in #1159513888199540817
Credits: grvyscale
What IS it?
only for realtime i think
RIN_E3 what is it?
new community made pretrain
can you explain to me what is the differences with the original prtrained models.
like what exactly is it used for?
and is it better to use?
it may be better for english voices as thats what it was trained on
yeah
Ayo? @hearty vault level 1 !!! 
im clinically insane
so for instance is it good for talking, rapping? ect.. like i have used rmvpe. its basicly another model like rmvpe is?
hello , how do I download a link to the voice model after searching voice models
rmvpe is pitch extraction
pretrain is like what the model trains itself using
you can use #1175430844685484042 or weights.gg
yes Ive found the voice model I want in search models but cant find it in voice models to get the link
Ayo? @toxic pollen level 1 !!! 
when you click on the link it should download
TRYOUT
can you show me the model?
Ive just been using the colab.research is that the best way
I figured it out I just need to use the link that it brings me to
hi
Hey!!
hai
where are the ai pics?
yo
hello
my voice changer sounds ass
😡
frasier moment
it was always used on fraiser but now its only used on me 
hi
hai
Hi, I was wondering if someone could give me a fast DIY on how I can teach my own voice to make it a model :3
hhola
uhhhh from personal experience, make sure you're actually shouting for when it comes to some audio ques
if you're very soft-spoken then it won't be good for songs with shouting vocals
Full AI Voice Model Training Guide (Local)
Link: YouTube
Credits: Christopher Villanueva
Model training with Mainline RVC
Link: Rentry
credits: Raven (ravencutie21)
AICoverGen Colab Guide
Link: Google Docs
Credits: Eddy (Spanish Helper)
Create a model with RVC disconnected (colab)
Link: Google Docs
Credits: Angetyde
How To Make an AI Cover With Ilaria RVC
Link: Rentry
Credits: 👽 Julia (ailen2091)
I mean like the pure basics to it, where do I start, how do I train one hehe... sorry
start with rvc disconnected
it might seem hard at first but it’s very easy to learn
Trying to set that up now but I'm lost at the part where it asks me to do smth with a zipfile in my google drive
Ayo? @wanton brook level 1 !!! 
ppl are soft these days
@elder willow could u vc perhaps so I can stream mybe
Ayo? @cedar glade level 1 !!! 

sorry man i have to go to sleep soon, plus i’m uncomfortable with using my voice
No worries
Right now the zipfile is not in the folder in my drive... (Exception: I can't find dataset in /content/drive/MyDrive/rvcDisconnected.)
Idk how to really add that stuff back
Thought it was easy 😭
i’m just an amateur
Experts rise! <3
server a bit too quiet rn
dead caht
why
😡
hello
Yeee, I got most of it working now, it's now only not showing my trained voice model in my rvcdisconnected folder
After training and exporting model from notebook to drive, the index drive isn't running
whats the best voice settings?
Searching for the perfect RVC e-girl voice model? 
⠀
Settings for Nvidia GPUs 
F0 Det.: rmvpe (suggested for all series)
RTX 40-series: 80-96 chunk | +16384 extra
RTX 30-series: 96-112 chunk | +16384 extra
RTX 20-series: 112-128 chunk | +16384 extra
GTX 16-series: 128-192 chunk | +8192 extra
GTX 10-series: 128-192 chunk | +8192 extra
Advanced Settings
Protocol : Sio or Rest
Crossfade: 4096 start 0.2 end 0.8
Trancate: 300
Silencefront: Off
Protect: 0.5
RVC Quality: Low
⠀
i dont trust bots
Ayo? @sharp wind level 1 !!! 
Voice changer right?
Input do ur mic output do ur vac
Gain and tune just mess around
Small question, does it matter much between 4070 or 4080 for performance?
Or just all the um, generation of the graphics card. 3000 or 4000
i am but it still sounds robotic
when im laughing sounds like im having a seizure
Most models mess up on things like laughs and coughs
i wonder if there is a austrian painter voice

awhhh there is not
what is wrong with people man 
i wanterd to do all types of things with that voice
bring back what my family started
i can't find Sherry Birkin voice
Any metal gear ai voices?
search the #1175430844685484042
Found it
Ayo? @elfin comet level 1 !!! 
I have found 4 results for the search ezreal...
I have found 3 results for the search Sett...
hi chat
can anyone help me find a Boomhauer model?
My w-okada isn't coming out sound, what do I do?
how do i download w-okada voice chat
-realtime
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
/ai help
-help
-help
Ayo? @void cosmos level 2 !!! 
-rvc
Full AI Voice Model Training Guide (Local)
Link: YouTube
Credits: Christopher Villanueva
Model training with Mainline RVC
Link: Rentry
credits: Raven (ravencutie21)
AICoverGen Colab Guide
Link: Google Docs
Credits: Eddy (Spanish Helper)
Create a model with RVC disconnected (colab)
Link: Google Docs
Credits: Angetyde
How To Make an AI Cover With Ilaria RVC
Link: Rentry
Credits: 👽 Julia (ailen2091)
Wrong place sorry
- Applio-RVC-Fork, by IA Hispano GitHub
- Mangio-RVC-Fork, by Mangio621 Huggingface
- RVC Studio, by SayanoAI Huggingface
- AICoverGen, by SociallyIneptWeeb GitHub
- Replay, by Replay Team Website
- Original RVC, by the RVC-Project team GitHub
You can find more info on the #1159513888199540817 channel. If you can't find your answer, feel free to ask for help in #✨│ai-help. Credits to Faze Masta and Antasma for compiling these links.
-colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HFv2, by r3gm Huggingface Spaces
- AICoverGen, by r3gm Huggingface Spaces
- Advanced RVC Inference, by r3gm Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
its literally human made tutorial, the bot just reads and outputs
does anyone know where I can find a text to speech AI that has the voices of the minions?
can too much dataset ruin a model
hello
Yes
How do I hear my voice on the okada voice changer
Turn on monitor
Even if all the dataset is really good quality
Send me a DM Screenshot Application
Hm?
-realtime
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
I think this will be what you are looking for
🎙️ Realtime Voice Changer (Online)
A free, online version of W-Okada that allows you to run code on Google's powerful GPUs.
No results found for the search modi...
No results found for the search Modi...
hello
hello
hello
Full AI Voice Model Training Guide (Local)
Link: YouTube
Credits: Christopher Villanueva
Model training with Mainline RVC
Link: Rentry
credits: Raven (ravencutie21)
AICoverGen Colab Guide
Link: Google Docs
Credits: Eddy (Spanish Helper)
Create a model with RVC disconnected (colab)
Link: Google Docs
Credits: Angetyde
How To Make an AI Cover With Ilaria RVC
Link: Rentry
Credits: 👽 Julia (ailen2091)
hi
h
hi
hi
Les go
I'm back
The itsy bitsy spider climbed up the tree I wanna reach to level 5 .. I'm all alone and bored in this chat now the itsy bitsy spider
😦
@wintry sinew bruh
Ayo? @elder willow level 1 !!! 
hi everyone
I’m working on a project, as weights.gg sucks with the voices sounding like the actual characters, I’m getting models from #1175430844685484042 and importing them to FakeYou as V2V models.
Ayo? @hot smelt level 1 !!! 
I have found 3 results for the search xxxtentacion...
oh, sorry, thought I was in #🔍│find-models 😬
@civic marsh Bro can you help me?
Full AI Voice Model Training Guide (Local)
Link: YouTube
Credits: Christopher Villanueva
Model training with Mainline RVC
Link: Rentry
credits: Raven (ravencutie21)
AICoverGen Colab Guide
Link: Google Docs
Credits: Eddy (Spanish Helper)
Create a model with RVC disconnected (colab)
Link: Google Docs
Credits: Angetyde
How To Make an AI Cover With Ilaria RVC
Link: Rentry
Credits: 👽 Julia (ailen2091)
friendly reminder that for help you have #1192011222023950368 #✨│ai-help
lol, no prob
Do you love me
I love you too let's get married.
I promise to make you the best pizza and pasta every single day.

thank you but im a happy single woman and i like things how they are
Ah shit
Nuh uh
Feminism enters chatroom
Lmao
🤣
Can't believe she rejected this offer
What is
😔
Italy rizz
Can't believe it too could have made her pizza out of diamonds.
Who tf rejects free pizza every day smh
okay if we talking about money im suddenly interested
Who normally eats pizza with diamonds?
But she's a strong independent women. It's okay.
Idc if you love money just make me happy and come back for some more money later
😄
PayPal ilaria 3K
what are the best voice models to use
Searching for the perfect RVC e-girl voice model? 
Inb4 he’s looking for a smoke alarm model, not an egirl
i did that :3
Still 1k short she gotta wait about 3-5 days ..
Ayo? @elder willow level 2 !!! 
2K is fine too
im fine with 2k for now
ong ong
What's my ROI from your side
I don't want you in the kitchen I'll get you a maid.
That's fine!
/busts through saloon doors.
i'll take anyone of y'all on in mario kart and win !
I’m good at Arcade Mario kart
I was thinking more like Elon Musk style while lay down with my laptop watching the stock market and my gf sitting at the back of my laptop with a black bikini playing Mario
HEY NO MARIO IS MY THING >:(
fight me in mario kart for it
WH A T 😭
pink bikini at least i mean
What is wrong people nowadays
Money talks yall
i still dont see my 2k btw
Let me post the pic here you'll see your 2k in progress to 3k


make model ark warden

