#🧬│ai-chat
1 messages · Page 247 of 1
Also saving at every epoch is a bit too much, do 15 or 25 instead, maybe 50 even
Or use some automatic detection
mmmmm not really?
if you want the best amount of precision to get the best kl, mel, fm stats
and then merge those later on
it's pretty good!
Yeah that's why I said most people 
I don't expect anyone to do what u said lol but ur right
Maybe I misunderstood what he said
also if you wanna use a model right b4 overtraining
but like, save frequency at 5 does it for me
like other karaoke models in UVR, BVE is still bad at separating unison, duets and group vocals. there is MedleyVox to try doing that but still not good as expected and the dev is unfortunately discontinued.
call me crazy but i see best weights at prime numbers... i think it is time to sleep gn8 y'all
FL studio and most DAWs can estimate BPM and sync audio samples with stretching, like in this tutorial
https://www.youtube.com/watch?v=r7SDWpSk1h4
This FL Studio beginner tutorial will show you how to synchronize audio samples to the project tempo in FL Studio, and also how to detect the tempo of a sample and match the project tempo.
There are several different techniques available. The technique used depends on the type of sample and what you are trying to achieve. Make sure to watch the...
Ayo? @elder willow level 2 !!! 
it's probably like for a day my man 🤷♂️
just use chatgpt
it gives the 4o model limited but free for everyone
its js for some time we cant do anything about it
literally go js chatgpt site and click on the sparkle and choose 4o
it should be out free for everyone now
ooo wow
its going out slowly for everyone, i dont think its only for some regions
You need to choose 4o and then click on an attach button lemme see if i can share a screenshot
oh you meant generate an image not attach one, nope thats not free
dall e 3 is not free only premium
wait thats weird, its prolly because of copyright tho, usually it cant generate things like batman
you need to get level 5 for embed perms
by chatting
Ayo? @elder willow level 3 !!! 
its probably because of copyright issues that sometimes doesnt let you generate it
O.o
Where's the channel for updates?
the mobile copilot app works rn?
if not u can js use /image with the weights bot (which should be using dall e 3 which is what gpt4 uses for generating images, or stable diffusion) in #🤖│bots , or use stable diffusion which is open source so free but harder to use
wat i put the tune on for the youngboy one
I feel like it would be a great Idea to have a channel for songs people seperated the vocals and intrumentals succesfully, so we could all use and share the highest quality outputs of songs, as well as reducing the need for each people to have to seperate everysong everytime
Ayo? @austere moss level 1 !!! 
Hey o Im new here and I dont know what am I doing here.
jest tu glos 2t4?
hi
Hi. I am new new here. I am not sure what happens here
Hi
what the hellllllll
hi
hi
AI stuff
My online potato friend's Brother is about to pass through the city that was the inspiration for JJBA part 4 and has no idea.
whar
hi
ello
https://rentry.co/VoiceChangerGuide has download links and how to use it
EOL - No further Updates
Github - Blanc-dot
Discord - Blanc_dot
Despite being end of life, most if not all information has not really changed, so should be very accurate until actual new stuff comes out.
Other Links
Antasma's Local Error Fixes
Antasma's Colab guide
Sushi's useful Links - You need...
hello, do you know a free AI website that can parse ~538000 character text and answer me some questions about that text?
(text is in polish)
yeah no, I don't think anything free will do that
even local llms would not handle it tbh 
whats jjba
maybe I can split this text into parts for ChatGPT? but for how many?
jojos bizarre adventure?
Correct @ionic pumice
oh
way too many parts, tbh
Ayo? @fallen ruin level 13 !!! 
it's not really worth it atp
time to vote
how does one gain the content creator role
Ayo? @fallow coyote level 2 !!! 
Use /jointeam and select content creator
🐢
Someone got some raw vocals that i can mix i want to try something new
Ayo? @random geode level 2 !!! 
Dm me if u want
Hi
You will hit the token limit on every site… even with api access you wont be able to get that
i need a ai chatbot for real estate, what will be the pricing for this bot ?
Just do it yourself buh
/colab
Ayo? @tardy jay level 1 !!! 
Hi
hi
Yoo
.
hi
hi
hi
Hi
hi
.
hi im new
Hello
I have restored Chris Chan's voice cameo thanks to AI!
https://www.youtube.com/watch?v=Wu5PxxeHeTw
According to The Create Unknown Interview, Christine Weston Chandler was originally going to have a voice cameo as Grease from the episode called "Who Violently Murdered Simon S. Salty?".
Due to budget issues, It was instead voiced by Harry Partridge.
But with the power of AI and editing, the cut voice cameo is now restored in its glory!
Check...
Ayo? @velvet cape level 7 !!! 
whats the best sova voice
what's the best tool for creating AI voices from scratch (i don't want to clone an existing voice).. is RVC my best bet?
I created a voice model, how can I share it on this server?
how can I create a voice model
Ayo? @woeful trail level 1 !!! 
download applio
Ayo? @radiant inlet level 2 !!! 
merhaba
give me some high dopamine ideas for this:
the intelligence is the peak
my goal is to dominate with the help of intelligence
(ai)
Fuck I’m here only for Peter griffin voice
omg finally I got my old AIs to work again
What happened to the old voice-models channel? I remember there were tons of Simon Petrikov (and other characters) models when new series came out but now there are only 2?
is there any place to just send covers
Bonjour y'a t'il quelqu'un de français ici svp ?
can I just send a wav file in chat or do I have to upload it to yt first
Does anyone know how I can use AI voices live? please
hi
JSONDecodeError Traceback (most recent call last)
<ipython-input-22-fb1748d5acca> in <cell line: 31>()
31 if os.path.exists(config_path):
32 # File exists, proceed with creation of creds and client
---> 33 creds = Credentials.from_service_account_file(config_path, scopes=scope)
34 client = gspread.authorize(creds)
35 else:
5 frames
/usr/lib/python3.10/json/decoder.py in raw_decode(self, s, idx)
353 obj, end = self.scan_once(s, idx)
354 except StopIteration as err:
--> 355 raise JSONDecodeError("Expecting value", s, err.value) from None
356 return obj, end
JSONDecodeError: Expecting value: line 1 column 1 (char 0)
Im getting this error
Colab is outdated. You can check the colabs that Automaze sent instead
-colab
- Applio, by IA Hispano Google 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
- Ilaria RVC, by thestingerx Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- 🆕 UVR5 NO UI for Google Colab, by Eddy Google Colab
- Applio, by IA Hispano Huggingface Spaces
- 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
Ty
Yw
hey why do i get an error when i try to run STEP 2 on google colab??
What Colab are you using?
This colab is outdated, use these colabs instead:
-colab
- Applio, by IA Hispano Google 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
- Ilaria RVC, by thestingerx Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- 🆕 UVR5 NO UI for Google Colab, by Eddy Google Colab
- Applio, by IA Hispano Huggingface Spaces
- 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
@naive ermine You should use these colabs
Thank you!
You're welcome :>
Just had the same issue 
Ayo? @amber raptor level 2 !!! 
how do i get screenshare permissions
merhaba
Ayo? @ripe osprey level 1 !!! 
yardımcı olabilecek biri var mı?
what are u yapping about
Ayo? @elder willow level 1 !!! 
what does level 5 give u
u sure? i can screenshare just fine
Vote Booster: Vote now for a 10% boost. https://arcane.bot/vote
Anybody know where i can find a good tory lanez model??
Ayo? @naive ermine level 1 !!! 
if you cant find any on the server you might just need to make it yourself
bru what
how are you able to screenshare
ts rigged
how do I use a Voice Model, sorry I'm new
wdym?
like how do u get the models in ur voicechanger?
https://docs.aihub.wtf/ has everything you need to know about RVC
if you want easier stuff, weights.gg
Last update: Mar 10, 2024
can a mod just give me screenshare perms 😭 🙏
Thanks I will check it out!
yeah
go to what the mod sent in chat
if u want stuff bout the realtime voice changer then check out https://rentry.co/VoiceChangerGuide
EOL - No further Updates
Github - Blanc-dot
Discord - Blanc_dot
Despite being end of life, most if not all information has not really changed, so should be very accurate until actual new stuff comes out.
Other Links
Antasma's Local Error Fixes
Antasma's Colab guide
Sushi's useful Links - You need...
Thanks alot!
Ayo? @finite basin level 1 !!! 
mj pls just give me screenshare perms i dont feel like chatting for 10 years 😭 🙏
i am pretty sure you can screen share already, though, as @fallow coyote pointed out
how does one become a trusted and verified member?
for some reason it wont allow me
neeko did u do something to be able to screenshare
How tf do i do that?
did you ever do anything in a chat or call that would make a mod want to take some of your privileges?
Ayo? @fallow coyote level 3 !!! 
trusted is given out to certain people, verified is given out to lvl 5 users
nope
Ayo? @elder willow level 2 !!! 
what's confusing is that both ai members and verified have no perms for video
so like... whyshqhdgqj d

im looking at the people who are screeensharing roles but like planquin doesnt have any roles that would give ss i dont think
is there any text to video that can do more than 4 secs at a time i checked all the ones on the internet but they all seem to create really short loops
Don't believe there is, as far as I know
Oh wait just remembered this exists
StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation
Maybe this works?
😂
is there a channel i can just spam in 😭 🙏
Dude's bro 😂
I am surprised at how fast AI music is advancing by leaps and bounds but video is lagging behind
i don't think its lagging behind
It's the hardest thing to train AI on, tbh. Heavy formats, large file sizes...
If OpenAI did it though, it's very much possible
Soon it'll be open-source
mj is there a channel u would allow me to spam in to get to level 5
Ok. That's dope.
nah, sadly 
but hey, we're chatting here
truee
Vote Booster: Vote now for a 10% boost. https://arcane.bot/vote
this mario guy he's so unkind to yoshi
like yoshi was out there helping bro when he was a child
and he does this
anyone else mourning over george coopers death?
what???
who is george cooper 😭
...
mf a random
have you not seen young sheldon?
its all over tiktok bro😭
im a yt shorts person
you watch anime?
mhm
though I have only watched like 1 or 2 fully, by myself
the rest, i have probably watched a couple of episodes
i reccomend jujutsu kaisen if you haven't watched it already, just read all of the manga and its amazing. now i have to wait every week for a new a chapter😭
Ahhhhh damn. I watched the entire anime though
Haven't read the manga yet
i saw a george cooper x jjk edit and its incredible😍
how do these fit
L
sorry 🤣
massive L
what in particular sucks about anime
fair enough!
anime doesn't suck, it's just that it's not for everybody
im done bru i give up
real
neeko u can screenshare?
yes
Vote Booster: Vote now for a 10% boost. https://arcane.bot/vote
✨ Tip: Use /card to modify your rank card
Vote Booster: Vote now for a 10% boost. https://arcane.bot/vote
im tired of ts bru
Ayo? @elder willow level 3 !!! 
FINALLY
Vote Booster: Vote now for a 10% boost. https://arcane.bot/vote
✨ Tip: Use /card to modify your rank card
yo if i get a voice from #1175430844685484042 how can i make it say stuff from the file
Now you will use RVC via Colab - check https://docs.aihub.wtf/ for more info on RVC n stuff, also Colabs to use on RVC > Cloud section
Last update: Mar 10, 2024
@forest quarry do u know alot about this server?
Alternatively, weights.gg can be used
mhhhh
@forest sun are you alive
not really a lot
whats the best male voice
are those both free?
does the content creator role give any perms or nah?
really depends, tbh
but search for a voice you like in #1175430844685484042 - you should find something
yes, weights.gg has a queue though, but its ease of use is unbeaten
mmmm idk tbh
how can i use text to speech with audio voice from one i found here
cause when i go to text to speech its just base voices
Ayo? @compact hamlet level 1 !!! 
yeah but it'll convert that base voice to the desired voice
i applied for it bcs i want to feel special💀 😭
lollll hope you get it then
i am also not for the green username, it does not look nice
Vote Booster: Vote now for a 10% boost. https://arcane.bot/vote
✨ Tip: Use /card to modify your rank card
CMON
lol
Ayo? @fallow coyote level 4 !!! 
......
pahahahahhahaa
yea now its taunting me
ts so rigged 😭
I HAVE PERMS TO SCREENSHARE IN the other ones
just not unlimited
how do i make x cover song
that makes more sense atleast
does anyone know how i can make an x cover song plz
hm?
like, you want to cover a song, with an ai voice model?
https://docs.aihub.wtf/ - has everything you need to know about RVC, how to use it, etc
Last update: Mar 10, 2024
alternatively if that's too hard you can use weights.gg
ok thank you
You're welcome! If you have any issues, let us know.
ok awesome i completed it thank you so much for your helo
Ayo? @elder willow level 1 !!! 
i just wanted to see how the song "My Sanity by Dxgnelo sounded with the xxx voice model and its so accurate
file:///C:/Users/kdvil/Downloads/XXXTENTACION%20-%20MY%20SANITY%20[vocals].mp3%20-%20[Weights.gg].mp3 heres the link if anyone wants to hear. I love this song. Perfect for late night drives and nostalgic introspection.
i think that's just a location in your files
teto is a goat
youre not in any of the vocaloid servers
Vote Booster: Vote now for a 10% boost. https://arcane.bot/vote
✨ Tip: Use /card to modify your rank card
very disappointing they never used the hologram projectors especially becuase they were charging $500 for tickets
Teto concert had a hologram
And no drama
I paid like $55 for miku concert
never knew teto had a concert
was it in america
so real
godzilla a goat
have u listend to mesmerizer?
Of course, did you check out their other songs?
32ki?
Yeah they did several miku teto duets
Im like me
i see miku and teto songs the most, are they the most popular vocoloids
Teto isnt a vocaloid
huh
But close enough (teto is an utauloid)
whats the difference
Idk like all the details because im new to the vocaloid community but basically vocaloid is paid utau is a free alternative with different voicebanks
wataru sasaki of crypton made the teto vocaloid v4 in 2017 it performed live and i have the physical album made with it
It’s not by the same company aswell
🤯
so the only real difference is that their different voice banks owned by different people
There are more differences but basically thats all you need to know
curious what it sounds like?
Sure
you can make your own!
is vocaloid similar to how people make models on this server
kinda, utau has ai too
Thank you for watching this video, I hope you liked it and found it interesting. Please take this for what it is: a rumor. I'm not confirming the existence of Kasane Teto for VOCALOID, I saw this information in an iceberg of VOCALOID in Spanish and I found it interesting to share it with you.
By the way, Teto doesn't sound like she usually wou...
is teto a girl
Ayo? @fallow coyote level 5 !!! 
Yes
her VP is very talented
Im gonna go sleep eepy goodnight everybody
people kept call teto a guy in the comments of the mesmerizer song
gn
kasane ted is official
Probably japanese translation because translation autotranslates to male because it can be both for every first person pronoun
It’s kind of confusing but i have to go now
Or well i explained it wrong my bad
Im panic typing rn my phone 1%
Something went wrong while deserializing the object Last.fm returned. It could be that there are no results, or that they're having issues.
what other songs would you recommend
Letter to the black world
Its my fav song
From teto
ill listen to it the now
Gn
gn
i met the producer, nice guy
want to play with the fun vocaloid stuff?
wdym
hola
Something went wrong while deserializing the object Last.fm returned. It could be that there are no results, or that they're having issues.
i can send you some
pls do
Hello, my name is Dania, nice to meet everyone. I am an artist who has worked for over a year in AI as a prompt artist video editor and image editor. You can view my video work here. https://youtube.com/@interdimensionaltravelagent?si=EGlt8Jf2FXDEcFXv
Ayo? @elder willow level 1 !!! 
The Last.fm user EitherEleleryOr has no listening history on their profile yet.
Just created your Last.fm account? Make sure you set it to track your music app.
Using Spotify? You can link that here. This can take a few minutes to start working.
Please note that .fmbot is not affiliated with Last.fm or Spotify.
jojo reference
how do you make a voice?
Ayo? @broken copper level 1 !!! 
I agree with Omniman here.
Lmao there is whole sticker for it nicee
Does anyone have an anime wind breaker model?
whitch female model is the most trained here for free?
Yoo, has been any improvements to the w-okado program or any competitors. Just wondering if AI voice tech gotten any better in the last year?
Yeah. Her.
@quartz roost Damn what is this?
Ayo? @supple plover level 1 !!! 
Looks cool 😎
the best selling singing ai voice
@quartz roost Sounds smooth, no cracking or static.
Is it a program with a specialized voice modal? Can I download it?
What's it called?
DAEMON/DOLL CD PRE-ORDERS OPEN UNTIL MAY 27TH: https://daemondoll.bigcartel.com/product/daemon-doll-album
(US and Japan only)
Streaming now: https://open.spotify.com/album/1tEsHuH8lXl4kyGCt5r3Pr
More about DAEMON/DOLL: https://daemondoll.site/
The mourning of one still alive
⚠ CONTENT WARNING: I promise.
Scroll down for a full list of war...

Hi I'm new
RIP weights
Mine dont work it keeps saying no model found
Works for me
Hey guys I’m about to go to the elementary school that’s a few minutes away I just wanted to know what grade has the tightest girls? Any feedback would be nice thanks for listening
Yo do you know if the voice changer duckus uses is a rat?
I think the first mistake you made was watching duckus
I’m just trying to get a ai voice changer 😭😭
-rt
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
Ayo? @cunning rampart level 1 !!! 
And I didn’t find a single thing
Like malware?
Yeah
No? It’s a RVC model
Also all the programs here are open source so you can see the source code if you wanted to
Read this guide since it tells you the correct settings and installation
A lot of time YouTubers don’t really do any research and just sometimes spread misinfo
On my phone rn
Ahh
Tho everything should be categorized for stuff like settings and downloads
Depends on your settings and models
And what’s realistic is subjective
What I mean by realistic is when I use it they don’t be like “hey that’s a voice changer”
Depending on the person might not be able to tell
If you ever need help ask in #🔍│help-w-okada
weights gg
thanks
yep, that's how programs typically do things lol
it kinda scared me
they just usually hide the cmd prompt from you when you install it
a rat or malware would hide it from you too xD
Just trust in the process 🤞
Titan pretrained models actually sounds pretty good
I noticed it can do laughing better than other models (still not that great, but better)
People when code
how do I use it on discord
It says how in the guide
its like
Ayo? @cunning rampart level 2 !!! 
laggy idk why
.
Also explained in the guide
It’s because of your chunk/extra probably
it sounds choppy
Or f0 det
what should I put that at
Hey how do I use ai things on mobile
I’m trying to make those weird baldi ai videos and I just need the voice
I'm Tiff I just admire AI music , art and stuff, I'm interested in learning to make some my self, but I don't have a computer and I'm slightly stupid.😅😭
could you look in dms please
Halo anyone please give me advice, what tools should i choose for make a voice model non English and Japan lenguage. i need to train bahasa indonesia and other lenguage 
what if i make it on RVC ? this is still good ?
and for the dataset, how much i need to serve ? like 2 x 5minutes audio or more ?
why is it not opening?
What file are you opening
RVC works in any language some better then others
You know, I would love it if we were able to interact physically with a character of our liking...
Isn’t that why cosplay exists?
None of the voices I use sound good 😭
Well, I had never thought of that... but what if we have the actual character by our side as a means to comfort ourselves?
okay, but i try with 2 x 7 minutes dataset it still there is noissy like robotic . so how much sample i need to prepare ?
Maybe the voice input has background noise
I recommend a good quality mic
i've clean the noise and try to get the voice input from podcast. it must be clean voice
With background noise suppressing microphones, the sound should be better
if you don't mind if I chime in what is epoch im new to this?
for training voice model, used on RVC
I don't know what any of that is 😭
But I am a bit worried that bringing the character into our reality would not be possible in my lifetime
Ayo? @stray crypt level 2 !!! 
Bud, you are trying to speedrun for answers
. We have guides https://docs.aihub.wtf/extra/glossary/
Last update: Mar 8, 2024
Last update: Feb 10, 2024
ah ya it is >.<
How am I ever going to fulfill my desire outside of imaginative realms?
Anyone?
I think the world would implode if hatsune miku was real
Send a screenshot of your settings
2x7??? Did you duplicate your dataset?
dms
no, its different dataset
Why not just say 14 then?
i dont know, i just curious how if i split the dataset to 2 part
Ayo? @lucid sigil level 2 !!! 
hi
hi
@storm meadow Sigh, I really want to be with a character that would care for and love me...
Lol I usually fall especially maths classes 😂😂😂
@finite void, I have found 4 results that match your search!
@finite void, I have found 3 results that match your search!
Sorry, I could not find models that match your search "rakyz"
@finite void, I have found 2 results that match your search!
donde puedo encontrar kits models ?
Does anyone have mordecai english version
we dont use kits here
kits sucks
we use rvc v2 which is better and free
check our docs https://docs.aihub.wtf
Last update: Mar 10, 2024
and theres #🌍│español
kits is an L
what the fuck
@finite void theres #🔍│find-models to use applio search command
👋
yoo
yii
could be pretrain issues 
i used ov2super
You need the 32k fix, hold on
do you guys have perms to take down models by the way?
ye, why?
I want mines gone #1243386397054992456 message thanks
alr, it has been done
omg ty sir ><
oooor titan
is there any good AI video outpainting tool yet?
we all use it instead of ov2
Sadly no
outclassed but still usable. Really depends if you have a clean dataset
Since AI video is only getting started
The original pretrains in the background:
yeah we just waiting for ov2 2.1. Dunno when that'll come out. Anyways I just wanted an excuse to get my post deleted 
Waiting for RVC v3 pretrains
:)
Never coming out but whatever
pika labs expand video is really promising.. but only allows a video size under 10mb... which is kinda a joke
it's 2024 and they don't want people to upload videos bigger than 10mb xD
They don't wanna strain their servers, which is understandable
Hopefully AI video goes open source very soon
As it stands there's only closed source stuff
what are yall yapping abt
waittt, what does astra labs do, i submitted a cover like a day ago but how do i receive it?
Yo guys I'm new to this and I was wondering if there is a free voice cloning app I could mess around in
what's thids server's command again to display all the software solutions for TTS, STS, and singing?
okay, nevermind, found it, but the bot only gives a list of Google Colabs and Hugginfaces for RVC
I'm looking for a decent, free TTS app/code for local use of TTS voice clones on one's own comp
hm, guess I'll suggest TalkNet to the friend who's asking about this
getting a dual 8pin pcie cable for my 750 watt psu so i can use my tesla k80
flippin frick yes
Hello together, im Sandro, i saw a yt Video about an AI Cover, found it interessting and wanna try it on my own. So thanks for being part of this community.
hi
How to use search voice model again?
You can check our docs abt it https://docs.aihub.wtf
Last update: Mar 10, 2024
hi, are there any rvc model to remove background noise?
gengeral chat
gengaral chat
I am sourav
hey guys have a question - is it possible to change lyrics of a song with ai? More of a lesser known song.
If I have the extracted vocals of course
Changing a word in or 2 is what I want to do
And if it’s possible can someone please guide me through how to do this!
You'd have to rerecord that song with the new lyrics, and then convert that with RVC
you know who else 'd have to rerecord that song with the new lyrics , and then convert that with RVC? MY MOM!
Try denoise on xminus
Wait does anyone here work wit yolo?
lol
Ayo? @ocean sedge level 3 !!! 
fak you 👍


how do i fix pipeline initializing
Lewding chichi is funni for the internet
by shoving it up your 
@signal cairn wassup

@river adder
@rare sorrel can you give me a free timeout?
- My prefix in this server is
-(customizable with-prefix) - Interested in how I'm built? I'm actually open source!
- Forgot a specific command? Try
/helpor-help
nooooooooooooooo
what
nationality incorrectly identified opinion rejected
Racist 
არა
umu
რუსებმა ჩემ ქვეყანას დედა უტირეს
ამიტომაც მე კარგი მიზეზი მაქვს რომ რუსები მეზიზღებოდეს
ეს მაინც რასისტულია
google translate ahh georgian
speak english 🥶
give this man, a true 
give this man, a false
Hating an entire race for what they did i think is racist wouldn’t it be?
not from my country's perspective
anyways im out, temp ban me or something idk
im not from russia tho, im from belarus
and im certainly not in support of russia
Hi
mfs when they see someone from a country they dislike (the guess wasnt even true)
SIGMA™
Ayo? @languid stone level 1 !!! 
so true™
i know right
fr
frfr
what is epchos chat
Ayo? @unborn bloom level 1 !!! 
What
what are your pc specs?
5700x3d 4070 48gbram
perfect and motherboard?
wtf
how tf u have that in brazil
do u live in a 3 story mansion???
like wtf
also the ram is ddr5?
Mfw people think everyone in Brazil is broke
yea u in a 3 story mansion for sure
u got a movie theater?
No
dam
I live in a rural area lmao
@signal cairn Motherboard and is ram ddr 5
Ddr4 3600 forgot motherboard
Kinda how many cycles of training happened
so whats a good one to look for
Doesn't mean more quality in all cases
what range
None
cooked
u got a showcase of ur girl models
can you look in system info?
does anyone have a tutorial link for the okada vc
hey guys, what UVR5 model should i use to keep the audio sample rate same as the original song
Ayo? @south atlas level 7 !!! 
ai segg when
Ayo? @round prairie level 1 !!! 
i noticed that almost every output is 32k, idk if it is really because UVR5 or the vocal of the songs itself 32k
🍔 
hello I am Savvy, i am a young growing music artist and i was wondering if this server makes producer tags and artist tags
Hi, do you know if you can import your own voices into a program? I'm using w-Okada's voicechanger, but I can only import voices from https://voice-models.com/

🤓
🗿
-colab
- Applio, by IA Hispano Google 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
- Ilaria RVC, by thestingerx Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- 🆕 UVR5 NO UI for Google Colab, by Eddy Google Colab
- Applio, by IA Hispano Huggingface Spaces
- 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
check kofi, but most are private
Hey guys why does hugging face tell me Invalid username or password when i try to download something? ive connected it to discord
It is possible that you want to download private and you do not have permission
it is publicly available on huggingface tho
Send me the link
Ayo? @haughty tulip level 1 !!! 
This file was either deleted by someone or someone blocked access for others
In other words you will not be able to download
Try to find the model on this site:
https://www.weights.gg/
auto car vrooooom vroooooom
huggingface.co/clubbedsam/**chriscornell/resolve/main/cornellv2.zip ** You can't find this because it doesn't exist
vrooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooom vroooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooom
@nimble hare yea you can unblock now
Ayo? @runic star level 1 !!! 
@runic star don't self promote here, thx
how can i add Code to be afk in colab
-colab
Suggestions for @elder willow
- Applio, by IA Hispano Google 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
- Ilaria RVC, by thestingerx Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- 🆕 UVR5 NO UI for Google Colab, by Eddy Google Colab
- Applio, by IA Hispano Huggingface Spaces
- 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
idk what i should do next when i press Ctrl + Shift + i
There's stuff like that out there, but I don't think it's particularly useful. You have to check the graphs every once in a while, y'know
You can always watch a vid and go back on that Colab tab every 5 mins
ight thanks ❤️
Yw, good luck on that training 🙏
hello
hello there!
Yooo
anyone have good obama model
am i a sigma for mewing or is edging goated rizz
autism maxxing
you should have received it in DM's, if you still haven't its possible that your DM was off and you didn't got it, try again
No
Ayo? @pseudo horizon level 1 !!! 
shit the fuck up you cog
I am gonna touch you to assert dominance
k
cuz i want a pc good for ai
ama buy everything u ahve
this right?
Motherboard:
Model: B550
CPU:
AMD Ryzen 7 5700X
RAM:
DDR4 3600MHz, 48GB (3 sticks of 16GB each)
Graphics Card:
NVIDIA GeForce RTX 4070
just the psu and we good
also case if u want ;p
👋
ello!!!
K
Colab was working fine for me and did about 40+ epochs and then iam getting this error everywhere in colab even after restarting everything "An error occurred: dictionary update sequence element #115 has length 3; 2 is required"
Ayo? @elder willow level 1 !!! 
mano
essa porra laga muito
é daora mas tem que ter um pc mó foda pra rodar isso
querer rodar uma tecnologia recente com uma placa de quase 10 anos atras q é foda
💀
Happy 54th birthday to Yukino Satsuki, who voices Kagome.
🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯🕯🕯🕯🕯🕯🕯🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯🕯🕯🕯🕯🕯️🕯️🕯🕯🕯️
h
Hi
Bana klonlama için yardımcı olabilir misiniz Macos da sanırım bu işi yapacak bir program yok
bro speaking monkey language
Ayo? @elder willow level 2 !!! 
what
mod 😨
Does anyone know how to separate the double vocal? UVR-BVE doesn't work.
karaoke
if its the same singer it might not work
and then rip
ohh. Im making dataset soo I need to seperate it
español?
karaoke v2 also doesnt work
si
nope
if the 2 voices are too similar you wont be able to isolate those anyway
yea its the same singer
rip then
rip :<
rippy
I have one more question. Leaving the breaths in the dataset improves their quality in the model?
🙂
Apparently yes
Hmm. And what if i add to dataset a custom high quality breaths?
hello guys any1 have the collab link cuz i havent read chatfor awhile?
Yo I’m trying to download a voice model to the easy gui and it says “Model downloaded, you can go back to the inference page” but IT WONT SHOW UP ON THE DROP DOWN THING
hello
hello
“Refresh” button
Might sound weird... not sure tbh
Colab links and guides in https://docs.aihub.wtf/ !!!
Last update: Mar 10, 2024
howdy
Good luck 🙏
Ello
Is this a good discord for a complete beginner when learning to make ai generated cartoons?
Mmmm, not really, sadly
It's more of an audio AI community here tbh
got any suggestions?
audio is a great start though I am okay with elevenlabs but learning more could be quite useful, I just cloned my own voice 😊
howdy
We use RVC which is FOSS and is audio-to-audio
Mmmm not really
what do you mean exactly
Hi
I'm assuming they want to create anime styled images
yall maybe can support my tiktok page? i think ima lil bit underated fr
🥸
hello everyone
no lol
#1159290752195633273 , ty
Thanks
🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯🕯🕯🕯🕯🕯🕯🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯🕯🕯🕯
you can edit breath duration types, duration and strength
Ayo? @quartz roost level 69 !!! 
😭 we arent talking teto sorry
i think it's this cat
does rvc like datasets with absolutely no noise in between words or should I leave the inaudible noise there
カバー:重音テト
原曲:電脳眠眠猫 / なみぐる feat. 可不
https://www.youtube.com/watch?v=eEnY-buv4jE
https://www.youtube.com/watch?v=50ABOddeI3c&t=0s
UST/イラスト/動画:Ragtam
コメントとても嬉しいです、ありがとうございます!
yeah I'd rather not have noise there, so noise gating (or downward expand on RX) would be pretty useful
does the voice changer work on linux ?
Should
https://flashcardfy.lol good study tool
Yo
Anyone got deku dub voice model
@fleet glade, I have found 1 results that match your search!
any alternative voice model download sites that isnt voice-models.com
thank you sm LOL
Ayo? @solid dome level 1 !!! 
Fweah
anyone know where i can get tts from any model i upload
guys, are there any UVR5 model to split lead and back vocal ? i tried 5-hp-karaoke but it only output like instrument-vocal
i know in the setting panel there is a thing like "vocal splitter options", but it only run when i run another model
What, anything wrong with it? And sorry about the late reply, @storm meadow , I am still a bit sad, I ain't done with the topic at hand...
Throwing this out there, what's the best stack for Domain Name, Hosting, Cloud provider for a website, landing page that can then let users run a demo through their browser?
Kendrick or drake
Should I reupload more waefrebeorn/(e)mangamer content on yt?
(The vids are prob on internet archive bc i prob uploaded them on internet archive)
Ayo? @elder willow level 3 !!! 
R.I.P ManGamer's og yt May 8, 2008 - August 22, 2023
Cause of death: self deletion
No
What's up yall 👋
👋
hii
Hi
Hi

UVR
help
wehn i download a modle
it wont pop up in
so vits fork
like i download the file and try to find it and i cant find it
please help
-svc
im not sure if the electric guitar stem in one of models in UVR/mvsep like htdemucs_6s is good enough, and unfortunately no decent acoustic guitar stem I know so far
BVE could do it better
Bro I don't get this
How To Troubleshoot 
- Don't simply mention your issue, like "
my rvc is not working". - Describe the step you are on, what you're trying to do, the RVC you're using, a screenshot, etc.
- The more context, the better.
- Don't be desperate. You can ping a Helper, but if they ignore, they aren't available/don't know the answer.
- It's okay if you're frustrated, but don't take it into this server.
- Don't DM without prior consent.
- Don't ask for every little instruction. Put your own effort & test things by yourself.
- Don't ask to ask.
- Check if your answer is a Google search away/on our guides website.
nah i ran accros this yt video it had me download comands and shi
Ayo? @agile moth level 1 !!! 
it it linked this discord
idk is there anohtet tut ?
i might have some some wrong\
im having problems with google colab
2.2
idk im going off yt videos
thats the one im using
- Applio, by IA Hispano Google 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
- Ilaria RVC, by thestingerx Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- 🆕 UVR5 NO UI for Google Colab, by Eddy Google Colab
- Applio, by IA Hispano Huggingface Spaces
- 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, yesterday i trained a voice model with the dataset 8 min, i set training v2 40k sample rate, 4 batch size, and only reached 375e for 3 hours (until disconnected). i've read how to read the tensorboard but tbh i don't really get it. and here it is i noted the smoothed of each epochs.. which one better?
i get this error every time i press train feature index in mangio WHAT DO I DO return _swigfaiss.write_index(*args)
RuntimeError: Error in __cdecl faiss::FileIOWriter::FileIOWriter(const char *) at D:\a\faiss-wheels\faiss-wheels\faiss\faiss\impl\io.cpp:98: Error: 'f' failed: could not open C:\Users\frede\Desktop\ \vocali\Mangio-RVC-v23.7.0_INFER_TRAIN\Mangio-RVC-v23.7.0/logs/eben/trained_IVF295_Flat_nprobe_1_eben_v2.index for writing: No such file or directory
Ah, i didn't keep it

Have you tried latest Applio?
are there any cyclops voice lines from the game subnautica?
Hi.
Can anyone help me with AI incomplete response problem? I am using Llama2. I do not want to specify the token limit. But breaks response middle of the sentence.
Please anyone help me 🙏
why llama 2? It has only 4k context lenght
use llama 3 that has 8k context lenght and put max_new_tokens ro the max (8192)
We will use Llama3 in future. Sure.
But It gives very short response than the current token limit. Even I specify the token limit to high still it breakes the response in the middle of the sentence
Hi
i mean 4k is a very small token limit already, and that being the max could also be a reason, else might be something in the code that didnt correctly set the max new tokens
azu girls reimagined as wagner pmc operators 😂
hi
You mean Replay? @elder willow
i think so yeah
I'm looking to trade or maybe sell off my RTX 4070, feel free to DM me some offers :3
where is voice models
hi
Happy Birthday J. Michael Tatum
happy birthday ig
🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯🕯🕯🕯🕯🕯🕯🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯️🕯🕯🕯🕯
happy birthday mr mike ig'
i think rmvpe
rvmpe, fast and has almost the same quality as crepe, while also dealing better with noise.
for most cases of RVC and voice changer, rmvpe is the best
guys who can do custom voice model? пацаны, кто сможет модель голоса свою сделать ?
just make a post in #1159289738314919936
ok
um I have a rvc model and I can't upload it to kits ai
im jeffrey
you cant upload to nor download models from kits, also it is paywalled
Honestly, don't use kits.ai - just use weights.gg and the models they have there. Much better, and also you don't need to subscribe to something to download audio
hello!
thanks I'll try
Where did you know about kits ai
And they don't even need that
Just look at Weights
They aren't that paywalled and do just fine
Fr weights is goated
most youtube videos about it are more than half year old and outdated, compared to the comprehensive guides in this server
I screen record the vocals so I don't need to pay
ok I'll look at it
You will get limited after converting 10 minutes of audio iirc
no you can't download the mp3 file but you get infinite converts
Didnt knew that
But still i recommend use something other than kits.ai
ok
hello guys
can someone help my sound so laggy
what are you using, and what's your gpu? AMD stuff needs a lil extra step
ummm how cani check it?
gpu? check task manager, performance tab
gpu NVIDIA GeForce RTX 4070 SUPER
Ayo? @chilly tusk level 1 !!! 
mmm
share your settings in #🔍│help-w-okada real quick