#✨│ai-help
1 messages · Page 90 of 1
k
?
This is not my Screenshot
@open flicker #🔍│help-w-okada message
Can anyone help? When I try to change a voice, i get this.
I think that Voice Changer -> #🔍│help-w-okada
This is my error
is there colab that doesnt require logging into google drive?
Can someone help me, it seems I can't hear myself.
hello! how can i fix this?
Can anyone help me?
Retry again
Getting this error
did you extract the whole thing?
the entire folder
@dawn nebulacan you help me ;-;
.
Is there anyone that can help me?
Ayo? @brittle wing level 2 !!! 
which colab
Easy GUI (for RVC v2, with crepe) (with improved downloader
what are u using
What's up?
Ayo? @open flicker level 3 !!! 
yep, works
supposed to look like that
@dawn nebula
?
yes, it is downloading some stuff
show me the whole voice changer
@dawn nebula
ive always used server
have u ran all the previous cells
yes
which link are u using
ive always used server and thats how i was able to get it to work with discord
this
use another model with index i guess?
im not very good at okada
well i tried asking for help there but no one responded XD
outdated
use rvc disconnected
can i have the new one?
Ayo? @jaunty flame level 2 !!! 
Also had no idea how to tell what im using
-colab
Suggestions for @jaunty flame
- 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
- 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
- GPT-SoVITS (demo), by litagin Huggingface Spaces
any suggestions for reliable good girl voices
thanks
do you know someone who can help me then?
Idk.
@dawn nebulahi
Ayo? @quick cliff level 1 !!! 
i have a voice feedback, when i uses in discord
@acoustic scarab@dawn nebula@scenic gale@tired kraken@stoic cloud@brittle wing
someone?
Ok some of us are busy so we can't help everyone instantly, also I'm an AI Art helper not an rvc helper, just be patient.
can you not
How do you upload a model for inference on applio?
Ayo? @subtle sage level 3 !!! 
its 4 am
ok, not problem
in my fuse no, i'm sorry xD
when i get to step 2 of the rvc 2 google colab it shows up red when i put in the link but ive completed everything in step 1 . im very confused @dawn nebula
can u not ping everyone
none of the voices work other then this one
Trying to upload a model from Huggingface but I keep getting this error: JSONDecodeError: Expecting value: line 1 column 1 (char 0)
How to separate a duo?

@twin heron Python スクリプト データのようです。JSON ホスティング変換を更新する必要があるか、バグを避けるためにダウングレードする必要があります。
RVC Guides (How to Make AI Cover)
Translation by country
can someone show me how i implement this to see if it works
How to infer on EasyGUI locally? I mean this may alternative for Gradio incase if the public URL on EasyGUI is only for paid users again on the future but I can't see/find the "audios" folder on EasyGUI so how I can upload the mp3,WAV etc. there?
What was the website with the good rvc models?
Hey, does anyone get runtime disconnection issue due to disallowed code in RVC Google colab?
its prolly an outdated colab
Send here the link of the colab you use
Google colab bro.. the free version
yea, which colab are you using for rvc?
theres many
What does this mean?
you are prolly using an outdated colab, new colabs have method to bypass that warning
send the whole link
thats the basic link of colab
colab is a google service in python code for many types of uses, so there are many colabs
okay one sec
-rt
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
Oh that one is blocked
yea, use the hina one
Yeah, so what to use?
I don't have a good enough gpu
that one is not blocked yet from what I know
Okay, is it same as w-okada?
Its the updated wokada colab, use that
this is also the guide for it if you dont know what to do
Yeah exact same thing, just modified slightly to avoid being detected by google
Do we need to keep using it to keep the runtime active?
Ayo? @mild hornet level 2 !!! 

@low shard
How many hours can it work without any issue?
4
Okk
not really
he can also use the code
for being afk on the colab page
I just looked in the GitHub repos. They is also a kaggle RVC
Okk
i havnt updated that in a while
yes, you can either look at the colab page, or look into this guide that has a code to make it always active so you can stay afk, just dont close the page https://discord.com/channels/1159260121998827560/1210335063447699486
symmetra (overwatch) model link doesn't work, can someone help
please follow the guide i sent you and ask in #🔍│help-w-okada
ok
Hello, I downloaded the Voice changer for mac everything went well until aI clicked on the voice and tried it out and I didn't hear the voice change. What my be the cause of the problem?
I checked my microphone✅
Checked my headphone✅
Used passthru to also check it✅
Mind sharing a screenshot of the program as well as the terminal that's opened with it ?
There might be something relevant within that
Where could I send you the screen shots?
Thank you.
media perms are gated behind level one on the server... which takes a few messages to get. I can just give the role though
Like the ones you found in #1175430844685484042 ? What do you want to do with them ?
Here's the program
Ayo? @brittle wing level 1 !!! 
use them in a discord vc with friends
The terminal has a bit of stuff so I will send it in multiple screenshots.
You're looking for this then :
https://github.com/w-okada/voice-changer
A guide with direct download links can be found there (the download links on the original project page are confusing)
https://rentry.co/VoiceChangerGuide
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
Frequently Asked Questions
Jump To The Important Sections
Other Links
Download NVIDIA
Download AMD/INTEL GPUs
Download Mac
Online Hosted Alt...
Actually this is the only thing I think you need. Right?
Yeah in this case
thank you thank you thank you
Ayo? @inner trench level 1 !!! 
I see what could be going wrong : there are spaces in folder names that lead up to voice-changer
it freaks out when there's spaces
Should I rename the folder?
"Ai Voice Changer" and " (1)" both cause issues
yeah you can put underscores (_) instead of spaces
Ok
wait what one should i download theres a lot on this github page
what's your GPU ?
I will try it again right now.
RTX 3060
Thank you so much.
Cpu Ryzen 9 5900
While you're there, can I just ask you to try something ? We don't see many mac users
try using voice-changer and see how low you can get the "CHUNK" setting to go without it struggling (also make sure to select rmvpe as f0 det)
can someone help it keeps saying waiting for pipeline
Never mind its not working again :/
I am going to try it one more time
Terminal again ig
Can you screenshot the command prompt (cmd) window that's opened with voice changer in here ?
real
Did you also rename the unzipped folder ?
cant send it here
Apparently you unzipped twice, so the 2nd folder has a (1) at the end (with a space)
you should be able to though
can you scroll up the cmd ? above all the pipeline spam
See the sneaky space in between the folder and (1) ?
Aha
Ayo? @minor blaze level 1 !!! 
Ok its kinda working now, but.... It cuts off
Ayo? @brittle wing level 2 !!! 
Oh great, there it is
in the folder you unzipped for voice changer , delete the folder called pretrain
relaunch, and make sure to use a custom voice model and not the default ones
Ok the more I increase the chunk the better its is (and the hotter the laptop is too)
ok
Try with a custom model too, and make sure the f0 det thing is set to rmvpe
The default models must be slow as balls on mac because they can't use the GPU
Haven't tried a custom model yet, will do that shortly.
See how low you can put chunk while not having issues and report back, I think I know a way to make it even faster, but I don't have mac hardware to test on
DONT CHNAGE THE S.Thresh to quickly
Ok.
What S.thresh would you reccomend?
Whatever works
Ok.
it's used as gate, anything below the threshold will just not get processed
Afster you've had a bit of fun, try this I guess
👀
Copy start_http.command to like start_http_test.command
Open it via a text editor, and replace
--content_vec_500_onnx_on true
to
--content_vec_500_onnx_on false
then relaunch with the new script, it might run better

Processing it thourgh my brain.
Which line?
My eyes are hurting
Oh hang on, can you send the start_http file in here ?
Ok
Can be annoying to edit on mac I guess
For the record : current file looks like this :
#!/bin/bash
curdir="$(dirname "$0")"
cd "${curdir}/" && \
PYTORCH_ENABLE_MPS_FALLBACK=1 MMVCServerSIO.app/Contents/MacOS/MMVCServerSIO \
--https off \
-p 18888 \
--content_vec_500 pretrain/checkpoint_best_legacy_500.pt \
--content_vec_500_onnx pretrain/content_vec_500.onnx \
--content_vec_500_onnx_on true \
--hubert_base pretrain/hubert_base.pt \
--hubert_base_jp pretrain/rinna_hubert_base_jp.pt \
--hubert_soft pretrain/hubert-soft-0d54a1f4.pt \
--nsf_hifigan pretrain/nsf_hifigan/model \
--crepe_onnx_full pretrain/crepe_onnx_full.onnx \
--crepe_onnx_tiny pretrain/crepe_onnx_tiny.onnx \
--rmvpe pretrain/rmvpe.pt \
--model_dir model_dir \
--samples samples.json
edited the following :
- --content_vec_500_onnx_on true \
+ --content_vec_500_onnx_on false \
Ok.(..)
@sand iris ty so much it works now how do i link it to discord
You download VB-Cable
i know one ok wjats next
Ayo? @brittle wing level 3 !!! 
is it in the same folder as all the voice-changer files ?
If it doesn't work, forget about it, I was just curious to know lol
Lol ok.
Cuts out but at least you can hear it. The one you open in google takes too much time and if you don't use it every minute or 5 minutes it closes.
plssssssssssssssss
somone help meeeeeee
plsssssssssss
in voic changer client
my rvcc input is 0000
vloume 00000000 showing
and i cant also hear me voice changed output
i am useless at this time tried everything
Ayo? @eager zodiac level 1 !!! 
Hello, I'm new to this RVC, I've seen many options like Mangio RVC on YouTube but none of them work for me, do you know which one I can use?
What pc do you have? Mac? windows?
Hi, Windows.
I recommend you watching this video.
https://www.youtube.com/watch?v=XHGlv-E7eBw
Ok I'll watch it thanks.
Ayo? @loud talon level 1 !!! 
it may could be outdated
and also thats the voice changer in realtime
@loud talon
Which everyone wants
@loud talon do you want the realtime voica changer or the ai cover tool?
depends on what he wants, mangio rvc is for making ai covers, not realtime
Ah yeah ai cover tool
Oh :/
@brittle wing see, some people want different things, and also dont send those youtube vids, they are old
Old doesnt mean they arent working, I used that one just now.
you can check up our docs, it has everything to make the even on mobile! https://aihubdocs.github.io/en
Last update: Feb 22, 2024
I thought RVC was only useful for making AI covers, that's why I wasn't very specific.
rvc is the tool for making ai covers and training ai voice models
wokada is the tool for using those ai voice models realtime as a voice changer
its better to use the guides we have that gets updated and have the best settings
Oh ok.
Ok I'll see it thanks.
Which channel/s is that?
-rt
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
The first guide link is for using the wokada ai voice changer
it also has a colab section in case your pc isnt good
You cant use it on mobile tho
Ok
for asking for helpof it go to #🔍│help-w-okada
The first one?
yea its the wokada one, what most people use
Ok thanks.
Yw
Who can help me? I want to create AI cover: I downloaded voice model, uploaded it to Google drive and opened access to it, but for some reason it does not want to be installed. Who knows what could be the matter?
Ayo? @fleet drift level 1 !!! 
what google colab are you using?
or are you doing it locally?
that colab is outdated
dont use it anymore
ok
Check this convo #✨│ai-help message
thanks
yw
i cant hear my voice changing, can someone help?
hello! someone help me pls. when i wanna convert voice in illaria RVC error is shown 😦 but model is worked in easy gui v2 and audio file too
my model sounds really robotic like, what can i do to fix it
are you using wokada realtime voice changer? Ask in #1192011222023950368 or #🔍│help-w-okada
can u send the model dowloand link?
also, is it the ilaria rvc colab or hugging face space?
maybe its better if you ask in #📑│making-models and remember that model quality, quantity and epochs matter
is colab
i trained it for 200 epochs, made sure it was clear and got 40 minutes
it just sounds robotic like
and alright sorry
u used the tensorboard?
its fine
when you get the error, show me a screenshot of the colab of ilaria rvc output if theres the error name here
yeah i tried
also, when you use iilaria rvc, its better if you manually check everything (like the index, audio, model) again to be sure everything works and convert it again
i couldnt read it well, first ever model yk yk
oh understood, upload an image of the tensorboard graph of the model in #📑│making-models , also read our docs which can help you making models too https://aihubdocs.github.io/en
Last update: Feb 22, 2024
alrighty
Hellooooo ❤️
Ilaria is showing me an error everytime
It's just a red box with the word error in it, I don't know why since I double checked everything out
If someone can provide me with an solution
can someone help me? there is a back vocal which is so persistent to not get seperated? I tried both UVR BVE and HP6.
RVC Guides (How to Make AI Cover)
Translation by country
update on the old RVC
Ayo? @storm holly level 1 !!! 
now downloading models doesn't work
what tool are u using?
i was using the colab one
which? send the link
i guessed correct
dont use that one, its outdated
check our docs that have updated colabs
the downloader instead of downloading it fucking puts the model on a spreadsheet updates the download count and shit
Last update: Feb 22, 2024
How many epochs should I make a 9 minute dataset with ov2?
The right epochs amount will always vary
On the size, length & quality of the dataset
https://aihubdocs.github.io/en/ check the epochs page to learn
Last update: Feb 22, 2024
Aim towards using TensorBoard instead
thanks
yw =3
Hi guys! I wanted to understand if it was possible to help you or add something, in this section where it is said to search for models in the forum you can add that unfortunately some of the models due to the elimination of the server on October 5th are not available in the #voice-models section https://aihubdocs.github.io/en/essentials/voice-models/
Hai I own the docs =3
Are those deleted models available somewhere?
Yes most of all on weights 😄
Like in my case some models didn't get ricovered and all of them fortunately are on weights
But my models aren't in applio website, idk why
hm I see
Are you sure it's necessary to put that?
I don't think it's going to affect newbies tbh
Ohh idk, maybe they search for some models in voice-models section and they don't find but you can decide because the doc is yours 😄
How do i download model in ilaria rvc?
why does applio take so long to convert?
However i didn't understand this why 
All my models aren't in applio website
the most recent yes, only the old one not
Hm I'll consider it. Some people used to ask why they can't find some models that used to be available
Thanks for the suggestion Kakao =3
https://aihubdocs.github.io/en/ check the Ilaria RVC page here
Last update: Feb 22, 2024
It's a complete guide
It depends on various things. But first, are you running it locally or through the cloud?
Ilaria is not working 😭
Please give more context so I can help you
!howtoask
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.

You welcome ! 😄
AttributeError: 'NoneType' object has no attribute 'tobytes'
Plz help 😭
website
Please don't beg for help or I won't help you
Did you read the docs?
Hugging Face or Colab?
the applio website
It has two websites. One hosted in Hugging Face and the other in Google Colab
Which one are you using?
yea
Ah
It still doesn't work
Ayo? @boreal shore level 1 !!! 
I have the same error like this
Remove the spaces of your audio file and upload it again
GirlOfTheYear instead of Girl of the Year
So i copied the model link here but uhhh theres no link to paste here in ilaria colab
There should be a Download tab
You need to let it run for longer
It looks fine for now
https://aihubdocs.github.io/en/ I recommend reading the TensorBoard page
Last update: Feb 22, 2024
Are you reading the docs?
https://aihubdocs.github.io/en/ here's a guide on how to use Ilaria RVC
Last update: Feb 22, 2024
It's in RVC → Cloud → Inference
I did read it and kinda understand but sometimes I doubt myself so I need like a 2nd opinion lol
since it looks like it overtrained on the d/total
It hasn't been training for much time so dw
You must let it run for longer until it's very evident it's OT
I think it overtrain now lol
And no need to get anxious, the checkpoints get saved either way
It's not going to ruin the model
mode collapse made me doubt it lol
Possibly. Let it run for longer
It's still doesn't work
but someone said that overtrain doesn't exist in high qulity studio recording
There are spaces on your audio file
more so barely noticable
Oh i see, i will try it
Remove the spaces of the file name and upload it again
Not working
Try rebooting the Colab
It's explained in the docs
In the Troubleshooting chapter
hmm, while using a spectogram my data set couldn't even top 10k hz, I do not know what causes that.
Maybe the quality is That indecent
Anyone knows what is causing that?
Where are you getting it from?
So I see.
My friend and I wanted to make a voice model of him
but it seems that whatsapp's compression is too agressive
Sheesh
looks like it will be a face to face occasion
what should I do if my voice is lagging too much?
I know it's that agressive but I had to verify
Make him record his voice with the phone's native voice recorder
Being lazy doesn't help I guess
Then he should send you the raw file
funky
I maybe have another alternative
Headset microphone is enough
Simply, I don't have money.
I mean, he told me if it's that good
he would employ me to be him
Audacity works fine
well
off I go
I do have other files but of a very low time
let me check if I work with them instead of a face to face recording sesh
yeah 2 mins will not be enough
It's work! Tysm 🥳
Poyo which one?
Is yours
There are plenty of Colab links
Np
But if I don't have Colab pro, is it safe to activate?
Yes, except for EasyGUI's Gradio
Si, a eso se refiere el Kirby
So Google didn't ban me for this? Right? 😅
La empresa multimillonaria es malvada.
Theoretically not.
But i wouldn't be so sure.
goofy ass dynamic 😭
Hello, I always get this error when trying to use the 2nd step on the Easy GUI for RCV v2:
JSONDecodeError Traceback (most recent call last)
<ipython-input-14-b114748cdea6> 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)
I suggest you to use Ilaria RVC.
@molten pecan Do you mind if I translate your Colab into several languages?
ill try, thanks
It really depends. Can we DM about it?
Yes
what's the least messy way to install applio?
Ayo? @storm holly level 2 !!! 
https://aihubdocs.github.io/en/ check the Applio page
Last update: Feb 22, 2024
I made a complete usage guide =3
nvmnd got it
5GB
if that's the compressed file i hate to see how massive the unzipped version is
Whats the difference between the normal installation and precompiled
One has a setup script that does a whole lot of stuff
The other contains all the executables already setup & everything
It is what it is. The precompiled pkg is just all dependencies stacked together
If you perform manual install, resulting disk usage is p much similar
So no pip install?
It is redundant
Ayo? @forest sluice level 31 !!! 
Only like CUDA is needed (should you choose that version)
now it just displays a generic "Error" message
Ayo? @old crypt level 1 !!! 
its not a pain on colab as you just need to run one cell to do it for you
Ik but like wouldnt using precompiled be faster
Or not i am not sure
i'm also having this error too
colab page ran through fine, links appeared and it didnt throw an error
I tried with different models as well
For people using ila rvc and having errors when converting try using mangio crepe instead of rmvpe in advanced settings or use this in the meantime until its fixed on the main:
https://colab.research.google.com/github/poiqazwsx/RVC-Notebooks/blob/main/Ilaria_RVC_Tempfix.ipynb
Open as Administrator
as i did both times
can I use applio without GPU ? will it work ?
I think no
Hm..
You can use Colab
using rvc things as Administrator messes things up
?
Sorry I didn't know
I don't use it locally. I don't know about that.
Sorry one more time
well it asks for run-install.bat but it's not in the folder
just dont tell people to run rvc things as Administrator
Okay sorry
Can someone help me with a problem here?
say the problem
Ayo? @dawn tendon level 1 !!! 
is that the old kalomaze colab
For some reason I can't use ai covers because the program doesn't let me and it did let me before so what is happening?
what's up with that one all of a sudden ?
What old?
Ok
the download model is bugged cuz it uses some dumb shit with loading it on a google spreadsheet and the gui is pooped cuz of huggingface hub
i made a fix but i just recommend using the newer one https://colab.research.google.com/github/poiqazwsx/RVC-Notebooks/blob/main/Easy_GUI_(for_RVC_v2%2C_with_crepe)_(with_improved_downloader).ipynb
Alright
- 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
- 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
- GPT-SoVITS (demo), by litagin Huggingface Spaces
here
Do not get mad
im just memeing dw
Hey, does re-training work when you stop the training and download the pth file?
?
um i need some help T_T
i just downloaded the voice changer program but
it sounds very weird and there is a huge delay showing
buf : 510ms
res : 8089ms (it went upto 200000ms)
same
How do i download it now?
Open the folder
Find the song_output folder Next, open the folder that is there and install this file (Penultimate)
You can also install back vocal and instrumental
Just make the window wider
i think it just updated right now
so refresh it and try again
ig
should work now
I see the song output but i don't see the rest of the staff
Show what the Console writes
Alright
Ayo? @dawn tendon level 2 !!! 
we've been over this already
Sorry, they already told me that.
True but.. Can you take a screenshot and send it here?
Oh No I mean 4 button below
That's what i did
:(
even tried switching google accounts
hang on
That's weird.
the first part doesnt take 5 mins to run anymore at least
I tried opening Ilaria RVC Colab and worked fine for me
i think
2nd code cell pls
i dont remember both parts having ticks (ive only ran the installation)
Is there a way to get free gpu?
Is there a way to get free gpu
unless im dumb and its always been like that
Is there a way to get free gpu?
wait
nah still not working idk why
I might have an idea wait...

!python3 app.py --colab became !source .venv/bin/activate; python3 app.py --colab
for both
because it's not persistent
i think i only pasted the first cell
do the 2nd one too
it's dirty but it works
it's the thing I mentionned like a week or so ago
get a clean env instead of inheriting colab's runtime that can just break at any given moment
aight added
@brittle wing

It doesn't show me the Url
screenshot 
thats the only kalomaze one
And that means?!
are you making a model or making covers?
Covers
- 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
- 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
- GPT-SoVITS (demo), by litagin Huggingface Spaces
Is it in the same page web am in?
what do you mean by that
Ok
it said the link here 
Si just need to press the button that said tunnel: Gardio?
First you need to do install ilaria rvc
I did it showed me the codes and staff
after finished you can click start
Tunnel gradio
Wait that all the installation finish
When is all complete you can click start tunnel gradio
I said didn't finish yet
Yes, when you finished all you can click there
How much is going to take?
Ayo? @dawn tendon level 3 !!! 
Not so much
It's still going for 2 minutes now
Try to wait max 5-8 minutes, unfortunately i don't know the time because i mostly use local and i don't use on colabs 😭
But i think 5-8 minutes max
I think the first start takes longer. But i think
Ok 😄
Now you can proceed with start gradio
I did
Ok now i think is always still loading
I got to the public url
Yes
You need to download the model first
Go on download voice models and you can put the huggingface link
How do i download it
Can you send it to me? I don't want to forget it
Sure i will send you in dm, but you can find also in official guide 😄 i send you also the link
Is a full guide about Ilaria RVC
You put the audio sample?
What sample?
For make cover, for example an mp3 audio or wav
for convert voice
Oh, you selected before click convert?
I can see the full screen if you want?
same
@half cove @glad zealot New error :DDD
Have you checked the colab terminal?
errors when converting
oh the tobytes one?
Oh Same, have you seen colab terminal?
What?
no matter what
If there is some problem
AAAAAAAAAAAAAAAAAAAAAAA
When you go on colab page if you see some error on terminal
that was the old error
Is the same page when you start ilaria rvc
with all those codes
yeah mangio-crepe works
gdrs thing only improved speed not fixing the error
@dawn tendon go to advanced settings and choose mangio-crepe
Never mind i did it
You resolved?
Yes
Ok 😄
If you encounter some other problems we are always here
wait Ilaria not working anymore? @dawn tendon
look at pins if you have errors on ila rvc
still not working
How do i remove the background noise? I tried to clean the dataset as much as i can, but i hear background sounds. How do i remove them?
It does work
poop
I know what's wrong with rmvpe
yea?
yea
weird

rmvpe downloaded suspiciously fast
<!DOCTYPE html><html><head><title>Google Drive - Quota exceeded</title><meta http-equiv="content-type" content="text/html; charset=utf-8"/><style nonce="objv2EdnWTkTax-o9jxeIw">.goog-link-button{position:relative;color:#15c;text-decoration:underline;cursor:pointer}.goog-link-button-disabled{color:#ccc;text-decoration:none;cursor:default}body{color:#222;font:normal 13px/1.4 arial,sans-serif;margin:0}.grecaptcha-badge{visibility:hidden}.uc-main{padding-top:50px;text-align:center}#uc-dl-icon{display:inline-block;margin-top:16px;padding-right:1em;vertical-align:top}#uc-text{display:inline-block;max-width:68ex;text-align:left}.uc-error-caption,.uc-warning-caption{color:#222;font-size:16px}#uc-download-link{text-decoration:none}.uc-name-size a{color:#15c;text-decoration:none}.uc-name-size a:visited{color:#61c;text-decoration:none}.uc-name-size a:active{color:#d14836;text-decoration:none}.uc-footer{color:#777;font-size:11px;padding-bottom:5ex;padding-top:5ex;text-align:center}.uc-footer a{color:#15c}.uc-footer a:visited{color:#61c}.uc-footer a:active{color:#d14836}.uc-footer-divider{color:#ccc;width:100%}.goog-inline-block{position:relative;display:-moz-inline-box;display:inline-block}* html .goog-inline-block{display:inline}*:first-child+html .goog-inline-block{display:inline}sentinel{}</style><link rel="icon" href="//ssl.gstatic.com/docs/doclist/images/drive_2022q3_32dp.png"/></head><body><div class="uc-main"><div id="uc-text"><p class="uc-error-caption">Sorry, you can't view or download this file at this time.</p><p class="uc-error-subcaption">Too many users have viewed or downloaded this file recently. Please try accessing the file again later. If the file you are trying to access is particularly large or is shared with many people, it may take up to 24 hours to be able to view or download the file. If you still can't access a file after 24 hours, contact your domain administrator.</p></div></div><div class="uc-footer"><hr class="uc-footer-divider"></div></body>

amazing
is there a new link for training on public url? the one i use doesn't work anymore
Ayo? @brittle wing level 1 !!! 
relevant line
so it downloads rmvpe when not present but the google drive file doesnt exist?
google drive limits the amount of downloads
we've reached that
It now returns a failure page instead of the file
Pixeldrain!?
oh fuck
and that failure page is saved as the model file...
so we can just replace it with somewhere else

should've been using that to begin with
if I had write access to either ilaria RVC's git or the colab, i'd be fixing it
hina will need fork it or ask ila to fix
ill do it rq untill hina wakes up
@sand iris yep
Did you ever use crepe-tiny?
I wonder what the difference was
Ayo? @glad veldt level 2 !!! 
I keep getting errors with this
@viscid moss 

I'm busy rn.
Try restarting the environment, that model works
*Doesn't
i get this error
D:\RVC1006Nvidia>runtime\python.exe infer-web.py --pycmd runtime\python.exe --port 7897
Traceback (most recent call last):
File "D:\RVC1006Nvidia\infer-web.py", line 8, in <module>
from infer.modules.uvr5.modules import uvr
File "D:\RVC1006Nvidia\infer\modules\uvr5\modules.py", line 14, in <module>
config = Config()
File "D:\RVC1006Nvidia\configs\config.py", line 35, in wrapper
wrapper.instance = func(*args, **kwargs)
File "D:\RVC1006Nvidia\configs\config.py", line 50, in init
self.json_config = self.load_config_json()
File "D:\RVC1006Nvidia\configs\config.py", line 68, in load_config_json
d[config_file] = json.load(f)
File "json_init_.py", line 293, in load
File "json_init_.py", line 346, in loads
File "json\decoder.py", line 337, in decode
File "json\decoder.py", line 355, in raw_decode
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
D:\RVC1006Nvidia>pause
Press any key to continue . . .
when trying to run bat file
Why does it give me an error?
Strange
It's a UVR bug
I run the same model and same settings
Hmmmm restart the environment
Sorry for my English. I have a bug:
JSONDecodeError Traceback (most recent call last)
<ipython-input-14-1d7b23896ae4> 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:
use the latest easygui colab
-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
- 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
- GPT-SoVITS (demo), by litagin Huggingface Spaces
nah
i will try with another acc
Okkie
Or try restarting the space
runtime > disconnect and delete runtime
RVC Guides (How to Make AI Cover)
Translation by country
a
Does anyone have a link to a working ilaria rvc?
It works as long as you don't use rmvpe
fix is known, just gotta have hina (who made the notebook) or ilaria (who made the GUI) fix it
I mean when trying to run the collab i just get an error
show the error
i put a temp one in pins until its fixed like always
Oh
fuck i cant spell

got it but now i cant download a model without an error

give me the link you used
for the colab?
still keep having errors with this
Take the lowest point in G
hi 🙂 can i ask for help on what to set rvc to maximize 3060 rendering?
Maximize 3060 rendering?
What do you mean?
oh, i see it already recognizes the GPU 3060, so i guess it's fine 😉
Ayo? @cinder crag level 1 !!! 
Well, i can give you an settings guide for each GPU type.
i thought that now it will set it up automatically for 3060, so there are other things to set? yes send me please 🙏🏻
Guide yourself by GTX 30 series
btw- couldn't yet understand at which folder i put the dataset?
you must put your dataset folder in the "datasets" folder of your RVC root folder
and this will be the path for the training folder? or that is another folder by itself? sorry for the confusion, coming from Colab
Yeah, training folder
Experiment name is the name of your model
training folder is the dataset ig
I thought I was the only one, I don't know how to fix it neitherrrr
Ayo? @royal pond level 1 !!! 
Someone help us, please
for people getting the model download error your prob using a old version of the easygui colab use this fix i made but havent tested or the newer one
old version fixed
new one recommended
fuck i cant make sense
old version fixed is the old one fixed that i havent tested
new one is the one i recommend you use
Ok, tysm ^_^
if your getting the error while infering in ila rvc look at pins
wait. sorry - so the path to the dataset folder should be inside the RVC app folder inside Pinokio? ---- D:\PINOKIO\api\rvc.pinokio.git ------- something like this?
Where is your RVC root folder?
isn't it the path i copied above?
Uhh, nop.
Also, why you didn't install RVC on C drive?
i preferred to install Pinokio on D for more space with all the renderings.. RVC is installed within Pinokio no?
Ayo? @cinder crag level 2 !!! 
What is even Pinokio?
I haven't heard about that in my life.
oh ok sorry 😄
when i download the model it says that there is not a valid pth file on the zip
What did you install?
and there is actually one
@glad zealot for when you wake up the problem was it downloading rmvpe from google drive and shi (gdr explains in the reply) you can fix by forking it and changing it to https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.pt
for example here:
https://colab.research.google.com/github/poiqazwsx/RVC-Notebooks/blob/main/Ilaria_RVC_Tempfix.ipynb
Both files weren't packed properly.
The structure of the model is: .pth and .index under a folder with the same name as the .zip of the model
It's not under a folder
i dont understand
create a folder called "hailey", and put the .pth and the .index files on that folder
alright
Pinokio is an app that you can install all the scripts inside for more easy gui experience.. like, i use Facefusion within the app, so it's great.. so you can also install RVC the same way, and you end up with the usual GUI window and tabs..
thanks<3
After that, convert the folder to a .zip file and reupload the file to your Drive
Or instead upload the model's zip to your Huggingface account
how do i do that
i cant run models
for sum reason
ModuleNotFoundError Traceback (most recent call last)
<ipython-input-2-5a694e04a2e4> in <cell line: 4>()
2 #@markdown Link the URL path to the model (Mega, Drive, etc.) and start the code
3
----> 4 from mega import Mega
5 import os
6 import shutil
ModuleNotFoundError: No module named 'mega'
You have already put the .index and .pth of your model in a folder?
right click "convert to zip"
In case you got winrar or 7zip
Oh wait
compress?
Ayo? @royal pond level 2 !!! 
JSONDecodeError Traceback (most recent call last)
<ipython-input-7-a372e2e58608> 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:
it said this too
ill extract it real quick
we all have the same problem help
alrrr
convert it to zip? i just downloaded the voice model
Ayo? @prisma fern level 1 !!! 
cant use UVR, i have this error :
Last Error Received:
Process: MDX-Net
If this error persists, please contact the developers with the error details.
Raw Error Details:
RuntimeError: "Unable to find a valid cuDNN algorithm to run convolution"
Traceback Error: "
File "UVR.py", line 6638, in process_start
File "separate.py", line 499, in seperate
File "separate.py", line 594, in demix
File "separate.py", line 635, in run_model
File "torch\nn\modules\module.py", line 1190, in _call_impl
File "onnx2pytorch\convert\model.py", line 224, in forward
File "torch\nn\modules\module.py", line 1190, in _call_impl
File "torch\nn\modules\conv.py", line 463, in forward
File "torch\nn\modules\conv.py", line 459, in _conv_forward
"
Error Time Stamp [2024-02-23 21:43:57]
Ayo? @grizzled heath level 1 !!! 
whats the difference between mmvc and rvc v2? Should I change to rvc instead?
your using the goofy ass kalomaze colab
read dis #✨│ai-help message
the colab still says that there isnt a valid pth file
i did literally what you said to me
the whole system buggin for me too
I am using the colab as well and getting this error:
JSONDecodeError Traceback (most recent call last)
<ipython-input-20-1d7b23896ae4> in <cell line: 31>()
31 if os.path.exists(config_path):
32 # File exists, proceed with creation of creds and client
did nobody read what i said
which one works
^
link ?
read
the new one
new one is better
is for making models? or
both
for me it just told me steps to make a model not use one
run the download cell then the ui cell (it says it doesnt work on free accounts but it should)
or use ila rvc
look at the pinned messages to find the colab for that as the main needs to be fixed
i think i finally fixed it
whatchu did rasp
how do I fix this shi
AttributeError: module 'huggingface_hub.constants' has no attribute 'HF_HUB_CACHE'
your using the old kalomaze colab
ok
-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
- 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
- GPT-SoVITS (demo), by litagin Huggingface Spaces

