✨│ai-help

[proper shale]

^

[silk brook]

so wait, first do I use RX10 or is that last after BSRoformer?

[proper shale]

It really depends, but I suppose if you're isolating audio you'd use BSRoformer and then RX10

[silk brook]

ok

and BSRoformer is in MVSep

[odd shale]

yep, it is

[silk brook]

is using uvr preferable?

[rare goblet]

Ayo? @silk brook level 4 !!!

[proper shale]

it really depends

[proud elbow]

for other models like BVE/karaoke 2, dereverb, etc.

[silk brook]

I see

[proper shale]

if you want no queues and some extra settings n stuff, go for it

[proud elbow]

also RX 11 seems good

[silk brook]

ok

would I use the ultimate vocal remover model?

[proper shale]

oh i thought u were talking about downloading UVR

mhhh

[silk brook]

no I was talking about downloading it

[proper shale]

yeah

[silk brook]

but if you reccmend this more

[proper shale]

so, it might be worth it

[silk brook]

I am just confused about the settings

I already have uvr downloaded

is that better?

[proper shale]

mhhh yeah it gives you more options

but idk, if this is easier for you

[silk brook]

its ok I already gots it

so whats your preffered stuff for uvr

[proper shale]

this is where my knowledge is terrible at

[silk brook]

ahahaha

[proper shale]

i think there's BSRoformer there, if not get it in the download center

[tacit tinsel]

Yeah amd doesn't go well, but in the changelogs they say they support certain amd gpus. :S

[proper shale]

They kinda lied 😭

[tacit tinsel]

🥲🥲🥲

[unique blade]

why dose my rvc sound nothing like the actor i want to sound like

[proper shale]

could be the model that ain't converting right (dataset/training issue), pitch range being completely different... etc

[unique blade]

ok ill try again

[proud elbow]

• probably "incompatible" accent, sometimes
• no index rate, as said
• too undertrained
• dataset prob contains different voices (including roleplayed voices)

[unique blade]

ok

[brittle wing]

Hey if u use ai covers I have a question how to run this rvc gui app? It’s crashing literally every time and I can’t use it I’ve made a lot of models but I am so sad I can’t use them any tips?’ 😭😭😭

Like when I want to open the rvc .bat it’s taking me to some black window and it’s writes “launching python server, click any key to continue” and when I do that it crashes and goes back to my screen. I tried thousands of rvc s like mangio easy gui NOTHING WORKS

and any key i tested my whole keyboard of keys and everything turns off that black screen wtf

And I want to do only one cover for my friend so bad! She wanted it so badly 😭😭😭 and I wanted to do her a surprise/like I have the models but can’t turn on the app to merge it with the music

[proper shale]

Mmm, I'd just use Colab at that point

Or maybe weights.gg - pretty easy to use

[azure marsh]

RVC Guides (How to Make AI Cover)

Documentation

📚 All-In-One English documentation

https://docs.aihub.wtf/

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

[brittle wing]

Can u tell me how, I never was good at this techno stuff but this one time I wanted to make one ai cover

[proper shale]

It's pretty straightforward if you do it via weights.gg

[brittle wing]

Okay I try thank u I’ll be greatful if that works 💗🫶

Oh.. god. How to use it!? Where can I upload my model it’s..

[proper shale]

Just go on the Create tab, click on the Create button below "Voice Conversion", and then you select the model & song you'll cover

The cover should be in "Creations" once finished...

[brittle wing]

Okay… and can I add my own voice model and my own song?

[silk brook]

hey mj coud I send you the song im working on

I wanna know what you think :)

[proper shale]

Yes

[proper shale]

Sure... why not

[brittle wing]

I don’t see I can add there my voice model?

It’s just says I can add SpongeBob or smth

[proper shale]

I meant you could search for the model you'd like

[brittle wing]

… okay then that’s not what I was looking for I have trained my own models and I want to use them in my “own” songs … if that makes sense at all

But thx

[rare goblet]

Ayo? @brittle wing level 2 !!!

[proper shale]

You could use Colab too (below is a guide on how to use Applio):

https://docs.aihub.wtf/rvc/cloud/applio-colab/

[brittle wing]

Okay I try that too..

God pray me it works 🙏🙏🙏

Hey what’s up with the hugging face can I add models which aren’t those?

Too?

[proper shale]

?

You can add models in Applio if that's what you mean, if they come from Huggingface especially

[brittle wing]

Mine are not from hugging face but I’ll try. Thx man! I’ll try it!

[proper shale]

🙏 you're welcome :)

[brittle wing]

OH MAN! THANK UUUU THANK UUUU! 💗💗❤️💗❤️❤️💗❤️❤️💗❤️

It works thank u for everything 😭😭😭❤️❤️❤️❤️❤️

[proper shale]

Glad I could help!!!

[upbeat vault]

hello

how do I use a voice model

every time I extract it doesnt show on RVC

[proper shale]

What RVC fork (program) are you using

[upbeat vault]

all good now

I sorted it with youtube

[lean orbit]

guys why when i uplaod audio and start converting it keeps processing forever

does that has something to do with the audio file ?

[proper shale]

ah

[proper shale]

what are you using to convert?

[lean orbit]

Ilaria RVC

[proper shale]

on colab orrr

[lean orbit]

yes

[proper shale]

mm

frankly idk if it's still working

[lean orbit]

it worked with two songs i made after this one

before*

sorry

[proper shale]

id just recommend using Applio in this case

https://colab.research.google.com/github/iahispano/applio/blob/master/assets/Applio.ipynb

[proper shale]

its alr

https://docs.aihub.wtf/rvc/cloud/applio-colab/

if u want the guide for it

[lean orbit]

thanks so much

i'll update if it did work

[proper shale]

yw, hope it works

[lean orbit]

so what's the average time does it take to convert

cause i tried and i think the problem is with the audio file

cause it's 300s in and nothing happened

[ionic oak]

Hello I come to ask you, what parameter and thing to modify on RVC so that the voice is like the basic one, without delay when I speak if possible?
thankss

[lean orbit]

it didn't work also 😦

[sinful lotus]

How can the problem of the application not using the video card even when it is selected to be used be solved?

[lean orbit]

does anyone know why it keeps processing forever ?

[rare goblet]

Ayo? @lean orbit level 2 !!!

[rapid marsh]

what if ther file i downloaded only has a pth file

how do i upload it

[vivid vigil]

When i use okada with vb cable for zoom, the other person who is on meeting, his voice also goes through okada and converts. Im using mac, can anyone help me in this issue?
In okada i use input -microphone, output vb cable
And in zoom i use input as vb cable and output as headset

[magic hare]

is there an alternative to llaria RVC? it keeps throwing errors when I try and convert

[brittle wing]

In Mainline RVC, is it possible to pause mid training?

To let my GPU chill down for a bit, and then resume training?

[lean orbit]

applio

but i have the same problem with iit

[lean orbit]

.

[magic hare]

I remember there was a collab thing like llaria, you just gave it the model link, audio file and then you could tweek settings like hop lenght

but I cant find it in the guides anymore

[lean orbit]

same

how do i know

it was working fine though i made two songs and it just stopped working

yes but appolio

let me check

i oppened Ilaria RVC

no its just three green dots

[dense marsh]

-colab

[azure marsh]

☁️ Google Colabs

• 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

How to use?

🤗 Hugginface Spaces

• 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

More commands: -audio, -local, -overtrain, -realtime, -rvc, -help

[lean orbit]

is there is limit to use collab ?

that's why

yes i used another account and it worked

thanks

[vagrant vector]

I want to start making ai covers and TTS which is easier and better to use for a beginner with an intel Mac? RVC or Applio?

Ok! So normal RVC for music and Applio for TTS?

[rare goblet]

Ayo? @vagrant vector level 3 !!!

[vagrant vector]

Oh ok!

[royal lark]

-colab

[azure marsh]

☁️ Google Colabs

• 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

How to use?

🤗 Hugginface Spaces

• 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

More commands: -audio, -local, -overtrain, -realtime, -rvc, -help

[proper shale]

If you're on AMD, that can happen - not much you can do about it other than converting models to ONNX

https://rentry.co/VoiceChangerGuide has a section talking abt that

[drifting rose]

Is it possible to ai cover a vocaloid song and make it sound not vocaloid

[proper shale]

Mmmm I think no, since the sudden pitch variations will be kept

[drifting rose]

How do i see people do it 😭

[rare goblet]

Ayo? @drifting rose level 3 !!!

[bold harbor]

which index should i be using i assume the trained on from the log folder?

[proper shale]

SynthV probably

[proper shale]

The added one, in logs folder yes

[bold harbor]

so added not the one that says trained

[proper shale]

yeah

[bold harbor]

gonna test it out thank you!

[rare goblet]

Ayo? @bold harbor level 1 !!!

[proper shale]

yw :)

[chilly estuary]

Can someone tell me why its cutting in discord but not in the rvc

[proper shale]

might be the speech threshold stuff in the settings, or the virtual cable

[drifting rose]

Can you use synthv with your own models?

[proper shale]

no, but it can be used to get the base audio

so you can convert

[drifting rose]

Oh yeah fair

Ill try that

[gray crow]

Hey guys, is applio with amd support available?

[glossy bough]

where can i find out how to train my own model?

[tacit tinsel]

i couldnt find any applio amd. I found rvc with amd but it doesnt find my gpu even tho i have an rx 6650 xt so idk

[gray crow]

i think zluda might be workiing

[tacit tinsel]

let me know if u have more luck 🙂

[gray crow]

https://github.com/vosen/ZLUDA

ZLUDA lets you run unmodified CUDA applications with near-native performance on Intel AMD GPUs.

[tacit tinsel]

can u let me know when u tried it out? would be nice

[gray crow]

Absolutely, will give you a ping. Probably not by today

[tacit tinsel]

https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/releases

rvc here has amd support but just didnt work for me

idk

[tacit tinsel]

great!

[bold harbor]

anyone up to hop in a call and just talk about experiance and stuff?

[proper shale]

Yeah Zluda might work

[drifting rose]

Does more audio footage make your model better or what is the recommended amount of footage that gives the best results

[proper shale]

More audio that includes variations of pitch and speech might make it better, yes

Around 10-20 minutes is alright for most models

[drifting rose]

Oh so 30 hours was too much?

[proper shale]

_ _

[drifting rose]

[proper shale]

how could you even

get

that much

😭

[spring orchid]

-colab

[azure marsh]

☁️ Google Colabs

• 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

How to use?

🤗 Hugginface Spaces

• 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

More commands: -audio, -local, -overtrain, -realtime, -rvc, -help

[proper shale]

that's pretrain level stuff

[drifting rose]

I am trying to make an ado model and i literally have every single word recorded that she has said 😭

[proper shale]

😭

[drifting rose]

I archived like basically everything on my pc

[proper shale]

have you trained it yet or

[drifting rose]

Yes but it had a bit of noise so its really rough

[proper shale]

😭

[drifting rose]

Im gonna try a smaller batch tomorrow lmao

But getting variations of pitch and speech should be easy enough

Ado can sing up to 4 octaves

[proper shale]

yeah get 5 mins of each variation if possible

or something like that

see what works best, experiment a lot

[drifting rose]

Do i need to like edit it into one audio file or can i keep it in separate ones and it would detect it or something?

The variations*

[proper shale]

Your choice, both will work

[drifting rose]

Alright ill try this + that beta uvr thing

Tomorrow

[proper shale]

Alrighty... good luck

[drifting rose]

Tyty i will keep you updated

[proper shale]

🙏

[drifting rose]

Also one last question do i need to edit out like silent parts

Or does that not affect it

[proper shale]

Yeah, do noise gating n stuff

[drifting rose]

Whats noise gating

[proper shale]

Basically, any noise below a certain threshold gets silenced

[drifting rose]

How do i do that

[proper shale]

Audacity should have that option

[drifting rose]

Is audacity free?

[proper shale]

yea

[drifting rose]

Alright thanks

Do you know if premiere pro has it

[still pumice]

Does anyone know why when I try to run the code for downloading a voice model that an error message keeps popping up that says "no module named Mega"?

I don't know anything about this stuff and I'm very confused lol

[proper shale]

That's an old Colab, use newer ones

https://docs.aihub.wtf/ has links and guides on the new ones

[proper shale]

Hmmm... I don't think so

[drifting rose]

Ill check tomorrow thanks for helping

[rare goblet]

Ayo? @drifting rose level 4 !!!

[proper shale]

You're welcome 🤗

[scarlet rover]

Can I get the latest update for Nvidia please?

[azure marsh]

RVC Guides (How to Make AI Cover)

Documentation

📚 All-In-One English documentation

https://docs.aihub.wtf/

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

[cosmic tiger]

I just downloaded applio rvc and tried 2 models, but the output audio is mostly the original audio, is there anything wrong in model, setting or is it supposed to be like this?

[proper shale]

For what program

[proper shale]

That can happen at times... might be the audio you're using or maybe the range of the model is different than the pitch in the audio

[scarlet rover]

the voice changer

[brave garnet]

Voicechanger Download (Okada)

⠀
Download for Nvidia GPUs
Version 18a cuda

Download for AMD GPUs
Version 18a directml

Download for Intel GPUs
Version 18a directml

Download for Mac
Version 17b Mac
⠀

Made with love by Ilaria 💖

[proper shale]

^

[scarlet rover]

thank you sm

[proper shale]

yw

[tacit tinsel]

what is index rate here?

[proper shale]

it's the index setting, helps apply the accent to the result

[tacit tinsel]

is that done during training or during infer?

ah or do you mean tts

[proper shale]

inference ye

[tacit tinsel]

ah ok, got it

[jovial spoke]

my tune is at 50 and my index is at 1

is that good

im on crepe

0.001 thresh

384 chunk

4096 extra

are these good settings and am i asking in the right place LOL

[thin stump]

#🔍│help-w-okada works too

It looks at a smaller sample so if your dataset is noisy, it's more easy for it to pick up on it. I'm kinda forced to use batch 4 since most of my datasets end up being 2-4 minutes

you can train a 15+ minute dataset with 4 and it'll turn out fine fyi

yw, but the default is usually going to be 8

You wouldn't need 5 hours because it's quality > quantity. Limit yourself to an hour and do a batch size of 16. And yes small datasets

20-30 minute is fine too (maybe batch 8 or 12)

Imo, there's more that you have to clean up if you add a lot of audio https://docs.aihub.wtf/rvc/resources/datasets/#range

This is my 30+ minute dataset I have to clean up. I'm manually denoising it instead of UVR or MVSEP

[pastel monolith]

can who help me

@thin stump can you help me

[thin stump]

Ask away

[pastel monolith]

when i open the voice changer its only show me cmd

[rare goblet]

Ayo? @pastel monolith level 1 !!!

[thin stump]

I don't use the voice changer sorry. You can also ask in #🔍│help-w-okada

[pastel monolith]

oh ok

[proud elbow]

RX 11 is out recently

[thin stump]

Depends on what you need. There's no new feature on rx11 besides dialogue isolate

[proud elbow]

RX 11 is mostly same as 10, only with some new additional modules.

music rebalance finally uses demucs instead of spleeter in 10

I see a new module Loudness Optimize, though no idea on it.

[thin stump]

The guide I always linked was outdated. That was technically Codename's old advice. The less processing the better #🔥│model-maker-chat message

that means no BS roformer if there isn't static noise etc

[vivid vigil]

can i run okada voice changer on my mac m1 and get good results (less lag) or will i need to run it on a GPU?

[thin stump]

hey get your model maker role bro, you already made good models except you just zipped it wrong

I'm not sure if it's different from audacity's resample. You can toggle a few settings here

[dusty warren]

can someone help me out i’m getting the error message “AttributeError: ‘NoneType’ object has no attribute ‘dtype’

[dusty mural]

how do i make ai covers

can someone give me a link

[proud elbow]

dialogue isolate tested #🔊│ai-development message

[thin stump]

weights.gg. Their cover creation is so quick

[rare goblet]

Ayo? @thin stump level 27 !!!

[brittle wing]

hey guys i have a problem im using rvc v2 from a tutorail and like i tried using a thing with my audio anad stuff and it said error

[rare goblet]

Ayo? @brittle wing level 1 !!!

[brittle wing]

i thought it was the mp3 file cuz i originnanlly used that but that didnt work

rhen i thought it was the output thing but t hat didnt work

[hot sable]

quiero modelos de ias para mi micro en latino alguna ayuda

[azure marsh]

RVC Guides (How to Make AI Cover)

Documentation

📚 All-In-One English documentation

https://docs.aihub.wtf/

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

[lilac glacier]

hi

how i train model in replay software without ios update

[jagged flax]

Hello, could someone send me a local rvc for ai covers + model training best for 16gb ram?

because im bored with the colab and huggingface ones

[jagged flax]

but for pc loacl

[jagged flax]

can it be ryzen 5 5600g integr?

[royal lark]

-colab

[azure marsh]

☁️ Google Colabs

• 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

How to use?

🤗 Hugginface Spaces

• 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

More commands: -audio, -local, -overtrain, -realtime, -rvc, -help

[rare goblet]

Ayo? @royal lark level 1 !!!

[proper shale]

Ya won't be able to train but you will be able to inference

[jagged flax]

i dont want to train cuz its not for me i cant do it

[proper shale]

mm

yeah it's gonna be alr then

inference shall take some time though, since itll use ur cpu

[azure marsh]

RVC Guides (How to Make AI Cover)

Documentation

📚 All-In-One English documentation

https://docs.aihub.wtf/

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

[idle briar]

inside the apps, is there possible to set output as microphone from iPhone?

[proper shale]

mmhhhh probably not

[brittle wing]

About the comparison between Colab and Locally.

Which one produces more temperature heat to my PC?

And which one trains faster?

I have RTX 2080 Ti.

[drifting rose]

@proper shale do you know which version of bsroformer works best for extracting vocals only

[proper shale]

Mhhhh you'd probably be able to train pretty well locally... ofc colab will be colder since it's just a website

[proper shale]

1296/1297 might do it

[drifting rose]

1296 made the audio bug a little

[proper shale]

mmm then 1297

[proud elbow]

colab is cloud compute that takes no load on your PC

[drifting rose]

ill try

[drifting rose]

also im supposed to remove the instrumentals and then use a karaoke model to get the backing vocals gone right?

[proper shale]

yeah

[drifting rose]

alright

[proper shale]

bsroformer then uvr bve yeee

[proud elbow]

1296 works a bit better generally, with overlap 4 for best balance
though 1297 can also work situationally

[drifting rose]

what does overlap do

also what does segment size do

[proud elbow]

https://docs.google.com/document/d/17fjNvJzj8ZGSer7c7OFe_CNfUKbAxEh_OBv94ZdRG5c/edit
for some technical stuffs

[drifting rose]

thanks

i have no clue where to find what im looking for

[brittle wing]

What technique or GPU that Colab use?

[frosty yacht]

Help.
Step 2 for the Google Colab method doesn't work-

[tame mica]

?

[frosty yacht]

What do you mean "?"-

[tame mica]

what guide

[proper shale]

use a newer colab - probably an outdated one

https://docs.aihub.wtf has links n guides for em

[ancient needle]

anyone know how to fix Illegal combination of I/O devices [PaErrorCode -9993]. I can't use any of my voices with it

[proper shale]

that happens when you're using 2 different types of... like, input

there's mme, asio, wasapi, stuff like that

just use one type of those

like mme

[ancient needle]

k thanks

[drifting rose]

@proper shale does a slight echo ruin a model

[proper shale]

i'd rather not keep it

[drifting rose]

so just use a different audio?

[proper shale]

ye

[drifting rose]

Ill try making a model with a livestream instead of songs for now

[brittle wing]

tried doing that but won’t let me

[drifting rose]

My graph isnt supposed to be going up and down right?

In tensor

I tested it at 100 epoch and it seems to be okay

[proper shale]

That can happen

[drifting rose]

I will

[brittle wing]

Is there any non local voice trainer?

[low shard]

Yep, you can use one of those google colabs for training rvc models:

• rvcdisconnected
• Applio

[manic plaza]

any noticeable difference between the audio outputs of RVC1 and RVC2

[azure marsh]

RVC Guides (How to Make AI Cover)

Documentation

📚 All-In-One English documentation

https://docs.aihub.wtf/

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

[manic plaza]

alright thanks

[low shard]

RVC v2 is better

[low shard]

its a bot lol

[manic plaza]

yeah and also RVC2 files are bigger

[rare goblet]

Ayo? @manic plaza level 3 !!!

[manic plaza]

RVC2 index files, three times the size of RVC1

[drifting rose]

Oh wait it was cuz my smoothing wasnt on lmao

[proper shale]

a

[drifting rose]

Im at 250 epoch and it still sounds a bit robotish

Maybe my audio file was rough

[solar lion]

how do I upload index and pth files to weights gg?

[brittle cypress]

any help helps

just got it kinda new

[proper shale]

you on AMD?

[brittle cypress]

nvidia

[proper shale]

yeah you got the wrong version for your gpu

https://rentry.co/VoiceChangerGuide read this, has download links and stuff

[brittle cypress]

alr

ty

this?

[proper shale]

ye

[brittle cypress]

alr

[brittle cypress]

looking better?

[proper shale]

just pick the gpu now, u should be good after that

[brittle cypress]

alr

ty

[fallow summit]

does anybody knows if i can use Titan Pretrain in the Ilaria Rvc ?

[proper shale]

for training, probably

for inferencing, no, it is not needed, pretrains r for training only

[fallow summit]

i know, but i dont know how to train with it

i put the g and d files in to the pretrain v2 folders

like it says in the tutorial

[proper shale]

now just copy their paths and put them in their respective lil box

[fallow summit]

I did, but i cant select them when im want to train

[proper shale]

oh is it one of those dropdown thingies from gradio?

where it has to be a certain option

😭

[proper shale]

keep as 32k, advanced options should have pretrain paths

[fallow summit]

hmm ok

[brittle cypress]

anything i need to change

?

[proper shale]

rvmpe_onnx as ur f0

[brittle cypress]

ok

[vivid vigil]

can anyone tell me what is the best recomended settings for F0 , Chunk and Extra when using L4 gpu on colab?
I am using index

[inner moat]

i cant get my outpout working can someone help me

[proper shale]

experiment tbh, but like 192/256 chunk, 8192 extra, use rvmpe_onnx as ur f0

[proper shale]

is the thing working inside w-okada or not? (set monitor to ur headphones)

[inner moat]

idk

thats how mine is et

set

[proper shale]

does it output anything?

[inner moat]

when i put my opout to my headphhones yes

[proper shale]

alrighty, so, have you tested it anywhere else, setting the input as the cable output?

[inner moat]

no

[proper shale]

try that, on Discord

[inner moat]

oh wait yeah i have

[proper shale]

mm

if the cable didnt work, i suggest trying vac lite then

[inner moat]

whats that

it semi works

but its like another mic combined

[proper shale]

disable monitor for a bit, and test it on discord only

[inner moat]

im trying reinstalling it

[cursive island]

Having the very same issue, I think something's broken in the code

[brittle wing]

yo guys i was training my voice for 2 hours and it said it has done it's job but the file isnt there. I think that was because i had like 700MB worth of free space on drive. Is there a way to recover the epochs with rvc disconnected with the logs or smth?

[rare goblet]

Ayo? @brittle wing level 2 !!!

[brittle wing]

i set the "save_frequency" to 15

[signal oracle]

do you have collab to train RVC v2 models?

[proper shale]

That's an outdated colab, check https://docs.aihub.wtf for the newer ones + guides

@signal oracle ^ has also training colabs (applio, rvc disconnected) links n guides

[signal oracle]

ok! thx!

[fresh nexus]

what is rvc?

[proper shale]

did it disconnect yet? if not, go to the weights folder inside Mangio-RVC-Fork and get those models asap

[proper shale]

Retrieval-based Voice Conversion

AI voice conversion

[fresh nexus]

Oh, thanks

[brittle wing]

where is that located?

[proper shale]

Colab file explorer, on the left side, inside Mangio-RVC-Fork folder

[brittle wing]

it has disconnected 3 minutes ago

is there any other option?

[proper shale]

mhhh, if it's not in your drive ya lost it

[jaunty flame]

what is the cmd to see rvc websites i forgot

[proper shale]

-colab

[azure marsh]

Suggestions for @jaunty flame

☁️ Google Colabs

• 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

How to use?

🤗 Hugginface Spaces

• 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

More commands: -audio, -local, -overtrain, -realtime, -rvc, -help

[jaunty flame]

ty

[manic plaza]

yeah true

[inner tulip]

hi i need help

how do i send pictures here

but i just started RVC but all im seeing is a white screen with no igons in it

[final hatch]

any link for kaggle? my version doesnt works anymore

or any other cloud (colab is shit)

[silk brook]

should I change quality to high?

[final hatch]

-kaggle

-colab

[azure marsh]

☁️ Google Colabs

• 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

How to use?

🤗 Hugginface Spaces

• 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

More commands: -audio, -local, -overtrain, -realtime, -rvc, -help

[wispy lodge]

You can try my kaggle notebook. Should be working fine
https://www.kaggle.com/code/suneku/voice-changer-public

[odd shale]

Hey bud.

Haven't you tried to apply for engineer or helper role?

[thorny violet]

where do i get help with rvc disconnected

[proper shale]

whats up

[thorny violet]

whenever i try to train, the code completes after only 15 seconds. it doesnt say an error occurred or anything like that

[proper shale]

mm? can you copy what it says?

[thorny violet]

yeah

Traceback (most recent call last):
  File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap
    self.run()
  File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "/content/Mangio-RVC-Fork/train_nsf_sim_cache_sid_load_pretrain.py", line 168, in run
    train_dataset = TextAudioLoaderMultiNSFsid(
  File "/content/Mangio-RVC-Fork/train/data_utils.py", line 18, in __init__
    self.audiopaths_and_text = load_filepaths_and_text(audiopaths_and_text)
  File "/content/Mangio-RVC-Fork/train/utils.py", line 274, in load_filepaths_and_text
    with open(filename, encoding='utf-8') as f:
FileNotFoundError: [Errno 2] No such file or directory: '/content/drive/MyDrive/rvcDisconnected/aishtick/%s/aishtick/filelist.txt'```

[rare goblet]

Ayo? @thorny violet level 1 !!!

[thorny violet]

damn only AFTER i send the thing can i post images thats rich

[proper shale]

using new pretrains with a sample rate it doesn't support, that's what i've seen causes it

atp just use original 😭 no issues with it anyway

[thorny violet]

but i am??

[brittle wing]

How

[proper shale]

_ _ wha

[thorny violet]

i accidentally ran index training before proper training could that be the problem

[proper shale]

ok shit

nah nah that doesnt cause that

[proper shale]

wait did u run this step

run that, and try again

:nailsP:

[thorny violet]

didnt work

[proper shale]

this is strange...

i didnt have this issue earlier today

[thorny violet]

how do i check my sample rate then? maybe original doesnt support the one ive got

[proper shale]

set training variables step

[thorny violet]

40k.. that should be fine tho

[proper shale]

yeah that should be fine

[brittle wing]

how tio get rid of background noise

[azure marsh]

RVC Guides (How to Make AI Cover)

Documentation

📚 All-In-One English documentation

https://docs.aihub.wtf/

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

[brittle cypress]

how to fix sounds robotish

[rare goblet]

Ayo? @brittle cypress level 2 !!!

[proper shale]

does this only happen outside of w-okada?

[violet heron]

Send a screenshot

And what virtual cable are you using

[frail swallow]

For multiple voices on a cover what does it want me to make my time stamps look like for each voice

[proper shale]

so it can apply voices for only one part of the song

[frail swallow]

Ik what its for but like how do i make one

[rare goblet]

Ayo? @frail swallow level 1 !!!

[proper shale]

just set the time stamps according to what you want, then it should just allow you to do it

i suppose that's weights.gg

[frail swallow]

Ok thx

[naive trench]

Why is the program not detecting the mic? Even when i setted it already

[rare goblet]

Ayo? @naive trench level 1 !!!

[proper shale]

Have you set monitor to your headphones? If so, did it give any output?

[naive trench]

Yeah, it worked yesterday but now the mic doesnt show anything

Like the mic stays in 0

[proper shale]

Check your command prompt

[naive trench]

Im trying to start the program rn

Im on the cmd but it takes so long

[naive trench]

Where is that

Im not that of an informatic mfer

[proper shale]

it's the cmd

[naive trench]

oh

Its like loading smth and telling me about an IP url

[proper shale]

mhm that's normal

[naive trench]

Yeah it happened a while ago also but im restarting so the program can detec the mic

Loading this on a daily basis is gonna be so boring omg

[desert niche]

Applio won't start and Idk why, it's just stuck on this :<

wait nvm it

it started

[naive trench]

I got the mic on output, the headsets at output and the monitor... The monitor lol

[desert niche]

well damn

now I'm getting this error

wait lemme try something

[glad zealot]

Put it on a folder path that doesn't have spaces

In the name

[desert niche]

The problem might be my username has a space in it

[glad zealot]

Put it somewhere like the D drive if you have

D:\applio

[naive trench]

Help

Ignore the photo btw

The vol stays in 0

[glad zealot]

#🔍│help-w-okada but does the console say anything?

[dire vapor]

how to use contentvec in rvc disconnected?

[warm fractal]

whats a good one to use

[naive trench]

I used this one https://vb-audio.com/Cable/index.htm

[warm fractal]

that one dont work for me

is there other ones

[violet heron]

Vac lite

[drifting rose]

@proper shale how can i improve this this is after training 500 epochs

[proud elbow]

https://software.muzychenko.net/freeware/vac470lite.zip is better

[naive trench]

Idk why the input is giving no sound to the rvc

[rare goblet]

Ayo? @naive trench level 2 !!!

[naive trench]

Help

[reef wedge]

thanks

ah

[rare goblet]

Ayo? @reef wedge level 1 !!!

[reef wedge]

emmm

something for mac?

}

help

[proud elbow]

double check the input/output. if u want to hear, set monitor to headphones or test on another app like discord

[brittle wing]

why does it say extension of file should be the following. index,bin

[untold mantle]

I'm having an odd problem. I try running GPU 0 which is most likely my GPU but once I press run, the program crashes and no voice can be heard

[minor bear]

how do i reduce useage on cpu and gpu

[violet heron]

Lower extra and chunk and use RVMPE

Or FCPE

[minor bear]

wich link is it

[rare goblet]

Ayo? @minor bear level 1 !!!

[violet heron]

No those are the settings that would reduce GPU and cpu usage

[minor bear]

where is the lnk to rvc

[violet heron]

-local

[azure marsh]

Suggestions for @minor bear

🖥️ Local stuff

• 🍏 Applio, 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
• GPT-SoVITS, by RVC-Boss GitHub

Need some help? 🤔

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.

More commands: -audio, -colabs, -overtrain, -realtime, -rvc, -help

[violet heron]

RVC is mainly used for covers, people use w-Okada more for real-time

[brittle wing]

What's the best extra interference time setting is good for a RX 580

[brave garnet]

RVC Colabs and Spaces

⠀

HuggingFace Spaces 🤗

⠀
Ilaria RVC
EasyGUI port with some improvements, by Ilaria.

RVC-HFv2
Applio port, by r3gm.

AICoverGen
AICoverGen port, by r3gm.

Advanced RVC Inference
Extended version of the GUI with advanced settings, r3gm.
⠀

Made with love by Ilaria 💖

[azure marsh]

RVC Guides (How to Make AI Cover)

Documentation

📚 All-In-One English documentation

https://docs.aihub.wtf/

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

[terse sequoia]

is it normal that i cant say sentences longer than like 3 sec without pause? everything else is fine

after 3 sec u cant recognize clearly the words

[edgy swallow]

can anyone tell me if this is safe to use? i have an rtx 4090 but idk if its safe

[terse sequoia]

what is safe?

[edgy swallow]

voice changer cause its been saying that virus has been detected

[proud elbow]

elaborate what are u using?

[terse sequoia]

the app is open sourced i think sure it is

the real time voice changer

[rare goblet]

Ayo? @terse sequoia level 3 !!!

[terse sequoia]

just curious if its normal

does saying long sentences without pause make any problem?

[proud elbow]

the voice changer doesnt cause it, prob some 3rd party app?

[terse sequoia]

feels like it cant handle that much of data at once

so i have to split the sentences into parts

it also happens when i simply just use the monitoring function to hear myself without discord or sth

[proud elbow]

im not sure if having some lag cuts the sentences

[terse sequoia]

btw increase chunk can improve the situation

maybe its the mod causing it

or the cpu spikes

i have a 12500f + rx6650xt

[unborn musk]

Is there a guide about how to use voice models ?

[spring chasm]

Which python version should I use for Applio?

[glacial sphinx]

can someone help me out? i did everything in the settings for a man voice model but it wont convert my voice (dm please)

[sinful quiver]

gyus which is better, or the diffrence? hubret and contentvec

[proper shale]

Both are used to detect speech in the audio you're converting. Test out and see, but apparently ContentVEC is better for speech

[proper shale]

Not needed. ContentVEC is for the inferencing part only... at least that's how Applio does it

[proper shale]

https://docs.aihub.wtf/

[proper shale]

3.9 or 3.10 I believe, but see if their documentation says otherwise

[proper shale]

Do you mind explaining your issue here?

Like, what are you using to convert, what happens, any logs if possible

[dire vapor]

thanks

[copper pebble]

@proper shale how much do you know of x minus?

[azure marsh]

RVC Guides (How to Make AI Cover)

Documentation

📚 All-In-One English documentation

https://docs.aihub.wtf/

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

[spring chasm]

operable program or batch file.```
How do I fix that?

It's already in env folder, already in C folder

[terse plover]

The system cannot find the path specified.```
How do I fix that?

[old oracle]

-colab

[azure marsh]

☁️ Google Colabs

• 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

How to use?

🤗 Hugginface Spaces

• 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

More commands: -audio, -local, -overtrain, -realtime, -rvc, -help

How do I know if my model is overtaining?

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

[proper shale]

barely nothing

[patent drum]

guys once you have downloaded a zip file how do i use it so my voice can sound like a character

[rare goblet]

Ayo? @patent drum level 2 !!!

[azure marsh]

Alex Director GOT BANANA LOL LOL LOL

HEY YOU @spring chasm YOU FUCKING GOT BANAN LMFAOOOOOOOOO
HEY YOU @spring chasm YOU FUCKING GOT BANAN LMFAOOOOOOOOO
HEY YOU @spring chasm YOU FUCKING GOT BANAN LMFAOOOOOOOOO

BRO GOT BANAN'D 1 TIME XDDDDDD

[proper shale]

https://docs.aihub.wtf/ has everything you need to know on how to use these

🙏

[patent drum]

Ok

[patent drum]

what's this for

[azure marsh]

THE FORTNITE BALLS LEADERBANAN

1. lusbert_ — 106
2. poopmaster_123 — 60
3. RayTracer — 40
4. timbovill — 21
5. antasma245 — 20
6. ravencutie21 — 10
7. wolfmk — 10
8. realpikachuwu — 9
9. highadmiralspire — 9
10. mrfurretgo — 8
11. kar2830 — 8
12. skyelightss — 6
13. notfelt — 6
14. kavis_123 — 6
15. chambeadorpro — 5

May 19, 2024, 12:38 PM

[proper shale]

Do you have any spaces in your folder names?

[proper shale]

just hoping stuff will go right yk

[patent drum]

ok

i'll try

[proper shale]

Yw :)

[drifting rose]

@proper shale

[rare goblet]

Ayo? @drifting rose level 5 !!!

[patent drum]

i'm not gonna lie i do not understand one bit of that

I kinda need help

[proper shale]

That sounds pretty decent... not sure there's a lot that can be done

[proper shale]

Just take your time, try to read carefully. It's made to be pretty easy on beginners.

[patent drum]

i'm not very good at that

all i have done is downloaded is a zip file of the voice i want

[drifting rose]

Oh ok

[proper shale]

You can always ask the Applio bot in #🤖│bots on how to use those, it could probably guide you on your way then

[patent drum]

Ok

[spring chasm]

no

[proper shale]

really not sure what's up then

[patent drum]

i give up i don't get it

i just want to use a goku voice 😭

[graceful anchor]

hey guys how can i record rvc into the daw??

[proper shale]

You can just convert normally

[proper shale]

You can always use weights.gg

To convert

[proper shale]

And then add that audio to the DAW

If you're using realtime you can set the input in the DAW to the virtual audio cable

[glacial sphinx]

can i dm?

[proper shale]

I'd rather you explain your issue here, so someone with a similar issue can search and find the solution for it.

[graceful anchor]

thank you so much

[proper shale]

You're welcome :)

[lapis tinsel]

Hi everyone

Does it work fine even if I load it with crackles or noises when creating the model?

[rare goblet]

Ayo? @lapis tinsel level 5 !!!

[patent drum]

that doesn't have goku

[proper shale]

https://weights.gg/models/clt57lpmg007pue3t6ww1zcw6

It does

[patent drum]

oh

ok

thank you

[proper shale]

You're welcome :)

[patent drum]

i've made a model but when i go to created models there is nothing there

@proper shale

[proper shale]

have you uploaded it there orrr

and btw, if you made a model on weights... it takes time to train yk

should be in the creations part

[patent drum]

i clicked on create this model

use this model i mean

[terse plover]

You have been rate-limited; you can retry this action later. If you're a new user, your limits will raise progressively over time. Get in touch with us at [e-mail] if you need access now. on RVC_HFv2 how do i fix im trying to duplicate the space. I made a new account

[rare goblet]

Ayo? @terse plover level 1 !!!

[proper shale]

Yes... now it should prompt you with what audio you want to use, or something similar

[patent drum]

i did

[proper shale]

Mmm. I suggest waiting for a while...

Like, an hour or so

But tbh I don't think Huggingface Spaces is a good idea rn

[terse plover]

ohh okay😀

[terse plover]

why not

whats better in your opinion

[proper shale]

Considering we have Colabs that are wayyy faster

(HF spaces use CPU....)

[patent drum]

how long do i have to wait for it

[rare goblet]

Ayo? @patent drum level 3 !!!

[terse plover]

which collab would you recommend

[patent drum]

yeah

[proper shale]

should take a little bit, check the creations part

[terse plover]

-collab

fcuk

[proper shale]

Either Applio or Ilaria RVC

https://colab.research.google.com/github/iahispano/applio/blob/master/assets/Applio.ipynb

https://colab.research.google.com/drive/1mHKTGH5e3SAyDSBss1KtiYRbDdQzwSMs

https://docs.aihub.wtf/ has guides for both of em if you need it

[proven hill]

I HEARD ILARIA RVC IS GOOD......... BUT I DONT KNOW MAN:................

[terse plover]

which model file is used for those

[proven hill]

any models

[terse plover]

oh is it😉

[proven hill]

yea bbg

[terse plover]

[patent drum]

creation part?

[proper shale]

HAHAHAHAHAHAHA

[proven hill]

i dont know much about rvc tho im just speaking for what i heard in the block

the discord block

[proper shale]

My Creations

[proper shale]

Mhm mhm

I don't know who that Ilaria girl is but idk I like her Ilaria RVC

[patent drum]

oh ok

oh thank you

i'm gonna listen to it

[proven hill]

ILARIA IS A WOMAN????????? THATS CRAAAAAAAAAAAAAAAAAAAAAAZYYYYYYYYYY

[patent drum]

how do i do text to speech instead of audio @proper shale

[odd shale]

Applio has TTS afaik.

[patent drum]

i mean on weights

[odd shale]

On that part, umm.. I don't know, sorry.

[patent drum]

Ok

[odd shale]

I don't really use weights.

[patent drum]

K

nvm i figured it out

[proper shale]

ah

have the screenshot bcuz its high effort

[wispy lodge]

Hey, nah, not yet

[cedar kindle]

do i need to get a song and remove the vocals just to make the ai voice sing it instead?

[proper shale]

yeah it should be vocals only

[cedar kindle]

so i just get any song i just remove vocals

[patent drum]

yeah i found out anyway

[cedar kindle]

also whats this website

[patent drum]

or search acapella

[patent drum]

called weights.gg

[cedar kindle]

ok

[patent drum]

here is a link https://www.weights.gg

your welcome

[proper shale]

yep

[cedar kindle]

ok

[rare goblet]

Ayo? @cedar kindle level 1 !!!

[patent drum]

almost finished

13 more

and now it's finished

yes

[cedar kindle]

how long does it normally take for the cover to be done with weight.gg

[proper shale]

It depends on the queues... a few minutes and it should be done

[cedar kindle]

alright thanks

its quite fast unless if you are using like a very popular character

[proper shale]

Mmm

Interesting

I've just started using Weights for covers recently sooo good to know

[tame iron]

How can i use titan pretrain?

[pastel oak]

You can just download them and put them in the pretrained_v2 folder

If youre using colab then the main developer should have it available already for selection

[tame iron]

ok

[pastel oak]

For local
#1236445948834611260 message

[brittle wing]

guys uhh while training with rvcdisconected ive stumbled upon a problem

when trying to download dependencies i got a warning that had something to do with cpu

[tame mica]

do u have a gpu on colab

[brittle wing]

i uhh

didnt have that warning yesterday

so i guess i did

[tame mica]

ooh wait

[brittle wing]

but i dont anymore

[tame mica]

so it's fixed?

[brittle wing]

uhh

no

[tame mica]

oh wait

[brittle wing]

it worked yesterday

[tame mica]

do u have any runtimes left

[brittle wing]

unsure

how do i check that?

[tame mica]

top right do u have the thing like this

[brittle wing]

-colab

[azure marsh]

☁️ Google Colabs

• 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

How to use?

🤗 Hugginface Spaces

• 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

More commands: -audio, -local, -overtrain, -realtime, -rvc, -help

[brittle wing]

anyone got a clue on how to fix this

i think my gpu usage time is over

if i remember correctly that's what the warning said when i tried to run Dependencies

oh

okay, thanks

[tame mica]

bruh

[proud elbow]

you would have gotten the message "could not connect to GPU backend due to usage limit" when trying to connect & run

[brittle wing]

yeah

i did

i just forgot what it said so i didnt mention it

now that i look at it it seems stupid

but i switched to an alt and it worked

[proud elbow]

good

[tacit tinsel]

hi upon starting applio i get this error "import gradio as gr
ModuleNotFoundError: No module named 'gradio'"

[rare goblet]

Ayo? @tacit tinsel level 4 !!!

[tacit tinsel]

it was ok yesterday

[fallen rivet]

guys im trying to extract all files on rvc so it works, and the time remaining keep switches between 29 minutes.. AND 6 HOURS

[tame mica]

there's many files so

[fallen rivet]

oh ok

sooooooo

how long will it acutally take

[proud elbow]

use ssd to extract a million of few KB files

[fallen rivet]

huh

[rare goblet]

Ayo? @fallen rivet level 1 !!!

[fallen rivet]

wat ssd

[proud elbow]

nvm, not really an issue if u wait patiently enough

[fallen rivet]

lol ok

[proud elbow]

what I know is, old laptop HDD and flash drives are so slow when copying/extracting lot of small files

[fallen rivet]

uhh i use a dell laptop running windows 10

[brittle wing]

tried making a model with rvcdisconnected twice

[rare goblet]

Ayo? @brittle wing level 3 !!!

[brittle wing]

every time i have tried it said that it's done or whatever

and it didnt give me the file

what am i doing wrong

it gave me the index file and the logs

but no actual model

[proud elbow]

there is 3 hour daily limit or depend on how often u run colabs. set lower target epoch or stop when needed, then run "export model to Drive"

[brittle wing]

you mean this?

also i have only tried to make the model once today

so the limit shouldnt be a problem

oh wait nvm i found the "Export Model from Notebook to Drive"

[shrewd peak]

hmm it seems to crash when i turn the program on

[brittle wing]

is it required to upload the model to huggingface to use it?

[tacit tinsel]

in which path should the .pth be for rvc local version? cant find under logs

doesn tensorboard only works with gpu?

[brittle wing]

is this supposed to take this long?

[violet heron]

What’s your GPU?

[fallen rivet]

idk

[violet heron]

Check in task manager

[tame mica]

using a cpu w rvc significantlu slows it down btw

[fallen rivet]

the completion is still 33% now lol

[brittle wing]

i've reached the 10 minute mark

[tame mica]

u can train using cpu but another member said it takes 5-10 mins each epochs

[brazen coral]

watafak

why am i in this

thing

or wtv

😭🙏🏻

[tame mica]

me everyday when i wake up

[proud elbow]

old cpu

what separation model tho?

[brazen coral]

this is scary

why am i here

im gonna touch u guys bro.

[tame mica]

??

[brazen coral]

wtf

who added me in this

thing

[rare goblet]

Ayo? @brazen coral level 1 !!!

[brazen coral]

🥰

[tame mica]

maybe u joined and forgor

[azure marsh]

RVC Guides (How to Make AI Cover)

Documentation

📚 All-In-One English documentation

https://docs.aihub.wtf/

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

[tacit tinsel]

is it possible to generate index with applio web ui without a gpu ?

i got this error in console while generating index for training

ValueError: need at least one array to concatenate

[violet heron]

-local

[azure marsh]

Suggestions for @brittle wing

🖥️ Local stuff

• 🍏 Applio, 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
• GPT-SoVITS, by RVC-Boss GitHub

Need some help? 🤔

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.

More commands: -audio, -colabs, -overtrain, -realtime, -rvc, -help

[violet heron]

Or -colab

-colab

[azure marsh]

☁️ Google Colabs

• 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

How to use?

🤗 Hugginface Spaces

• 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

More commands: -audio, -local, -overtrain, -realtime, -rvc, -help

[native parrot]

i have downloaded a voice model from huggingface. how do i train this model: "RVC Disconnected, by Kit Lemonfoot Google Colab". It says that the dataset requires wav format audio files but i only got an Index and a .PTH file

[tame mica]

if you get a .pth and an index, it is already trained. you can just use it

[proper shale]

well the index and .pth are a model file

[iron sapphire]

where do i get the pre-trained base models G and D from? sry it's been a while

[rare goblet]

Ayo? @iron sapphire level 1 !!!

[brazen coral]

From dark web

[iron sapphire]

sure ok whatever

[brazen coral]

bruh

im gonna touch u bro

[native parrot]

uhhh okay, what do i put here then? Advanced: Set your pretrain type to "custom" and input HuggingFace links to your G and D files here.

[rare goblet]

Ayo? @native parrot level 1 !!!

[tame mica]

are you possibly related to slitter and ketchup

[tame mica]

? you dont have to train it

[brazen coral]

yes

edgeking

[tacit tinsel]

is it possible to generate index with applio web ui without a gpu ?
i got this error in console while generating index for training
ValueError: need at least one array to concatenate

[brazen coral]

no

[native parrot]

OH

SORRY

😭

[tame mica]

dw gang

[tacit tinsel]

where should it idealy be after generated?

[violet heron]

No you need a GPU to train locally

[proud elbow]

you got a finished model, not a dataset needed to train

[violet heron]

Use the applio colab instead

[native parrot]

yes, im slow 😭

[brazen coral]

hard

are u hard

[tacit tinsel]

too many errors, didnt work for me. I am training with cpu but it cant generate an index which is the problem

[iron sapphire]

?

[violet heron]

How tf did you train a model without a GPU

[tacit tinsel]

it creates pth file and different epochs

[iron sapphire]

it's not showing up in my files

[brazen coral]

im coming

[violet heron]

ik

[tacit tinsel]

but no index, which i also need

[violet heron]

Try using the colab again

The errors mean nothing half of the time

[iron sapphire]

ok so i think its just v2 that isnt showing up for me

[native parrot]

can i run this model on colab?

[tame mica]

yea

inference notebooks are hard to come by though

[brazen coral]

i have no idea what yall r talking abt

but i want what yall r on

edgekings

[violet heron]

Discord

||and meth idk||

[native parrot]

oh

[proud elbow]

[native parrot]

locally then

[brazen coral]

oh..

sure

im gonna touch u bro

[violet heron]

You can’t touch me… I’m already touched

[brazen coral]

..

Still gonna touch u

[violet heron]

ok

[brazen coral]

are u coming

edgeking

[brazen coral]

i came

a tear ran down my legs

sorry yall i got emotional

[brazen coral]

shut up

[rare goblet]

Ayo? @brazen coral level 2 !!!

[brazen coral]

u

timblori

tyrannosaurus

[tame mica]

timbovile

[brazen coral]

shut up

car

[pearl mountain]

---------------------------------------------------------------------------
ModuleNotFoundError                       Traceback (most recent call last)
<ipython-input-1-5dd4fdc9f6d6> 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'

---------------------------------------------------------------------------
NOTE: If your import is failing due to a missing package, you can
manually install dependencies using either !pip or !apt.

To view examples of installing some common dependencies, click the
"Open Examples" button below.
---------------------------------------------------------------------------

what is this error?

[brazen coral]

bounce on my dick

ops

wrong gc

[violet heron]

What was your download link?

[brazen coral]

i aint reading allat

omegas

[pearl mountain]

https://huggingface.co/liilliliiiliil/GenshinImpact_Klee/resolve/main/Genshin Impact_Klee.zip?download=true

[violet heron]

Try without the ?download=true

Wait nvm

Remove the from mega import mega part

In the cell

[native parrot]

i have downloaded this voice model. how do i run this locally: https://huggingface.co/OwlCity/OwlCityRVC/resolve/main/OptimusPrime07ROTFDOTM.zip?download=true

[proud elbow]

seems like old colab

[pearl mountain]

Is it an old link? What is the latest link?

[rare goblet]

Ayo? @pearl mountain level 1 !!!

[violet heron]

-local

[azure marsh]

Suggestions for @native parrot

🖥️ Local stuff

• 🍏 Applio, 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
• GPT-SoVITS, by RVC-Boss GitHub

Need some help? 🤔

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.

More commands: -audio, -colabs, -overtrain, -realtime, -rvc, -help

[violet heron]

-colab

[azure marsh]

Suggestions for @pearl mountain

☁️ Google Colabs

• 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

How to use?

🤗 Hugginface Spaces

• 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

More commands: -audio, -local, -overtrain, -realtime, -rvc, -help

[pearl mountain]

Thank you!

[brazen coral]

ur welcome

edgeking

[tame mica]

since when did you help

edgequeen

[brazen coral]

bruh who helped u come

edgeking

[tame mica]

you

[brazen coral]

memory loss

yes

[tame mica]

edgequeen

[brazen coral]

im a man

[tame mica]

index go to logs and pth go to weights

[brazen coral]

spread ur legs

[tame mica]

edgepeasant

[brazen coral]

edge

i edge to ur pics

[tame mica]

edgemaster

[violet heron]

Microsoft edge

[brazen coral]

edgeboss

next edgeskibidiboss

[tame mica]

show us how u #edge

[violet heron]

Bill Gates

[brazen coral]

timbovilla

bend over

[fallen grotto]

why is it just static noise when i convert an audio

[brazen coral]

ilove1989tv is typing

because it means there cum in uit

[violet heron]

Send a screenshot of your settings

[fallen grotto]

the advanced settings?

[violet heron]

Normal settings

[fallen grotto]

is it this one or something else

[violet heron]

Inference

[brazen coral]

https://tenor.com/view/edge-gif-24763835

[fallen grotto]

do i like need to change something because i never encountered one of these before

what does the embedder model mean?

[violet heron]

Try changing the Voiceless Audio one

I use default settings expect for like index ratio

Make sure it’s not static if you convert using a different audio or model

[fallen grotto]

is it the voiceless consonant

[violet heron]

Yes

Try adjusting that maybe?

[fallen grotto]

im gonna try setting it to 0

[brittle wing]

Hello how to set the sonic shadow sound to be good?

[real quarry]

anyone know how to fix this error in step 2? is the JSON error

[brazen coral]

no one knows

edgekings

[plush compass]

Everyone Use the volume envelope of the input to replace or mix with the volume envelope of the output. The closer the ratio is to 1, the more the output envelope is used: What value do you give for the option?

[brazen coral]

shutup

[brazen coral]

no there is not

[leaden sigil]

"Traceback (most recent call last):
File "F:\downloads\ApplioV3.2.0\ApplioV3.2.0\env\lib\site-packages\gradio\queueing.py", line 528, in process_events
response = await route_utils.call_process_api(
File "F:\downloads\ApplioV3.2.0\ApplioV3.2.0\env\lib\site-packages\gradio\route_utils.py", line 270, in call_process_api
output = await app.get_blocks().process_api(
File "F:\downloads\ApplioV3.2.0\ApplioV3.2.0\env\lib\site-packages\gradio\blocks.py", line 1908, in process_api
result = await self.call_function(
File "F:\downloads\ApplioV3.2.0\ApplioV3.2.0\env\lib\site-packages\gradio\blocks.py", line 1485, in call_function
prediction = await anyio.to_thread.run_sync(
File "F:\downloads\ApplioV3.2.0\ApplioV3.2.0\env\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
File "F:\downloads\ApplioV3.2.0\ApplioV3.2.0\env\lib\site-packages\anyio_backends_asyncio.py", line 2144, in run_sync_in_worker_thread
return await future
File "F:\downloads\ApplioV3.2.0\ApplioV3.2.0\env\lib\site-packages\anyio_backends_asyncio.py", line 851, in run
result = context.run(func, *args)
File "F:\downloads\ApplioV3.2.0\ApplioV3.2.0\env\lib\site-packages\gradio\utils.py", line 808, in wrapper
response = f(*args, **kwargs)
File "F:\downloads\ApplioV3.2.0\ApplioV3.2.0\tabs\train\train.py", line 152, in save_drop_model
os.rename(dropbox, pretrained_path)
OSError: [WinError 17] The system cannot move the file to a different disk drive: 'C:\Users\ccateni\AppData\Local\Temp\gradio\f583bd59348a1c7ae4a5c03e41f71ba21c0c01f8\D-f032k-TITAN-Medium.pth' -> 'rvc\pretraineds\pretraineds_custom\D-f032k-TITAN-Medium.pth'"

I assume this is due to being on an external drive instead of C drive?

I downloaded the Compiled release and unziped it.

Is there a way to run it on stuff other than the C drive since it does take up a lot of space?

[violet heron]

Yes

Just select the model

And don’t select the index when uploading

Most people don’t use the index anyways

[tacit tinsel]

what is the index for?

can i see on colabs how long i still have the connection to their workstation ?

[thin stump]

The index is the model's accent. That gets saved to the rvc disconnected folder if you ran the training cell. You can view runtime by clicking on T4

or ram disk

[white roost]

the console crashes

[brazen coral]

edgeking

[rare goblet]

Ayo? @brazen coral level 3 !!!

[tacit tinsel]

thank you

[azure marsh]

RVC Guides (How to Make AI Cover)

Documentation

📚 All-In-One English documentation

https://docs.aihub.wtf/

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

[low shard]

You are using an outdated colab, check our docs https://docs.aihub.wtf/

[low shard]

That just depends on the model lol

[trim star]

Hey guys, it took a lot of time to master some skills at doing covers or make your own vocals to infer it with another singer (if you can't sing) and found precise ways to make it sound as much natural as any other tracks out there.

1. Picking up the best clean vocals (DRY), no back vocals, no reverb, plain and simple dry. There multiple methods you can find in this discord group with UVR or MVSEP.

2. Infer main vocals using no enveloppe, adjust index as you need, remove filter option and protecting option, infer using RVMPE for coarse vocals or Mangio-Crepe for smoother vocals.

3. (Optional) Infer back vocals for certain parts you want some lower back vocals, -12 semi tone, same settings.

4. Infer another one using less index (around 25) but keeping still the model's voice timber. Add enveloppe if you need, adjust as needed, it just needs to sound different from the main vocals, otherwise you'll have some phasing issues.

5. (Use with caution, analyse the audio) Denoise all vocals using tape.it/denoiser it's a great tool for denoising.

6. Import everything (instrumental and all infered vocals) in any DAW you work with and assign everything to individual channels.

7. Main vocals plugins

• GOYO - Clear (Now Supertone Voice Separator) to lower ambient noise (it actually removes the robotic feeling of the vocals)
• Use a side enhancer, I use Ozone Clarity.
• Dynamic EQ (For stereo control)
• (Important) shaping up low ends accordingly (Inferred vocals messes up with the bottom frequencies, I don't recommend bass boosting, I recommend shaping it dynamically, it definitely needs more low frequencies)
• (Optional) Vocal slap delay (SEND)
• Dynamics for a more modern crisp or simply adding more richness and depth
• (Very Important) De-Esser, but be careful with it. It can be powerful when used correctly with precision. I use Waves Siblance for this, with a 20% detection, -100 threshold and -10db range only, it really picks up the ESSES, HISS, FFF, u get it..

[leaden sigil]

Now my copy of apollio isn't working. I moved it to C drive and its the latest version.

now this shows up.

Sync graph is now activated! With sync graph enabled, the model undergoes a single epoch of training. Once the graphs are synchronized, training proceeds for the previously specified number of epochs.
Starting training...
Loaded pretrained_G rvc\pretraineds\pretraineds_custom\G-f032k-TITAN-Medium.pth
Process Process-1:
Traceback (most recent call last):
File "C:\ApplioV3.2.0\ApplioV3.2.0\rvc\train\train.py", line 284, in run
latest_checkpoint_path(hps.model_dir, "D_*.pth"), net_d, optim_d
File "C:\ApplioV3.2.0\ApplioV3.2.0\rvc\train\utils.py", line 139, in latest_checkpoint_path
x = f_list[-1]
IndexError: list index out of range

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\ApplioV3.2.0\ApplioV3.2.0\env\lib\multiprocessing\process.py", line 315, in _bootstrap
self.run()
File "C:\ApplioV3.2.0\ApplioV3.2.0\env\lib\multiprocessing\process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "C:\ApplioV3.2.0\ApplioV3.2.0\rvc\train\train.py", line 300, in run
torch.load(hps.pretrainG, map_location="cpu")["model"]
File "C:\ApplioV3.2.0\ApplioV3.2.0\env\lib\site-packages\torch\serialization.py", line 1014, in load
return _load(opened_zipfile,
File "C:\ApplioV3.2.0\ApplioV3.2.0\env\lib\site-packages\torch\serialization.py", line 1422, in _load
result = unpickler.load()
File "C:\ApplioV3.2.0\ApplioV3.2.0\env\lib\site-packages\torch\serialization.py", line 1392, in persistent_load
typed_storage = load_tensor(dtype, nbytes, key, _maybe_decode_ascii(location))
File "C:\ApplioV3.2.0\ApplioV3.2.0\env\lib\site-packages\torch\serialization.py", line 1357, in load_tensor
storage = zip_file.get_storage_from_record(name, numel, torch.UntypedStorage)._typed_storage()._untyped_storage
RuntimeError: PytorchStreamReader failed reading file data/7: invalid header or archive is corrupted
Traceback (most recent call last):
File "C:\ApplioV3.2.0\ApplioV3.2.0\rvc\train\train.py", line 720, in <module>
main()
File "C:\ApplioV3.2.0\ApplioV3.2.0\rvc\train\train.py", line 159, in main
edit_config(model_config_file)
File "C:\ApplioV3.2.0\ApplioV3.2.0\rvc\train\train.py", line 148, in edit_config
config_data["train"]["log_interval"] = steps
NameError: free variable 'steps' referenced before assignment in enclosing scope
Saved index file 'C:\ApplioV3.2.0\ApplioV3.2.0\logs\Snootz32k\added_IVF122_Flat_nprobe_1_v2.index'

[still pond]

Billie Eilish (RMVPE) (RVC2 600 Epochs) posted by Maru. HuggingFace download link isnt working:

Or to be more exact i'm getting an error message "invalid username or password" which might indicate the link is broken/moved or a deleted user

https://huggingface.co/marup/BillieEilish600Epochs/resolve/main/Billie.zip?download=true