✨│ai-help

[rare goblet]

Ayo? @pearl python level 1 !!!

[slim geyser]

you can do it for free on the no-ui notebooks

you can only use it for like 2 hours a day or something tho

[pearl python]

idk what is a "no-ui notebooks"

[pearl python]

oh damn

i'm currently watching a video of a guy showing a tutorial for something called "Applio RVC"

[proud elbow]

dual boot then

but still colab recommended for less hassle

[odd shale]

Actually don't use video tutorials

these tend to be outdated

read the docs instead

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

Btw, ZONE-TAN????

[pearl python]

alr thanks i'll do this later

[odd shale]

zone tan replied to me!!!!!!!111!!!!!

[pearl python]

[barren canopy]

To create a public link, set `share=True` in `launch()`.
D:\Applio\ApplioV3.2.0\env\lib\site-packages\gradio\processing_utils.py:587: UserWarning: Trying to convert audio automatically from int32 to 16-bit int format.
  warnings.warn(warning.format(data.dtype))
ERROR:    Exception in ASGI application
Traceback (most recent call last):
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\uvicorn\protocols\http\httptools_impl.py", line 411, in run_asgi
    result = await app(  # type: ignore[func-returns-value]
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\uvicorn\middleware\proxy_headers.py", line 69, in __call__
    return await self.app(scope, receive, send)
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\fastapi\applications.py", line 1054, in __call__
    await super().__call__(scope, receive, send)
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\starlette\applications.py", line 123, in __call__
    await self.middleware_stack(scope, receive, send)
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\starlette\middleware\errors.py", line 186, in __call__
    raise exc
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\starlette\middleware\errors.py", line 164, in __call__
    await self.app(scope, receive, _send)
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\gradio\route_utils.py", line 707, in __call__
    await self.app(scope, receive, send)
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\starlette\middleware\exceptions.py", line 65, in __call__
    await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\starlette\_exception_handler.py", line 64, in wrapped_app
    raise exc
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\starlette\_exception_handler.py", line 53, in wrapped_app
    await app(scope, receive, sender)
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\starlette\routing.py", line 756, in __call__
    await self.middleware_stack(scope, receive, send)
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\starlette\routing.py", line 776, in app
    await route.handle(scope, receive, send)
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\starlette\routing.py", line 297, in handle
    await self.app(scope, receive, send)
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\starlette\routing.py", line 77, in app
    await wrap_app_handling_exceptions(app, request)(scope, receive, send)
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\starlette\_exception_handler.py", line 64, in wrapped_app
    raise exc
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\starlette\_exception_handler.py", line 53, in wrapped_app
    await app(scope, receive, sender)
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\starlette\routing.py", line 75, in app
    await response(scope, receive, send)
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\starlette\responses.py", line 352, in __call__
    await send(
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\starlette\_exception_handler.py", line 50, in sender
    await send(message)
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\starlette\_exception_handler.py", line 50, in sender
    await send(message)
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\starlette\middleware\errors.py", line 161, in _send
    await send(message)
  File "D:\Applio\ApplioV3.2.0\env\lib\site-packages\uvicorn\protocols\http\httptools_impl.py", line 549, in send
    raise RuntimeError("Response content shorter than Content-Length")
RuntimeError: Response content shorter than Content-Length

Fresh new Applio download

[pearl python]

is that meant for me?

[barren canopy]

No'

Me asking for help

[pearl python]

oh i see mb

[barren canopy]

context: happens randomly when adding audio files, error also shows up when i can preview audio files but try to infer with any voice

[safe harbor]

I need advice on pitching voices while putting a female/kid voice over male vocals

[rare goblet]

Ayo? @safe harbor level 2 !!!

[plush dew]

anyone knows of a paperspace notebook that actually works? I've read the docs, Applio does not work.

[opal patrol]

how can i find program that makes voice database for me auto

[rare goblet]

Ayo? @opal patrol level 1 !!!

[opal patrol]

like i record smth and put the files in the program and it seperates stuff etc

i had it on my old laptop but now i am on pc

[thin stump]

Automatic dataset makers aren't good. It's better to be hands on with the audio you're working with https://docs.aihub.wtf/essentials/how-to-make-voice-models/

[distant storm]

is there any way to convert an svc model to rvc

[thin stump]

Nope, you would need to retrain in rvc

[opal patrol]

😀😐🤨😩😮‍💨😤

[thin stump]

soul is back on the menu boys, he's going to make a first dataset 👀

[opal patrol]

I have already one but

When i did record myself i had air in my audio

[thin stump]

Can I dm you?

[opal patrol]

Yes

I watch for some friends

[brittle wing]

Yeah Apollio has issues for me too.

Mainline seems to be the only one to work.

[thin stump]

@brittle wing just a reminder why I hate helping people

nah refused to read more like

the docs are so accessible but still alien 👽 '

[opal patrol]

yapping about me while not knowing me ?
shame

first of all mdv is my game morning day vibin (an fnf game with cool modcharts)
and model in the pfp is my model made it with 3-4 days of experience (without blender only using roblox studio)

3. you don't even have pfp and your name is worser

[brittle wing]

🤓

☝️🤓

[spice gate]

anyone know what went wrong here?

https://youtu.be/ZjH4jkXggPY?si=K-s-nxDP9-StZVMO the model is trained off this video with 300 epochs rvc2 rmvpe

on applio local

[thin stump]

It sounds like the echo/another voice got trained in and you didn't denoise it

[long plank]

im trying to use illaria rvc but the public and local links dont work

[thin stump]

only Ilaria mainline works. I thought they would have removed it from the docs but I guess not

[long plank]

im using that one

the local one says This site can’t be reached

and public says no interface is running

[rare goblet]

Ayo? @long plank level 1 !!!

[leaden igloo]

how can i convert .safetensors to pth ?

or any format where i can use for rvc

[wispy lodge]

Where did you get an rvc model in safetensors format? 🤔

[leaden igloo]

https://prompthero.com/ai-models/eris-mushoku-tensei-download

needed eris voice model only site which actually has it

[wispy lodge]

That's not an RVC model, that's for Stable Diffusion

[leaden igloo]

ohhhh

well i'll wait until someone makes a rvc ig

(don't have enough braincells to make one)

[cloud lava]

where to download RVS?

[brittle wing]

hm is there a place to ask if something exists? 🤔 coz i tried looking it up but im not sure if it exists.
i basically want a voice that sounds like squeaking when i talk LOL

[fleet cedar]

GUYS HELP ME WHERE IS THERE A ECHO VOICE

[low shard]

Thats LORA, its for sd, for generating art not ai covers

[low shard]

Wdym

[low shard]

You mean rvc? Check https://docs.aihub.wtf

[idle yacht]

how to use

how to use these voice models

[brittle wing]

why rvc is nothing effect my voice?

[proper shale]

https://docs.aihub.wtf/ has everything you need to know

[proper shale]

what's your settings rn? send a screenshot

[faint latch]

How do I add the person's voice I need here? Please help

[proper shale]

not sure i understood - you have a model of someone? and want to upload it here? or do you wanna use someone's voice

[faint latch]

I want to upload the voice of one person, I have a recording of his voice

[proper shale]

Oh you wanna train a model, I see

https://docs.aihub.wtf/ has everything you need to know

How to make voice models section is pretty good, then use an RVC program to train

[faint latch]

Thank you moder 👏

[rare goblet]

Ayo? @faint latch level 1 !!!

[proper shale]

Yw :)

[stark spade]

hello, um i want to ask a question.
why my gpu settings in google collab doesnt show the T4 option? I can only connect to my own cpu

[proper shale]

that's probably because you ran out of GPU time, you'll have to wait 24 hours to get it back, probably

[stark spade]

ohh i see

even if i can run the google collab, i cant connect to the gpu ?

[proper shale]

yeah, not rn

[stark spade]

okayy, thank you very much

[proper shale]

yw :)

[south tree]

good morning, does anyone know how I can upload my voice model to huggingface?

bc when I want to use ilaria it asks me for the huggingface model link, and it does not allow me to upload GD links

[proper shale]

https://docs.aihub.wtf/essentials/voice-models/#uploading-to-hugging-face

oops, mobile internet moment

[south tree]

tyyyy

[proper shale]

yw! :)

[pliant plaza]

Hello!

Can someone help me with a question?

[barren canopy]

https://dontasktoask.com

[stiff goblet]

Is Applio good for training ?

[steep niche]

Comrades, can you tell me which config I should choose when using the so-vits-svc fork?

[proud elbow]

!howtoask

[patent trellis]

How To Troubleshoot

__**GIVE CONTEXT.**__ 📝

• 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.

__**BE POLITE.**__ <:matsuripray:1159685390156967936>

• 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.

__**BE PRODUCTIVE.**__ 🤝

• 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.

If you've changed your mind about your message, feel free to delete/edit it.

[finite galleon]

We dont use sovits svc anymore (by anymore i mean like since last year). We use RVC v2

You could look on #1159513888199540817 for more info

[steep niche]

thank you very much

[brittle wing]

train model's: error 40000

[proper shale]

sample rate was changed...

between preprocessing and training maybe

[fierce spindle]

best settings? F0 METHOD and pitch

[spark mason]

I have been try for 2 days straight to do a voice swapwith literally every program. but Its always something. Im so over with

[rare goblet]

Ayo? @spark mason level 2 !!!

[spark mason]

im so fustrated

[plush dew]

does the ilaria rvc colab not work?

[odd shale]

Nope, it doesn't. Various users reported the same.

Use Applio Colab instead.

[reef steeple]

im trying to drag the zip file into voice.ai but it says that the file isnt supported and it has to be mp2 mp3 wav flac aiff

[brittle wing]

Do you recommend something good for vocals on the phone so that the AI model does not have hoarseness when singing and other strange voices?

Isolation

Cn guys help me ? My ai voice is delay 2second

[low shard]

Nope, the ilaria mangio rvc doesnt work, check #📰│dev-updates

[plush dew]

bro I have LITERALLY just finished to port it to paperspace and now it doesn't work xD

[brittle wing]

how it convert in 1 model

Sorry I dont know your language well

[low shard]

😭 i mean the colab doesnt work, the hf space does but its outdated and anyways doesnt get and wont get updates, you can just port the ilaria rvc mainline which is alot better and has training too

[plush dew]

oh i was talking about mainline

i cant read thank god

[low shard]

Oh lmao

[brittle wing]

I can't find this uvr cloud nickname anywhere

[low shard]

you are writing a guide or what lol

[brittle wing]

But I click on cloud and I can't access the link

[brittle wing]

help

[low shard]

To separate the vocals and instrumentals, use this, to clean the vocals use this

[plush dew]

For the time being it's just a notebook but I could write a guide as well.
The problem is there are various workarounds I had to use so it's a bit dirty but works nonetheless

[rare goblet]

Ayo? @plush dew level 2 !!!

[brittle wing]

Which is the best model?

[low shard]

Its not a conversion, your model saves every tot epoch frequency you putted, you need to choose the best one based on the tensorboard

[low shard]

wdym with workarounds

[low shard]

for the first colab i sent, use MDX23C 8KFFT InstVoc HQ 2, for the 2nd colab, check https://docs.aihub.wtf/rvc/resources/vocal-isolation/#best-models as there are differents based on use

oh just noticed bsreformer models got added to uvr colab lol

[brittle wing]

I have it, what's next?

[plush dew]

@low shard for example paperspace has weird problems with torch and its outdated cuda version so i had to specify the path to a specific python module otherwise it would always return an error
also it uses python 3.11 so i had to use miniconda to install python 3.10

[brittle wing]

And that white button on the left?

Yes?

What names?

Folder

2

Folders

And make the vocal from the second link or where?

From the second link, right?

No

[low shard]

i mean aint that bad lol

[brittle wing]

It's too difficult to explain to peasant people

Explain it to me in common sense*

So that I understand

I want the model to sing without hoarseness, coughing and other strange things, I have an MP3 without vocals

The entire song with instruments, etc., with the entire background music

So what to do step by step

???

@low shard

[split fiber]

-rvc

[azure marsh]

Documentation

AI HUB Docs

https://docs.aihub.wtf/

🍏 Applio Docs

https://docs.applio.org/

✨ More guides

• Full AI Voice Model Training Guide (local) by Christopher Villanueva
• Model training with Mainline RVC by Raven (ravencutie21)
• AICoverGen Colab Guide by Eddy (Spanish Helper)
• Create a model with RVC disconnected (colab) by Angetyde

[brittle wing]

Where can I find this path?

drive

MyDrive

Okay, but how to put MP3 music there?

Where

[split fiber]

-easy

-rvc

[azure marsh]

Documentation

AI HUB Docs

https://docs.aihub.wtf/

🍏 Applio Docs

https://docs.applio.org/

✨ More guides

• Full AI Voice Model Training Guide (local) by Christopher Villanueva
• Model training with Mainline RVC by Raven (ravencutie21)
• AICoverGen Colab Guide by Eddy (Spanish Helper)
• Create a model with RVC disconnected (colab) by Angetyde

[brittle wing]

@brittle wing

[split fiber]

-python

[brittle wing]

@brittle wing

@low shard

[split fiber]

what version of python should i have running locally

[brittle wing]

what settings yall suggest for 2070

[split fiber]

-rvc

[azure marsh]

Documentation

AI HUB Docs

https://docs.aihub.wtf/

🍏 Applio Docs

https://docs.applio.org/

✨ More guides

• Full AI Voice Model Training Guide (local) by Christopher Villanueva
• Model training with Mainline RVC by Raven (ravencutie21)
• AICoverGen Colab Guide by Eddy (Spanish Helper)
• Create a model with RVC disconnected (colab) by Angetyde

[brave garnet]

Voicechanger Settings (Okada)

⠀

Settings for Nvidia GPUs

F0 Det.: rmvpe (suggested for all series)

RTX 40-series: 80-96 chunk | +16384 extra
RTX 30-series: 96-112 chunk | +16384 extra
RTX 20-series: 112-128 chunk | +16384 extra
GTX 16-series: 128-192 chunk | +8192 extra
GTX 10-series: 128-192 chunk | +8192 extra

Advanced Settings

Protocol : Sio or Rest
Crossfade: 4096 start 0.2 end 0.8
Trancate: 300
Silencefront: Off
Protect: 0.5
RVC Quality: Low

⠀

Made with love by Ilaria 💖

[proper shale]

3.10

[brittle wing]

-colab

[azure marsh]

☁️ Google Colabs

• Applio, by IA Hispano Google Colab
• RVC Disconnected, by Kit Lemonfoot 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
• 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? @brittle wing level 15 !!!

[brittle wing]

@low shard

[brittle wing]

.

[low shard]

Check your google drive, and srsly dont spam ping me im literally out rn

[quasi ether]

I am using RVC disconnected, and I am experiencing a problem... nothing I did worked...

[rare goblet]

Ayo? @quasi ether level 3 !!!

[proper shale]

You'll have to wait for 24 hours to get GPU time again

[quasi ether]

oof...

[brittle wing]

if im making vocals for a song to put thru ai would it be better to record with autotune or

put the autotune on after i make the vocals

[proper shale]

both will work fine tbh

but id rather do it after conversion tbh. dont wanna screw up the model's output

[brittle wing]

ive already done half of them and cant be bothered to rerecord w the autotune off

guess if it sucks il just rerecord it all

[proper shale]

ah

i mean. if it works it works ig lol

[brittle wing]

whats the name of the software that lets u use ai voice changers in real time

i was gonna get it before i forgot to

[odd shale]

W-Okada.

-rt

[azure marsh]

This interaction has expired, use the command /guides realtime if you wish to see it again.

[brittle wing]

do i just like select the model and have it go thru vbcable

i already have vbcable

[odd shale]

Now you must install W-Okada (specificly, the version compatible with your GPU)

[brittle wing]

oh theres just 1 download

oh nvm nvm

i downloaded the right one i just forgot 😅

will it have like a significant performance impact if i use it ingames

i know theres specific settings for different gpus

[split frigate]

well I can't train 5hr dataset that I created
it's bugging... is there any solution or do I need to decrease it to 3hr or something

[brittle wing]

is it possible to delete these

[brave garnet]

RVC Colabs and Spaces

⠀

Google Colabs

⠀
AICoverGen-WebUI
Useful for making quick covers, by Hina.

AICoverGen-NoWebUI
Useful for making covers, doesn't include a UI, by Ardha, by Eddy, Hina and Gdr.

RVC Disconnected
To train new voice models, by Kit Lemonfoot.

EasyGUI
The OG interface, by Rejects.
⠀

Made with love by Ilaria 💖

[pastel oak]

overwrite them by uploading the new model in their spot

[brittle wing]

kinda cringe that u cant just delete them but thx

[wispy lodge]

You can delete them from model_dir

[pastel oak]

ah ye what emojikage said ^

[brittle wing]

my voice is like deeper than the model im using and it sounds off is there anything i can do about that or do i just need to like

speak with a high pitched voice

[inner cloak]

is this a problem? never seen this before

[slim geyser]

the pitch slider is your freind

like, pitching your voice up would only mess with it more if you don't have it set right

having your pitch off even by 1 can make it sounda kinda weird

[pseudo wing]

this my first day ever trying to do this stuff how do you add voices into the RVC V2 and how do you work it im also mobile so i can’t download anything that involves a pc cus my laptop won’t work

[slim geyser]

and considering that a bunch of people don't mess with it and just set it to 12, you can imagine how many people are just screwing themselves over

[low shard]

Be sure to read https://docs.aihub.wtf/, use the cloud ways

[pseudo wing]

Ok thank you

[thin stump]

@unborn geyser dms? #1159514067187277865 message

[pseudo wing]

how to you add the model into the software i can’t find out where to add it

[rare goblet]

Ayo? @pseudo wing level 1 !!!

[pseudo wing]

might have miss read the thing that you told me to read cus i’m also not the best reader but

[opal kelp]

-colab

[azure marsh]

☁️ Google Colabs

• Applio, by IA Hispano Google Colab
• RVC Disconnected, by Kit Lemonfoot 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
• 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

[low shard]

Which colab are you using?

You are using the cloud ways right?

[pseudo wing]

like the websites?

[low shard]

Yea, the google colabs

[pseudo wing]

rvc v2

ohh

[low shard]

Google colab is a platform where you run the ai using remotely google pc gpu

[pseudo wing]

lemme open google colabs

[low shard]

There's like, applio, rvc disconnected, etc

Its all under here (except ilaria rvc bc the one in the docs is the mangio one which is kinda outdated we will fix that, and paperspace ofc)

[pseudo wing]

does it matter which one i use or nah

[low shard]

I mean, just the way you use it, aicovergen is ONLY for ai covers, rvcdisconnected is a no ui (interface) colab for making models and its good because you have less chance of being disconnected than ui ones but harder to use, then there's applio whicb is good ui and has training, inference, and tts

Soo depends what you like

[pseudo wing]

Ok ima try applio

actually no ima try the first one ai cover gen

[amber zephyr]

what other website can i use to convert my audio to the ai voice. illaria is not working for me

[azure marsh]

Suggestions for @amber zephyr

☁️ Google Colabs

• Applio, by IA Hispano Google Colab
• RVC Disconnected, by Kit Lemonfoot 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
• 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

[amber zephyr]

k

[wheat sentinel]

Is Ilaria the only manual AI voice conversion Colab in AIHub at the moment? I don't prefer using the automatic cover generators, like the AICoverGen colabs.

[pseudo wing]

using that apollio thing and i have no idea what is going on

i wish i could send ss here

Ok

[low shard]

there's also applio

[inner scarab]

Can anyone give me latest rvc Colab link?

[azure marsh]

Suggestions for @inner scarab

☁️ Google Colabs

• Applio, by IA Hispano Google Colab
• RVC Disconnected, by Kit Lemonfoot 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
• 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

[brave garnet]

RVC Colabs and Spaces

⠀

Local Forks 🖥️

⠀
Mainline RVC
Original project, suggested for advanced users,
by the RVC-Project team.

Applio
Simplified, suggested for all, by the Applio team.

RVC Studio
Simplified, suggested for all, by SayanoAI.

Mangio-RVC
Simplified, may not be supported anymore, by Mangio621.

AICoverGen
Simple yet great way to make covers, by SociallyIneptWeeb.

Replay
From the greators of weights.gg, excellent product for everyone.
⠀

Made with love by Ilaria 💖

[proper shale]

Probably fixed rn

[fathom reef]

Uh...

[proper shale]

Refresh your page

[fathom reef]

How do I know which settings to use for realtime RVC?

[proper shale]

It's basically... trial and error, tbh

[fathom reef]

In case my graphics card isn't in the list here.

[proper shale]

I mean there's https://rentry.co/RVCRealtimeGuide

ah

[fathom reef]

I know about the "message me on Discord".

But at the same time, I'm still confused on what to do.

[proper shale]

I suppose go for something higher in terms of length

Since it's probably an older GPU?

or a newer one, who knows?

[fathom reef]

For further reference, my GPU is an AMD Radeon RX 580.

[proper shale]

yeah, increase your sample length or... whatever it was called, i forgot 😭

[fathom reef]

Yeah, it's sample length.

[proper shale]

Since it's an older GPU it'll have more delay and all that stuff

[fathom reef]

@pastel oak, your thoughts?

Nevermind, found a good one.

[rich bronze]

quick question chat, does the index file go into the weights folder too?

[glad zealot]

No

[rich bronze]

ok thanks

[thin stump]

Oh, my colab was out of date last I used it. It's either one of my accounts

because I still see the note left by blaise

to reach out to him if there's an error regarding the autosave

[glad zealot]

I use autosave on mainline

[thin stump]

Yup turns out it was the outdated version

[proper shale]

Thankfully Kit fixed it very quickly

[amber zephyr]

will illaria rvc be fixed soon as well?

[thin stump]

in big bold text too 😭 #📰│dev-updates message

[shy gale]

We're to go, to make ai songs?

[mystic marsh]

-colab

[azure marsh]

☁️ Google Colabs

• Applio, by IA Hispano Google Colab
• RVC Disconnected, by Kit Lemonfoot 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
• 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

[amber zephyr]

dawg wtf i'm tripping

[amber zephyr]

i'm not use to this

[mild prism]

I need some assistance with RVC. I'm in the process of clearing echo and music from my audio samples, but I keep getting the same error.

[rare goblet]

Ayo? @mild prism level 1 !!!

[timber heart]

I have the same problem lol.

[mild prism]

So I realize that both the vocal seperation features and the training are pretty much out of my reach due to being an AMD Radeon GPU user. So now the next question is that if I gather the appropriate audio files, would anyone be willing to help me make them into public models? The main one I was working on rn was Sylvia from Viewtiful Joe. So that is my focus.

[native igloo]

Hey! I am just getting started to all this AI voice stuff, and i was wondering if i could use RVC for streaming and stuff, like, if it would change my voice in real time

Oh, i might try thena

Is there a link for Okada on the guides?

Thank you my dude

[rare goblet]

Ayo? @native igloo level 1 !!!

[native igloo]

Lets gooooo

[plush dew]

-realtime

[azure marsh]

This interaction has expired, use the command /guides realtime if you wish to see it again.

🎙️ Realtime Voice Changer (Local)

💻 (Local) Realtime Voice Changer

• Guide for W-Okada's RealTimeVoiceChangerClient
• How to use real time conversion with RVC (voice changer)
• RVC TTS

🎙️ Realtime Voice Changer (Local)

💻 (Local) Realtime Voice Changer

• Guide for W-Okada's RealTimeVoiceChangerClient
• How to use real time conversion with RVC (voice changer)
• RVC TTS

[plush dew]

[split fiber]

-rvc

[azure marsh]

Documentation

AI HUB Docs

https://docs.aihub.wtf/

🍏 Applio Docs

https://docs.applio.org/

✨ More guides

• Full AI Voice Model Training Guide (local) by Christopher Villanueva
• Model training with Mainline RVC by Raven (ravencutie21)
• AICoverGen Colab Guide by Eddy (Spanish Helper)
• Create a model with RVC disconnected (colab) by Angetyde

[elder cloak]

Hey so AICoverGen-WebUI, by SociallyIneptWeeb (modified by Hina) is now requiring NVIDIA driver. I haven't had this happen before

[split fiber]

install it

[elder cloak]

I did but it said it couldn't detect It had a Nvidia in my system

if that makes sense

[rare goblet]

Ayo? @brittle wing level 53 !!!

[elder cloak]

ohh okay

[split fiber]

so does v2 take less epochs to train

[brittle wing]

Hey guys i was wondering if you had any advice for a problem im having. I created a few models and downloaded a few however it doesnt sound like the character or person when I change the pitch. So it can sounds like them but wont fit in the song. Do you guys just keep it at 0 or transpose the song?

[fallow shell]

omg can you share how you did it or perhaps share the notebook? i've tried so many things for weeks to no avail 😦

[proper shale]

Transpose the song if possible

[obsidian marten]

how to make ai cover?

[rare goblet]

Ayo? @obsidian marten level 1 !!!

[azure marsh]

🎙️ Realtime Voice Changer (Local)

💻 (Local) Realtime Voice Changer

• Guide for W-Okada's RealTimeVoiceChangerClient
• How to use real time conversion with RVC (voice changer)
• RVC TTS

[proper shale]

https://docs.aihub.wtf/

[strange rain]

what does this mean

Looks like there's a bit of a problem.
unknwon message

If you clear the information being managed by this app, it may be recoverable.

Initialize

Reload without initialize

Error
unhandledrejection
no error stack
Error: No available storage method found.
Error: No available storage method found.
at n (http://127.0.0.1:18888/index.js:2:1150122)

[coarse falcon]

Can anyone give me best Collab which take less time and gives good results too

@brave garnet your Collab is not working properly 😭

[proper shale]

All Colabs are the same really, but you should have decent results with Ilaria RVC Mainline: https://colab.research.google.com/drive/1mHKTGH5e3SAyDSBss1KtiYRbDdQzwSMs

[coarse falcon]

Can you share guide

@proper shale

[proper shale]

It's pretty straightforward so I don't think it's necessary, just run the install and run steps, use gradio link and it should be pretty much like the other one

[low shard]

btw you tagged the bot, not ilaria, and ilaria rvc mangio the one that was on our docs, doesn't work anymore, check #📰│dev-updates

[surreal magnet]

hello, so just wondering if anyone got the same issue, im using ASIO on rvc, when i set mic as direct input and line 1 as output it works just fine, but when i set Steelseries Sonar as input and line 1 as output, it does not produce any sound.
been following the guide at https://rentry.co/Realtime-less-delay
any idea of why ?

[plush dew]

https://docs.google.com/document/d/1cvqC9k6rDpEqTxoCIJ274PCN3a7hnMlOAl1lQGgDy8M/edit?usp=sharing

I've also done the same with Applio but haven't had time to write it down

let me know if it works

[low shard]

@viscid moss btw this could be added to the docs ig

idk if ddenno wants to be staff

[viscid moss]

Yes, I had already talked about it with him.

[pastel oak]

Did you make sure you selected the correct steelseries input?

the one with - microphone

[surreal magnet]

hi, and yes, heres the flexasio output
backend = "Windows WASAPI"
bufferSizeSamples = 256
[input]
device = "SteelSeries Sonar - Microphone (SteelSeries Sonar Virtual Audio Device)"
suggestedLatencySeconds = 0.2
[output]
device = "Line 1 (Virtual Audio Cable)"
suggestedLatencySeconds = 0.2
wasapiExclusiveMode = false
wasapiAutoConvert = true

[pastel oak]

and what microphone did you select on steelseries sonar?

[rich moss]

hello I have a problem I just followed the tutorial to create a voice with rvc but my gpu is not detected (I have an adm and I installed the RVC0813AMD_Intel.7z) how to make it detect please

[pastel oak]

First of all i dont know how you managed to find a download for RVC0813 lmao

Secondly, are you trying to train a voice model? You can not train a model with AMD gpu on windows

[rich moss]

is it only nvidia that can create models or amd too?

[rare goblet]

Ayo? @rich moss level 1 !!!

[rich moss]

I find it here the RVC0813 https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main

[surreal magnet]

i've checked on Sonar setting > microphone input is "Default mic from windows"
on my win11 system sound, i've checked the input was Microphone USB Audio

[rare goblet]

Ayo? @surreal magnet level 1 !!!

[daring heath]

:loss_disc=4.070, loss_gen=2.954, loss_fm=8.945,loss_mel=17.824, loss_kl=1.309
What does that sentence mean

[odd shale]

Hey bud.

@plush dew

If you're interested, you can use the /jointeam command to make a test so you can join the staff team.

People like you could be a nice addition.

[plush dew]

I'll have a look in a moment

[azure marsh]

Suggestions for @vague ether

☁️ Google Colabs

• Applio, by IA Hispano Google Colab
• RVC Disconnected, by Kit Lemonfoot 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
• 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

[low shard]

you can use rvc on colab yes

check our docs https://docs.aihub.wtf

if you mean to use a realtime voice changer, check the guide below instead

-rt

[azure marsh]

This interaction has expired, use the command /guides realtime if you wish to see it again.

[low shard]

you can use the wokada colab

[azure marsh]

🎙️ Realtime Voice Changer (Online)

☁ (Online) W-Okada - Colab Version

• 🔗 How to use W-Okada's Voice Changer

A free, online version of W-Okada that allows you to run code on Google's powerful GPUs.

ⓘ Please note that this doesn't work on mobile because there's no VAC (Voice Audio Cable) for it

[rare goblet]

Ayo? @vague ether level 1 !!!

[merry glacier]

how much crepe hop should i set?

[pastel oak]

only nvidia

amd can train on rocm with linux i think.. im not a linux user

[pastel oak]

i mean if you check if your steelseries sonar microphone gives an output on discord, then everything else after should work

cause you should be doing:

1. Steelseries sonar
   Input: your normal microphone
   check if it works. if yes, youre fine

then flexasio input steelseries sonar microphone -> output line 1

on rvc you do input: flexasio output: flexasio

and on discord etc. you do input: line 1

[pastel oak]

if youre new to training models just use rmvpe its great overall, crepe is very specific

[merry glacier]

alr ty

[surreal magnet]

thanks for the info, tried with input mic then sonar then discord normally w/o ASIO = works
but once i put the rvc on, it doesnt work, but if i go through normal mic > asio > rvc it works lol
i ended up changing to nvidia broadcast, it works rather flawlessly

[rare goblet]

Ayo? @wispy escarp level 1 !!!

[dry light]

So guys, I kinda need some help here.
I've made a model (some months ago I've done the same, in collab). I clicked on "one click traning", it did start and finish. But now I only have the .pth file, and when I click to generate the .index, it loads briefly something and then stops and does nothing.

The final logs are these:
INFO:prof-fedeli:====> Epoch: 300 [2024-06-07 12:26:15] | (0:00:08.379548)
INFO:prof-fedeli:Training is done. The program is closed.
INFO:prof-fedeli:saving final ckpt:Success.

[proper shale]

that's for the .pth

index ain't really necessary

[dry light]

Yes, but like, when I click in "Train feature index" nothing happens basically

[dry light]

I can use any random then?

[proper shale]

it's not even necessary to have it

[proper shale]

that's... kinda weird

[dry light]

Like, the "Output information" briefly starts to load and then goes back to normal with 0 logs

I'll try to test the model then

[formal narwhal]

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)

[lunar holly]

Has anyone tried to use an NPU inside of newer AMD/Intel CPUs to lift the job doing the RVC?
I'm planning to buy a mini PC, but I do not know, if 10 TOPS inside of R7 7840HS in it's NPU is enough for this task.

[low shard]

You are using an outdated google colab, check newer ones in https://docs.aihub.wtf and next time be a lil more specific

[frail fulcrum]

any tips for improving RVC realtime gui's output quality when using it with your real voice

if I speak japanese into a JP model it vastly improves my voice and speaking

on the other hand if i speak english into a EN model it drops a lot of syllables and generally adds a very heavy accent that i cant remove unless i enunciate a lot and speak very loudly

and finally theres speaking chinese which surprisingly works perfectly with EN models but not at all JP ones

[lunar holly]

i'm sure english has quite different ways of pronouncing (american, british, australian, irish, indian, and others), so possibly your origin might be not-so fitting for the model

[frail fulcrum]

i speak pretty standard american english

[rare goblet]

Ayo? @frail fulcrum level 1 !!!

[frail fulcrum]

i speak japanese with a kind of off accent but enough that AI could fix it

chinese is perfect at least speaking

and i believe the model does come from an american voice?

[proper shale]

don't think NPUs work for this type of AI stuff yet

[lunar holly]

i tend to speak better than most russians speak english, since i actually studied, and had chatting, that geard towards to american english, though i haven't tried any other models besides default tsukuyomi-chan that comes with

[frail fulcrum]

english is my main language even though its my second language

so i dont believe the problem is with input pronunciation

maybe default models perform better idk

[lunar holly]

believe me, i tend to speak english more often than i do speak in russian irl most of the time, though i did used in rvc a little bit to meme out about one person

[rare goblet]

Ayo? @lunar holly level 1 !!!

[lunar holly]

it felt, that the rvc's AI interpretation of my russian speech cut out the "r" letter, and that almost felt appropriate for a local telegram chat meme at one point

[frail fulcrum]

I need to say the l extremely hard for it to pick up

otherwise it makes it r

[pastel oak]

can you send a screenshot of your gui

[frail fulcrum]

yeah let me get on my pc real quick

[pastel oak]

and about the accent part, do you have index enabled?

[frail fulcrum]

index? let me check real quick

index rate is 0 i think why

i think the issue might also be from my mic

it's not exactly shit but it's pretty quiet

[pastel oak]

could be a factor

if ai cant recognize the sound you make from its dataset itll mess up

[frail fulcrum]

what does index do

[pastel oak]

forces the accent of the voice model

so thought its that

people who have a very heavy accent use it, but if you dont then you dont have to unless your model is idk australian and you wanna sound more like it, to some degree

[brittle wing]

-colab

[azure marsh]

☁️ Google Colabs

• Applio, by IA Hispano Google Colab
• RVC Disconnected, by Kit Lemonfoot 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
• 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

[frail fulcrum]

i can do aussie accent fine

even though im not really aussie at all

but my model i am pretty 80% certain comes from american accent

index rate 0.00 right now

discord not starting on pc

response threshold - 60
pitch setting 12
index rate 0.00
loudness 1.00
sample length 0.52
cpu processes 6
fade length 0.15
extra inference 3.02

[rare goblet]

Ayo? @frail fulcrum level 2 !!!

[frail fulcrum]

rmvpe

[split fiber]

It’s crazy one of my voices so clear it only needs 50 epochs and sound good asf

[split fiber]

Yessir

The acapellas was so clear

[pastel oak]

and what gpu? but your settings look fine

must be the mic then

[frail fulcrum]

3070

[pastel oak]

you can go way lower in sample length then

like 0.18 or lower

as for extra, you can try to see how it behaves if you lower extra

put it to 1.80 and see if it makes any difference on the english model @frail fulcrum

[fleet raven]

Please help! I use google colab applio and i clicked generate index but I don't see it.

[split fiber]

It will be located in the logs @fleet raven

[frail fulcrum]

well

it is just my mic

if i put my lips on it

perfect voice

perfect output with same settings

if im just slightly further

exponentially drops in quality

drops a lot of syllables hella accent etc

[split fiber]

What mic do you have

[frail fulcrum]

laptop built in 💀

and 3070 means somewhat loud fans

in a laptop

youd figure

[split fiber]

Oh no buddy you need a real mic

[frail fulcrum]

so lower sample length = higher quality = needs better gpu

[frail fulcrum]

aight ill use the mic from the car

or do you have any recommendations

[split fiber]

😂😂😂😂

[frail fulcrum]

would be great

[fleet raven]

It says index file generated successfully but I don't see it in the logs folder.

[rare goblet]

Ayo? @fleet raven level 1 !!!

[split fiber]

Yes blue yeti

[frail fulcrum]

i thought someone said yeti was bad but ik friends who have it who also use rvc

and their results are great

[brittle wing]

anyone here mac rvc user?

Wondering If anyone ran on mac and how

[split fiber]

There not bad

[rare goblet]

Ayo? @split fiber level 6 !!!

[weary mist]

where the fuck does mangio go after it finishes installing in the command prompt?

[frail fulcrum]

i can just swallow the vent for now

[weary mist]

I cant find it, can someone please help me?

[fleet raven]

Is this good?

[spare shale]

@weary mist wdym?

[spare shale]

aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa

[spare shale]

I think this is very good (sarcasm)

[weary mist]

i figured it out, i cant run the program in my downloads file for some reason

[spare shale]

well then I'm glad I don't have to help you

[weary mist]

does the .pth file go in weights or logs?

[spare shale]

weights

In the logs folder you can find index

[weary mist]

ok, i couldt rememeber off the top of my head

[fleet raven]

But why did it randomly jumped down to 12 at 2k steps

[spare shale]

thb I don't use this (I'm too stupid for that) but I think it's possible. It's something like a bag/lag and everything will be otay?

[analog ridge]

whats wrong?

[fallow shell]

GOD BLESS YOU🙏 I'll try this and let you know if it works. THANKS A LOT 🥰

[plush dew]

I've also written a guide for Applio if you're interested https://docs.google.com/document/d/1ooG2hJrfNNLUln0reTKKIOpNBjp53G0joak50H_sQhE/edit?usp=sharing

[fallow shell]

Omg you have a space secured in heaven, I'll try it out as well 💖

[brittle wing]

is it possible to have multiple vb cables

[polar crest]

hey guys, does anyone know the rough amount of steps needed to train under a 50 minute dataset

I'm at 83000 and I know it's not enough

[azure marsh]

Suggestion for @junior needle

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

🎙️ Realtime Voice Changer (Local)

💻 (Local) Realtime Voice Changer

• Guide for W-Okada's RealTimeVoiceChangerClient
• How to use real time conversion with RVC (voice changer)
• RVC TTS

[polar crest]

that doesn't cover it at all

[pastel oak]

open the docs aihub link and check tensorboard

else, check this if it helps you
#✨│ai-help message

[polar crest]

ohhhh i see

thank you so much

[glass flicker]

Yo I dont have image perms but the Voice Changer Client basically disappeared and a new page saying
"Looks like there's a bit of a problem.
unknwon message

If you clear the information being managed by this app, it may be recoverable."

How do I fix this

[delicate kettle]

Is there anyway for me to download collab locally on my pc

[rare goblet]

Ayo? @delicate kettle level 3 !!!

[rare goblet]

Ayo? @leaden parcel level 1 !!!

[plush dew]

colab is a sort of remote computer

what are you trying to use?

[delicate kettle]

Trynna make ai covers

But I found an app called replay

[plush dew]

check out https://github.com/TheStingerX/Ilaria-RVC-Mainline

[brittle wing]

what python version is needed for RVC-GUI

[rare goblet]

Ayo? @brittle wing level 1 !!!

[brittle wing]

i tried 3.8 but it could not find a version that satisfies the requirement torch

they never tell you how to get it all installed

[quasi ether]

I want to make a better ai model of my voice, I have more samples than before and I'm aiming for 2000 epochs, however, Copilot forces me to constantly move my mouse, which is a problem for dinner situations, My computer ain't strong enough to do the training on GPU, is there a better solution?

[brittle wing]

is a RTX 3060 enough for training

-colab

[azure marsh]

☁️ Google Colabs

• Applio, by IA Hispano Google Colab
• RVC Disconnected, by Kit Lemonfoot 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
• 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

[leaden parcel]

Should I change the voice changer type?

In the file uploader

Also too, I'm trying to figure out if my setup can even handle this

I have the i5 version

I just got this a few days ago

[sick axle]

where can I find the training link to train a titan model.

[leaden parcel]

Also too it just randomly stops working (the voice changer)then I have to restart my computer

[jaunty skiff]

I'm trying to download a jacksepticeye model and this keeps happening

[azure marsh]

Suggestions for @jaunty skiff

☁️ Google Colabs

• Applio, by IA Hispano Google Colab
• RVC Disconnected, by Kit Lemonfoot 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
• 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 skiff]

Do I have this right?

[tame mica]

seems right to me

[jaunty skiff]

Awesome! Haven't done this in a while, so thanks.

[brittle wing]

how long does training usually take

[jaunty skiff]

Also, does it take a while for it to download the audio with the voice? Cause my audio is like 3 minutes.

[tame mica]

like a few hours max maybe

[tame mica]

?

[worldly lodge]

what is the difference between dio, pm, and harvest? i tried translating the description but its structured in a confusing way

[tame mica]

it's currently inferencing right now. a few minutes of audio should take a few minutes i think

[worldly lodge]

im training my model on rmvpe_gpu right now cuz my gpu is stronk but it doesnt sound the best

[snow pasture]

Is titan the better option over ov2?

[tame mica]

it's all different types of pitch extraction. usually three of those are not used in model creation/inferencing

yeh

[worldly lodge]

guess i just gotta feed it more data then

[jaunty skiff]

So does it take a while depending how long the audio file is? Because mine is 3 minutes.

[snow pasture]

rmvpe is the norm but mangio crepe could sound good with certain models especially if it's speech oriented.

[jaunty skiff]

How do I do that?

[tame mica]

ye. huggingface spaces usually use a cpu for it so it's way longer than google colab

[worldly lodge]

im using it for song covers so im not speaking is what im going for

although i do get drastically beter results when i train it on rmvpe and then use crepe for conversion

[tame mica]

crepe usually aims for studio quality acapella from what ive heard so https://cdn.discordapp.com/emojis/1205989909819822120.webp?size=48&quality=lossless&name=thumbs

[worldly lodge]

i tried using mangio but its like uber broken on the conversion ui and from what ive heard its an abandoned project so i dont know if training on it will be any good

ye

i had better luck with the rvc by RVC boss, i havent looked into other forks yet. but with mangio i would only be able to convert one or two times before it would corrupt the audios and make them super slowed down

[rare goblet]

Ayo? @worldly lodge level 2 !!!

[worldly lodge]

i got really tired of closing the program every other conversion and it made me question the integrity

are there better forks for rvc other than what im using right now?

[terse turret]

-7

how do i fix it

it keeps saying -7

[tame mica]

wtf is this colab

[terse turret]

yeah

[queen kraken]

To me mainline's voice is pretty similar to the dataset voice, but mangio's output voice is totally different. same rmvpe

[tame mica]

the mangio fork is not updated anymore

[worldly lodge]

are there links somewhere to those?

[queen kraken]

but the rmvpe algorithm is the same, right?

[tame mica]

ye should be

[terse turret]

alright, so to disconnect i change runtime right

and then putting back to T4 GPU

yeah

so what do i do to disconnect

[brittle wing]

will the model work if i hit stop training or do you have to let it go all the way

[terse turret]

alr did that

i hope the -7 doesnt appear

[brittle wing]

what is an epoch and what happens if it's higher

[tame mica]

it should only make the g and d files. but you can retrain it for 1 more epochs to get your finished model

[viscid moss]

WTF

[brittle wing]

does it train in the background

[rare goblet]

Ayo? @brittle wing level 2 !!!

[brittle wing]

what do you do when you trained

how do you use applio with this

yeah but how do i use it

what files do i need to put into this

but i have multiple pth

they're all G_xxx.pth and D_xxx.pth

i don't see it

[tame mica]

okay so, retrain your model for 1 more epochs from the latest g and d epoch count

[brittle wing]

how do i do that

[tame mica]

wait why are you training for 950 epochs?

[brittle wing]

????

only 800

sorry im new

this?

[tame mica]

no

retrain for 1 more epochs to get your model pth

[brittle wing]

i had total epoch at 800

[brittle wing]

what do you mean train for 1 more epoch, increase by one?

[tame mica]

yep

[brittle wing]

or just1 total epoch

where do i check that

do i have to generate index again?

[rare goblet]

Ayo? @brittle wing level 3 !!!

[tame mica]

nope

[brittle wing]

i didn't get the final pth file

is it because it's D_4000 and G_4000 and i need to put 4001

again?

that can't be it

i can't find any zip file

what would it be named

i keep training for one more epoch and i still can't find a model pth

yeah i don't see a zip folder

this is all in logs

[elfin dock]

whats the input and output for it?

[brittle wing]

it says it trained successfully

[elfin dock]

i alr have my voice and stuff, i just dont know what input and stuff it is for discord calls

[jaunty flame]

-colab

[azure marsh]

☁️ Google Colabs

• Applio, by IA Hispano Google Colab
• RVC Disconnected, by Kit Lemonfoot 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
• 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]

wait i know where it is

it's in the root of my c drive

well that's what it would have been saved in if it had permissions

[lofty musk]

hello chat i have a question and this is mainly for my friend but uh. is there a way to download a voice model someone developed off of elevenlabs so it can be used as a RVC

[plush compass]

HP6 karaoke users, what do you set the WINDOW SIZE and AGGRESSION SETTING to?

[floral walrus]

The error is caused by a malformed JSON file located at the path specified by the config_path variable. The error message specifically mentions "Expecting value" at the beginning of the file, indicating that the JSON parser encountered an unexpected character or structure.

Suggested Changes:

Verify the JSON File:

Check if the JSON file at config_path exists and is not empty.
Use a JSON validator tool to ensure the file is syntactically correct.
Update the Credentials Object:

If the JSON file is valid, the issue might be with the Credentials.from_service_account_file() method. Try updating the method call with the following changes:

what do I do

[azure marsh]

Suggestions for @floral walrus

☁️ Google Colabs

• Applio, by IA Hispano Google Colab
• RVC Disconnected, by Kit Lemonfoot 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
• 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

[queen frigate]

can someone help me make an ai voice model of kanye west runaway

[surreal magnet]

i have like 472ms of algorithmic delay, is that normal ?

[tawdry parcel]

Any zip link I try in the google collab does not work

ModuleNotFoundError Traceback (most recent call last)
<ipython-input-2-be56f2050b6f> 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'

[carmine hearth]

-colab

[azure marsh]

☁️ Google Colabs

• Applio, by IA Hispano Google Colab
• RVC Disconnected, by Kit Lemonfoot 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
• 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

[jovial galleon]

Yo

so I have a really solid model now

but it still has that AI tone that makes it obvious

its hard to explain

but even when the audio is properly mixed etc you can notice

and i dont know what it exactly is

[brittle wing]

-colab

[azure marsh]

☁️ Google Colabs

• Applio, by IA Hispano Google Colab
• RVC Disconnected, by Kit Lemonfoot 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
• 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

[jovial galleon]

It's mostly when you have it extend the last part of a word so if it's supposed to sing knooowwwwww it will start getting this weird ai tone at the ooooowwww part

idk how to explain rlly

i dont rlly have an example where its clear

but its ok ig

ight

[low shard]

Are you using ilaria rvc? That one is the mangio version that doesnt work, use the newer ones in our docs https://docs.aihub.wtf/

[solid cloud]

who can make a voice from a YouTube channel to use it in real time?

[proper shale]

you yourself could probably do it

but, if not

#1159289738314919936

[solid cloud]

my pc very slow + very bad

[proper shale]

there's colab yk

[brittle wing]

how do i isolate vocals locally?

[proper shale]

You can use UVR

https://docs.google.com/document/d/17fjNvJzj8ZGSer7c7OFe_CNfUKbAxEh_OBv94ZdRG5c/edit#heading=h.czix2y8eiuna

[brittle wing]

can i use it on 3.11 python

[proper shale]

I'm.... actually not sure tbh

I think it might be prepackaged but I'm not sure

[slow aspen]

Guys is everything ok on this graf?

[proper shale]

looks ok, that mel/total value is kinda high but it's still going so i expect it to get better

[slow aspen]

okkk thx ❤️

[brittle wing]

Will a RX 6600 perform similar to a GTX 1660 Super in Ai?

[slow aspen]

If it only goes up from this point then I have to choose the model where the lowest mel value is?

[granite falcon]

i have a question

[rare goblet]

Ayo? @granite falcon level 2 !!!

[granite falcon]

im using AICoverGen-WebUI, by SociallyIneptWeeb (modified by Hina) but it doesnt have the voice training option

i tried some others and they dont have either

i wanna make a voice model , i have the vocals ready and everything

can someone help ?

[slow aspen]

-colab

[azure marsh]

☁️ Google Colabs

• Applio, by IA Hispano Google Colab
• RVC Disconnected, by Kit Lemonfoot 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
• 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

[slow aspen]

Use RVC Disconnected or Applio

[proper shale]

nope

if it goes up, wait for it to go back down

if it doesn't, then pick the latest point that wasn't going up

if you want to merge the best mel stat ofc you can pick that

[slow aspen]

you mean the latest from total or mel?

[proper shale]

mel

or maybe even kl

[slow aspen]

okk

[molten iris]

Hello, I have a problem when I try to open go-realtime-gui-dml. This message appears and when I press a key, it closes directly, yesterday it worked perfectly. How to do it, please?

[granite falcon]

hello ? can somebody answer my question ?

[proper shale]

ask away

[proper shale]

hm, id probably reinstall ngl

[pearl plover]

Hey guys i got a question

is there a way to make my voice as a model for RVC?

[low shard]

you can make a model of your own voice, check https://docs.aihub.wtf/essentials/how-to-make-voice-models/

[pearl plover]

creating a model is using tensor?

[rare goblet]

Ayo? @pearl plover level 1 !!!

[pearl plover]

im lost

[odd shale]

Nope.

You must record at least 10-15-20 mins of your voice.

And make sure your audio doesn't have any noise.

[brittle wing]

is there a way to seperate overlapped vocals

[rare goblet]

Ayo? @brittle wing level 6 !!!

[brittle wing]

if its like the same voice

[odd shale]

What model is that?

[gaunt citrus]

-colab

[azure marsh]

☁️ Google Colabs

• Applio, by IA Hispano Google Colab
• RVC Disconnected, by Kit Lemonfoot 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
• 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

[safe harbor]

How do I not get this?

[violet heron]

What was the model link?

[safe harbor]

This

[brittle wing]

whats the best free website for voice ai covers?

[proper shale]

https://weights.gg

[brittle wing]

are you able to use your own files?

[proper shale]

files as in models?

or audios

[brittle wing]

yes

welll

both i suppose

[proper shale]

you do need to select a model there

you could also use colab

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

[brittle wing]

thx

ill try that one if the other one you sent me doesnt work

[proper shale]

alr

[brittle wing]

wont let me access this one for some reason

[proper shale]

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

[brittle wing]

just keeps telling me to log into an admin account then nothing happens when i log in

okay its fixed

[rare goblet]

Ayo? @brittle wing level 1 !!!

[worldly lodge]

are you supposed to train feature index before or after training the model

[proper shale]

before

[worldly lodge]

thats so strange, some of the documentation says to do it after

also

for these is there anything better than these to use to train the model or is this it?

[brittle wing]

How do you properly convert a male voice to a female voice?

Right now mine sounds horrible

[proper shale]

mess with pitch options

[brittle wing]

Alr

[proper shale]

another fail of the docus

[proper shale]

this is fine

altho 48k might bring a lot of noise with the model

[worldly lodge]

shiiit

would i have to restart and choose a different sample rate from the start?

like here?

[proper shale]

your option tbh

[tough fiber]

how can i merge my models guys without okada

can someone help me

fast

asap

[proper shale]

mainline rvc

[tough fiber]

can u gave me link pls

[proper shale]

https://docs.aihub.wtf/rvc/local/mainline/

[tough fiber]

it isnt take time right like making models

[proper shale]

yea no

[tough fiber]

yes or no didnt get it :D

[proper shale]

i said no

[tough fiber]

oh okay thanks <3

[proper shale]

😭 sorry

[proper shale]

yw !!!

[proper shale]

suppose it's because you're using crepe, switch to rvmpe

rmvpe

😭 god i get it wrong everyday

[limpid plinth]

still nothing

[proper shale]

check command prompt

[limpid plinth]

o

all zeros

[proper shale]

ah

[proper shale]

so

you don't have an nvidia gpu?

[limpid plinth]

no

[proper shale]

or a dedicated gpu in this case?

[limpid plinth]

i do have AMD gpu

[proper shale]

yeah you downloaded the wrong version

[limpid plinth]

i downloaded this one

[proper shale]

[marsh moat]

well, since Ilaria isnt being updated anymore, whats the other one i could use

[proper shale]

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

[marsh moat]

ty

[proper shale]

ila rvc mainline, works basically the same way 😎

[proven hill]

i agree

[proper shale]

OMG

ILARIA APPEARANCE

[proven hill]

https://tenor.com/view/mercy-overwatch-come-here-gif-14280244

wheres embed perms

[proper shale]

what

why dont u have embed perms

wth

[proven hill]

https://media.discordapp.net/attachments/1136305612737753259/1136583660745793587/let_ilaria_help_you.gif

[proper shale]

try again

[proven hill]

thats funny

https://tenor.com/view/mercy-overwatch-come-here-gif-14280244

^this me rn

[proper shale]

ilaria on her way

[proven hill]

https://imgur.com/t9cxTNd

https://media.discordapp.net/attachments/1136305612737753259/1136583660745793587/let_ilaria_help_you.gif

[tough fiber]

waiting to extract lmfao

i have m2 ssd bro wtf is this sh

20 mins still not %50

[tough fiber]

which one is

for merge

[proper shale]

either the 3rd or 4th iirc

4th

4th

[tough fiber]

ckpt one

[tough fiber]

and only pth files is enoguh right for merge

i dont want to use index

[proper shale]

yea

[tough fiber]

it says path

should i upload assets/weights folder and

copy path right

[proper shale]

yeah

[gusty kestrel]

@scarlet venture, I have found 1 results that match your search!

deimon367.

Deadpool - Pepe Toño Macías

• Uploaded: <t:1715979817:d>
• Server: AI Hispano
• Likes: 0
• Lang: Unknown

Epochs

500

Technology

RVC

Algorithm

Rmvpe

Requested by kstalin · Jun 8, 2024, 9:10 PM

[tough fiber]

cant we put more than 2 model

[proper shale]

no sadly

[tough fiber]

idk is it worth. after merge can i add model by one every merge

merge to merge lol

@proper shale well if it work for one run

it was suprised

[proper shale]

yeah, i suppose so

[tough fiber]

oh i forget " path

doesnt work

[slim geyser]

Are you trying to merge models of different sample rates?

[proper shale]

that might be it ngl

[tough fiber]

all my modfels same sample rate i guess but

idk one is working other isnt

[slim geyser]

You guess?

Did you train them?

[tough fiber]

i trained but i dont remember old ones

but specially i choose 32k sample rate always

[slim geyser]

There's no 32k target button

Idk just use w-okada to merge if you can't get this to work lol

[tough fiber]

when i use on okadar

it says initialize or something

it gaves error everytime

[dim wave]

JSONDecodeError                           Traceback (most recent call last)
<ipython-input-8-f9b61a38b267> 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)```

Hello. I'm on the browser, got this mistake at the Download The Model part, after entering the link and running the code. Tried out other links but no luck. Do you have any idea?

[tough fiber]

@slim geyser

[azure marsh]

Suggestions for @dim wave

☁️ Google Colabs

• Applio, by IA Hispano Google Colab
• RVC Disconnected, by Kit Lemonfoot 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
• 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

[dim wave]

I had no idea, will try. Thank you!

[slim geyser]

🤷‍♂️

Idk every error of okada

[tough fiber]

is there way to change sample rate

[slim geyser]

You retrain the model

[rare goblet]

Ayo? @slim geyser level 24 !!!

[tough fiber]

my datas isnt my pc anymore

cant we change sample rate on pth files

[slim geyser]

Nope

You can't

Should always keep your data in the future lol

[tough fiber]

well someone merged 32k sample models and it happen 48k samplerate idk how it possible but

[slim geyser]

Ask them then?

Cuz idk how you'd do that

Unless you're just merging at 32k, and then you take audio from that merge and train at 48k

[brittle wing]

Help

content/drive/MyDrive/Input Folder

output_folder:
content/drive/MyDrive/Vocales

I don't understand how to do it

It gives me errors as it is done now

[tough fiber]

well he just merged on okada he didnt know how to

[brittle wing]

Pls help

[proper shale]

spaces in folder name, remove those in both drive and the colab path you're putting it on, it should work

[brittle wing]

I don't understand 😦

It's difficult net

It is hard*

[rare goblet]

Ayo? @brittle wing level 9 !!!

[brittle wing]

.

[viscid sigil]

does anyone know how to use the voice changer in apps

to set the iput

pls

[proper shale]

https://rentry.org/VoiceChangerGuide#virtual-audio-cables-mandatory You need Virtual Audio Cables

[proper shale]

remove spaces in the folder name

[brittle wing]

content/drive/MyDrive/InputFolder

Yes?

@proper shale

FileNotFoundError                         Traceback (most recent call last)
<ipython-input-3-97d7db895b10> in <cell line: 74>()
     72 extensions = (".mp3", ".wav", ".flac")
     73 
---> 74 uvr_cli(audio_input, output_folder, extensions, output_format, model)

<ipython-input-3-97d7db895b10> in uvr_cli(audio_input, output_folder, extensions, output_format, model)
     37         audio_input = "/content/temp"
     38 
---> 39     for audio_files in os.listdir(audio_input):
     40         if audio_files.endswith(extensions):
     41             found_files.append(audio_files)

FileNotFoundError: [Errno 2] No such file or directory: 'content/drive/MyDrive/InputFolder'

[proper shale]

it probably is content/MyDrive/InputFolder

[brittle wing]

Pls help

[proper shale]

I'm trying

[compact violet]

Hi
I have some questions and I hope someone answers me

1. What is RVC Titan ? What's the difference between it and the regular RVC?

2. Is there any way to make the generated AI vocals sound less robotic in DAW ? I mean is there a plugin can do it and make it sound more natural?

3. Is it okay if I used vocals from youtube to train a model? I found Dolby Atmos stems there and there are lots of clean and dry vocals in these stems. But I can't get them anywhere except youtube and isolating lead vocals using ai models like those in mvsep.com doesn't always work ..

Sorry for these long questions

[proper shale]

1. TITAN is a new pretrain for RVC. It is a good alternative for when a model screws up with the original pretrains.

2. I'm not sure, although I believe it can sound pretty good when mixed well

3. Yeah, just train at 32k sample rate

[compact violet]

Thank you ❤❤

[proper shale]

You're welcome :)

[worldly lodge]

i cant see tensor board in the window when i open the link. when i inspect the page im met with this error in the console

does anyone know a fix for this?

ive seen other errors like this online but i cant understand the jargon they are saying

same error

fire fox

same thing

[rare goblet]

Ayo? @worldly lodge level 3 !!!

[brittle wing]

I'M SEEING OT FKE THE FIRST TIME

[worldly lodge]

i fixed it

had to open this file

and add a hashtag to line 190

for some reason the browsers hated that line

[worldly lodge]

well now ive run into another problem

its not showing any data

FML

is there a specific point where the graphs start to show data?

does this only evaluate every saved epoch or every single epoch

:D

you're awesome, thank you so much

[mortal anchor]

does why anyone know why my rvc voice glitchs?

[worldly lodge]

small/dirty dataset or overtraining

that would be my guess

[mortal anchor]

no like the res goes to more than 6k ms

when i tried talking

[worldly lodge]

ohhh, i havent touched the speech to AI yet sorry

[lusty mirage]

what is titan?

[tame mica]

#✨│ai-help message

[slate delta]

how do i help reduce static noise

[plush dew]

what gpu do you have

[spark ridge]

Hi, do you need python and pytorch?

[rare goblet]

Ayo? @spark ridge level 1 !!!

[plush dew]

to run what rvc? yes

[rose arrow]

why does the voice sound muffled at times?

and what makes the res go up

[spark ridge]

what about for okada?

[plush dew]

ofc

but it you download it from their hugging face you shouldn't need to install anything iirc

[spark ridge]

is he wrong?

[plush dew]

python comes with okada

[spark ridge]

ohh

[plush dew]

you just don't need to install it yourself

[spark ridge]

I just ran the start_Http and it's installing things, I just wait right

[plush dew]

are you trying to use the realtime voice changer?

[spark ridge]

yes

[cloud finch]

Do you need a NVIDIA GPU for applio

[plush dew]

w8 i might be confusing with the original rvc

[spark ridge]

btw do I need to keep the cmd program to use voice changer client?

[plush dew]

that yes

[rare goblet]

Ayo? @plush dew level 4 !!!

[spark ridge]

Ok

Lemme restart brb

[plush dew]

I'm not sure about what I said earlier about python tho, I mixed up stuff

I have never used okada locally

[spark ridge]

it doesn't open

I mean it opens but

[cloud finch]

!help

[tawdry gull]

LunaBot 🌙#9997

LunaBot 🌙 is the perfect music bot! Feature rich with high quality music! And Custom Playlist

You can start listening music by just joinning a voice channel and typing: /play [song name or link] (Remove brackets).
We support only Spotify, soundcloud, bandcamp and more!

To view more help on a specific command or category, run
/help <command> or /help <category>

Important Links:
Support
Premium
Invite

Command Categories:
🎶: Music
💰: Premium
⚙️: Utility
📕: Admin

Select A Page From Dropdown Menu Below

LunaBot · Jun 9, 2024, 5:44 AM

[cloud finch]

wait fuck no

[plush dew]

idk does it say anything on the terminal

[spark ridge]

howd o u fix this

[rare goblet]

Ayo? @spark ridge level 2 !!!

[spark ridge]

uh

cmd prompt right

[plush dew]

ye

[spark ridge]

oh

it opens now

I waited like

10 seconds

[plush dew]

good to hear

[spark ridge]

what now?

[plush dew]

have you installed va cable?

[spark ridge]

vb?

[plush dew]

yes

[spark ridge]

yes

vb cable

wheres the input

[plush dew]

choose it as you output

[spark ridge]

nvm

ok

[plush dew]

input is your microphone

[spark ridge]

My output is vb cable?

[plush dew]

yes

[spark ridge]

then?

[plush dew]

then choose a model and hit start on the top right

[spark ridge]

I don't hear anything if I test it on discord