#✨│ai-help
1 messages · Page 55 of 1
i just accidentaly sent an uncompleted question bruh
damn no embed perms 
anyways
i dont know if this question has already been asked but, how do i resolve this error?:
C:\Users\binx2\Downloads\AIvoicemodels\RVC\Mangio-RVC-v23.7.0>pip install tensorflow
ERROR: Could not find a version that satisfies the requirement tensorflow (from versions: none)
ERROR: No matching distribution found for tensorflow
[notice] A new release of pip is available: 23.2.1 -> 23.3.2
[notice] To update, run: C:\Users\binx2\AppData\Local\Programs\Python\Python312\python.exe -m pip install --upgrade pip
C:\Users\binx2\Downloads\AIvoicemodels\RVC\Mangio-RVC-v23.7.0>pause
Press a key to continue . . .
(im trying to download TensorBoard from this pinned message #✨│ai-help message)
C:\Users\studi\Desktop\RVC\Mangio-RVC-v23.7.0_INFER_TRAIN\Mangio-RVC-v23.7.0>runtime\python.exe infer-web.py --pycmd runtime\python.exe --port 7897
'runtime\python.exe' is not recognized as an internal or external command,
operable program or batch file.
C:\Users\studi\Desktop\RVC\Mangio-RVC-v23.7.0_INFER_TRAIN\Mangio-RVC-v23.7.0>pause
Press any key to continue . . .
anyone know whats wrong?
oh don't use that
You aren't meant to use conda & docker
dont use mangio rvc
what?
mangio rvc is not working for me so yeah just don't use it
u got one version of any doing real time???
Ayo? @blazing salmon level 1 !!! 
_ _
technically i could say the same about applio, mainline, rvc studio, etc
cuz i have a mac 💀
mangio is literally the most stable
: / for me it doesnt works : / ( im a windows user )
maybe ur doing something wrong?
idk i just installed all of it step by step
but i think this may work https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/docs/en/README.en.md
Ayo? @void roost level 1 !!! 
yeah this one is very stable too
ok thnkx
i can get the web gui running, but whenever i try the "realtime" then i have errors
(okada) macbook@MacBook-Air-de-Macbook DDSP-SVC % python web*.py
Running on local URL: http://127.0.0.1:7858
but i know there is another menu for live, ... and on any version i have an error then. DDSP,RVC,...
RVC Guides (How to Make AI Cover)
Translation by country
ive made a model, am I right that I need this files to use it? (I just dont know where it should be saved so idk, seems like thats it)
nope, the pth u need to use is the one from weights
what about the index and config
latest one
index is fine, don't need config
sooo theres a problem
Ayo? @agile storm level 2 !!! 
oh good to know
i am talking about those menus
uhh, I tried using a model and it resulted this error:
File "D:\RVC1006Nvidia\infer\modules\vc\modules.py", line 185, in vc_single
audio_opt = self.pipeline.pipeline(
File "D:\RVC1006Nvidia\infer\modules\vc\pipeline.py", line 410, in pipeline
self.vc(
File "D:\RVC1006Nvidia\infer\modules\vc\pipeline.py", line 221, in vc
if protect < 0.5 and pitch is not None and pitchf is not None:
TypeError: '<' not supported between instances of 'dict' and 'float'
Traceback (most recent call last):
File "D:\RVC1006Nvidia\runtime\lib\site-packages\gradio\routes.py", line 321, in run_predict
output = await app.blocks.process_api(
File "D:\RVC1006Nvidia\runtime\lib\site-packages\gradio\blocks.py", line 1007, in process_api
data = self.postprocess_data(fn_index, result["prediction"], state)
File "D:\RVC1006Nvidia\runtime\lib\site-packages\gradio\blocks.py", line 953, in postprocess_data
prediction_value = block.postprocess(prediction_value)
File "D:\RVC1006Nvidia\runtime\lib\site-packages\gradio\components.py", line 2076, in postprocess
processing_utils.audio_to_file(sample_rate, data, file.name)
File "D:\RVC1006Nvidia\runtime\lib\site-packages\gradio\processing_utils.py", line 206, in audio_to_file
data = convert_to_16_bit_wav(data)
File "D:\RVC1006Nvidia\runtime\lib\site-packages\gradio\processing_utils.py", line 219, in convert_to_16_bit_wav
if data.dtype in [np.float64, np.float32, np.float16]:
AttributeError: 'NoneType' object has no attribute 'dtype'
probably messed something up
the last pic is mangio rvc fork realtime gui
Probably don't use that tbh
voice-changer works better and is less jank
i would, any of them doing what i want, ahahah
uhh.. okay? I mean, I tried inferring with my model that I just made
on a default mainline rvc thing
and it resulted this error that I send above
cannot help for that, i am just trying to use as a voice changer, training I never tried...
mangio realtime rvc gives an error, also it only starts to "work" when I choose both windows directsound devices, when I tried choosing two different ones it was stuck on <All keys matched>
mangio realtime moment
I'd like to use a model on this discord but I have no idea how to use rcv... can you recommend me any video tutorial or.. a guide to get started with that poor favor
-colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HF, by r3gf Huggingface Spaces
- AICoverGen, by r3gf Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
- Advanced RVC Inference, by neuclya Huggingface Spaces
Does anyone else get stuck on this while making a account on huggingface? I just did the "you're not a robot" test and now it's stuck on here https://gyazo.com/8d50ddfb36c40bda6b1b71bae000b1a1
Plsss help me bc I've just made an ai cover minutes ago but then this error appeared, i can't run the first option, "dependencies" "clon github repository" "download the base model"
BRAND NEW FEMALE VOICE MODEL!!
Female e-girl sexy voice model for Okada (RVC V2) is now avaliable on my Ko-Fi!
Get it now here! https://ko-fi.com/s/734d5f276c
Or find other female models (including free ones) here: https://ko-fi.com/ilariaowo
20% discount if you DM me!
Does it say anything?
I think it says "ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
lida 0.0.10 requires fastapi, which is not installed.
lida 0.0.10 requires kaleido, which is not installed.
lida 0.0.10 requires python-multipart, which is not installed.
lida 0.0.10 requires uvicorn, which is not installed.
llmx 0.0.15a0 requires cohere, which is not installed.
llmx 0.0.15a0 requires openai, which is not installed.
llmx 0.0.15a0 requires tiktoken, which is not installed.
tensorflow-probability 0.22.0 requires typing-extensions<4.6.0, but you have typing-extensions 4.9.0 which is incompatible."
Ayo? @lone pivot level 1 !!! 
Maybe it disconnected?
What Colab notebook r you using?
Send the link if u want to
Sadly this is outdated
-colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HF, by r3gf Huggingface Spaces
- AICoverGen, by r3gf Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
- Advanced RVC Inference, by neuclya Huggingface Spaces
Try AICoverGen or Ilaria RVC
is it online too?
Both are online yeah.
Thanks,I will try to see if it works for me
Im trying to covert a 22 minute audio file, Im not sure if it is working or not, but after 5 mins progress stays at 0. Any ideas? using Applio btw
it seems very complicated :
It is, at first, but you'll probably be able to understand
And get used to it
It's probably doing it, give it some time
I'll give it a shot, if i have issues can i ask u ? o.o
What is the best index ratio???
Yeah just state your issues here
-colab
Suggestions for @lyric vine
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HF, by r3gf Huggingface Spaces
- AICoverGen, by r3gf Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
- Advanced RVC Inference, by neuclya Huggingface Spaces
Read the #1159513888199540817 if confused about the one you'll use
But no work
All of these work
This depends on the audio you're using. Try stuff out
You don't need to ping
The RVC models aren't working for me
oh i cant post images here ? o.o
Ayo? @proper horizon level 1 !!! 
my cpu around 50% when using it is it normal
ai voices arent working for me
hey can anyone help me
That's an old Colab - check the ones I linked.
Yeah sure, what's the issue
Where
Ayo? @lyric vine level 2 !!! 
i have such great models but the issue is when i try to make some covers the models just arent able to hit the correct notes
-colab
Suggestions for @lyric vine
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HF, by r3gf Huggingface Spaces
- AICoverGen, by r3gf Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
- Advanced RVC Inference, by neuclya Huggingface Spaces
Are they offtune or they just can't reach the notes?
Witch one
both at times
Whichever fits what you wanna do
they sometimes sound cracking
AICoverGen is good for covers so
can someone help me, whenever i use this and speak it plays back my normal voice instead of the ai
and what i cant understand is how people are making covers of songs with their models sounding crisp and good but im over here struggling even though i use UVR5 and have very good models
Your input/output settings could be wrong
The input output settings should be like this in W-Okada:
Input - Your mic
Output - CABLE Input
And in Discord:
Input - CABLE Output
Output: Your headphones
I need some new guide on this, because now im having an issue where if im able to hear my voice through the rvc software, it wont pick up on the game im using it for, but if I change some settings and I cant hear it, thats when it works, if that makes sense. What are microphone settings that work best? I swore I had to use Line 1 for my output but it just doesnt seem to work
what do the collabs do and is there settings that are ''default'' that we should set or we just play with them and find what fits us
my settings are perfectly fine, but the voice changer wont play
Ayo? @vocal mirage level 1 !!! 
Refer to the thing I just posted, but instead of discord it can be another app
all of my models are rvmpe models
Honestly I'm quite unsure, it could be the acapellas you're using, y'know
For inference
yeah but what else can i do after using uvr5 to get lead vocals
Make sure they're like the ones I just posted
I mean, UVR5 has Karaoke stuff?
You probably already have the lead vocals
i used that and it gives the raw vocals as lead vocals and sometimes if lucky id gives me ad libs or high notes isolated
But some songs give problems
exactly but then how do other people make ai covers of these songs i struggle with
Maybe they're using other Karaoke models?
MDX Karaoke is pretty decent
thats exactly what i use
first i get all vocals
then i use reverb hq
then i use vocal extractor
then i use karaoke
thats the routine
you know the mdx all vocals
@proper shale can u help me out
what's up
basically the rvc voices aint working
even the ones that come with the voice changer
Does CMD say something?
uvr mdx net 1
wym
Yeah I don't use UVR, sorry for the confusion. Anyways, I don't see the problem with isolation so it probably isn't thst
The terminal, command tab, black screen with text, whatever you wanna call it
Ayo? @dapper osprey level 1 !!! 
is it supposed to say that?
nooope
how do i fix it?
can you give us more actually
more what?
yep, it failed loading the pretrains, try deleting the pretrain folder and restarting W-Okada
wheres that
inside the MMVCSERVERSIO folder
this?
yeah
alr then how do i restart with W-Okad
just close the cmd tab
and reopen it?
yeye
yea keep that running
alr i will ty
Hello! is there a way to turn off the playback off the voice but still have the voice be recorded? thank you!
Hey Guys, ive been experimenting with RVC voice models for a bit but i was wondering how some of you are able to get the voices almost identical to the original
For example, I saw a video on TikTok of a character singing, but when i used the exact same model, setting the Transpose to 12 would be just a little too high, and 11 would be a little too low, I even tried using the exact same song but to no avail
Ayo? @wheat shell level 1 !!! 
You can use decimals
🎙️ Realtime Voice Changer (Local)
Suggestion for @soft tiger
Description: This one has more options and is somewhat more convenient to use than Real-time RVC.
Link: Rentry
Credits: ravencutie21
Description: More accurate than W-Okada's, but requires a decent GPU.
Link: Google Docs
Credits: teas.hi
Description: Text to speech with RVC
Link: Rentry
This will help
🎙️ Realtime Voice Changer (FAQ)
well, now i feel stupid
Modification by the user hina so they add extra features and work
ooh okay i see
and if iwant to try a model from discord i just download it and import it to the voice changer client ?
yeah but u need to extract first to upload model and index separately
u see i tried to do stuff like that and play with settings
but i think its nowhere near what i hoped it'd sound like
I'm giving up. Thank you
Theres too much like ''weird sounds when not talking'' and the ''speach recognition'' like im either talking autisticly or its just not hearing me xD
how many pitches and crepe hops to make elaina's voice anime-like
Full AI Voice Model Training Guide (Local)
Link: YouTube
Credits: Christopher Villanueva
Model training with Mainline RVC
Link: Rentry
credits: Raven (ravencutie21)
AICoverGen Colab Guide
Link: Google Docs
Credits: Eddy (Spanish Helper)
Create a model with RVC disconnected (colab)
Link: Google Docs
Credits: Angetyde
How To Make an AI Cover With Ilaria RVC
Link: Rentry
Credits: 👽 Julia (ailen2091)
Hi, has anyone worked with shitty audio for a model?
RVC Guides (How to Make AI Cover)
Translation by country
to resume training a model so i need a index file or just the pth
Ayo? @uneven scroll level 3 !!! 
my gasoline broke
hello, i have a quick question, my mel graph and d/total still decrasing but my g/total it's flatting and rising a bit, however the other two not, should i continue training?
is there a working hugginface?
-colab
Suggestions for @slender lotus
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HF, by r3gf Huggingface Spaces
- AICoverGen, by r3gf Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
- Advanced RVC Inference, by neuclya Huggingface Spaces
Rule 6
I’m trying to make it so I can hear my Rvc and be able to speak in game but currently I can only do one of those things any help to fix this issue?
I’ve also been using the Line 1 device and that works to let me speak but I can’t hear, then I switch to my main headset and I can speak and hear but it doesn’t work in game
Does anyone else get stuck on this while making a account on huggingface? I just did the "you're not a robot" test and now it's stuck on here https://gyazo.com/8d50ddfb36c40bda6b1b71bae000b1a1
You can make an ai cover using Ilaria RVC online @sour lion
If you need a guide it’s the link I just posted
Got it! Thanks mate! :DD
is it ok if it says index not used in huggingface when i make a cover
do i ONLY need a .pth file and the training data to resume training for colab? what else do i need
I saved a .pth of early training but thats it so is it useless now
does anyone have rentry epoch site that llaria made
does anyone have the site for it
do you have the rentry epoch site that llaria made
What
bc i had the site but cant find it
When did Ilaria make a rentry on epochs
the epoch guide that llaria made
like idk 2022 but yeah i cant find the link now
Talking about Ilaria audio analyzer?
talkin bout dez nuts in yo mouf
no llaria epoch guide that talks abt like if your dataset audio is like 2mins you have to set it to this or that epoch
he made it but idk where i can get the link
she*
Talking about this
talkin bout dez nuts in yo mouf
This was made by nick and is not accurate
i know it is literally more than 8 hours later but i forgot to say thx
Ayo? @random badge level 1 !!! 
okay back but yeah im asking for that one do you have the link for it
you know who else is asking for that one do you have the link for it? MY MOM!
@prime hemlock do you have the link for the rentry for the epoch that llaria made
i need that for help for the my ai model training im making
idk what the rentry link she made, but if you are trying to make a model, i can help with some questions you might have
if i have a 2min dataset audio what do i set it to do yk
my suggestion is to set it at 300-350 epochs, you can go higher if you want to keep training after it is done
oh okay thanks ill do that
cool
yup cool
what files are required for resuming training i dont know what to download and its super confusing
BRAND NEW FEMALE VOICE MODEL!!
Female e-girl sexy voice model for Okada (RVC V2) is now avaliable on my Ko-Fi!
Get it now here! https://ko-fi.com/s/734d5f276c
Or find other female models (including free ones) here: https://ko-fi.com/ilariaowo
20% discount if you DM me!
sexy e girl voice model is a thing?
never knew that 😭
How does one figure out what the min and max pitch should be in Applio? I've looked through all the docs and couldnt find anything on it
Depends on your vocals and high and low you want your model to go
I just ignore it
ok
how do i save a checkpoint in colab do i have to stop it
when i install step 1 it says "ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
lida 0.0.10 requires kaleido, which is not installed.
torchdata 0.7.0 requires torch==2.1.0, but you have torch 2.0.1 which is incompatible.
torchtext 0.16.0 requires torch==2.1.0, but you have torch 2.0.1 which is incompatible.
torchvision 0.16.0+cu121 requires torch==2.1.0, but you have torch 2.0.1 which is incompatible"
and also, when i try to do step 2 it says im trying to execute forbidden code
💀 🔫
I have a fan in my background that my mic picks up in the RVC client is there anything that can prevent it from turning my fan into a jumbled muffle?
Turn down in
RVC Guides (How to Make AI Cover)
Translation by country
are rvc only for regular voice or it also works when you yell?
does it stil accurately convert the yelling? i doubt that
Depends if the model had yelling in it
But it can do good
i just downloaded RVC-GUI from the tutorial made by Rizzardo AI and i can't find out how to get the program to open. 😭
you're welcome :)
-rvc
Full AI Voice Model Training Guide (Local)
Link: YouTube
Credits: Christopher Villanueva
Model training with Mainline RVC
Link: Rentry
credits: Raven (ravencutie21)
AICoverGen Colab Guide
Link: Google Docs
Credits: Eddy (Spanish Helper)
Create a model with RVC disconnected (colab)
Link: Google Docs
Credits: Angetyde
How To Make an AI Cover With Ilaria RVC
Link: Rentry
Credits: 👽 Julia (ailen2091)
Hello! I'm trying to make an ai voice with a friend and I'm wondering if there is a good script or document where it would have everything I need to make a good ai voice
There's #1159513888199540817 for #1159588254220288121, for example, and also to create models with RVC Disconnected. Read some of these guides and you'll be good to go
thank you so much
You're welcome, good luck on the models :)
Lmk if something goes wrong by the way - I'll try to help asap
I have a feeling I might have said it wrong because I tried asking before on a different place and I got meh results
thank you
I'll just ask it differently
is there a document or a script meant for ai models that my friend can read out loud so that I can have a good ai voice
Ayo? @brittle wing level 1 !!! 
It really depends on the dataset though. But yeah if the other place wasn't the greatest the model would be meh
Ohhhhh wait lemme find it
thank you
There's an Azure TTS script publically available, it'll certainly help with training the model
is there a link to it?
This is very useful
Not really, you can use part of it
10-20 mins and you should be fine
nah just in total
Ah, okay! thank you so much!
@proper shale why is taking so slow
Is Mangio a good RVC fork?
I've got it working, but I'm not super happy with the results. Probably user error.
Just wondering if others are using it with success.
RVC Guides (How to Make AI Cover)
Translation by country
😭
aicovergen has issues on colab again...anyone got an updated / working link?
Use Non webui i think it will work
need webui otherwise i can't use it :/
Why?
bc i can't run it locally
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HF, by r3gf Huggingface Spaces
- AICoverGen, by r3gf Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
- Advanced RVC Inference, by neuclya Huggingface Spaces
but where's the ui in the end then?
Use 2nd one
You will got everything
i didn't ask abt the link i asked how i get to the ui if it's not in the web bc i can't run anything locally
You don't need to run anything locally
so is there just no ui at all then or?
Non UI is just like web UI! Bhot works same
hm it doesn't tho since i use local files so it seems much harder to make that work + i need to work with multiple models
Upload your files on huggingface or Google drive
i don't want my files to be available to other people...
Ayo? @turbid badger level 3 !!! 
Keep it private
idk how i rlly just came for a fixed or working webui link...
how do i fix the traceback issues?
Traceback (most recent call last):
File "C:\Users\ollie\Desktop\RVC1006Nvidia\RVC1006Nvidia\runtime\lib\site-packages\librosa\core\audio.py", line 155, in load
context = sf.SoundFile(path)
need help with smt??
yeah the webui aicovergen colab is having issues again i was looking for an updated/working or fixed link
here u can find the eddy's version
i used it yesterday
Rvc is an open source project used for voice cloning and voice model training
that should work
Which one should I go for?
faster
i need a webui version since i use my own models locally and don't wish to upload them to huggingface :/
Yes
upload them on drive (?)
That's why it is developed
.
I suggest the same!
i don't want to upload them at all...i hope somone can provide a working webui link soon
Now what?
Keep them private! Or use it locally
i dont see the problem if u use them locally
.
u need to upload ur model btw use this chat
#🔍│help-w-okada
what does the traceback mean when i am trying to isolate voices/reverb and echo
-Egirl
Suggestion for @brittle wing
@brittle wing just read here
how do i use them in the thing then if i only have them locally? it clearly asks me to insert a link to them...in the webui thing i can just upload them in the gradio
oh sorry i saw u wrote that u used them locally
You have to upload it in Google drive, then you have to copy a link From drive
just upload the ones that u need in drive or mega or mediafire etc. and get the link
are you saying no one is ever going to fix the webui version?
I think It could take some time
@turbid badger its really a problem?
Upload your files to Google drive and manage access to everyone with link after that paste that link on nonui. After that change it to private
last time it took like a day i assume it's a common occurrence no? or do u think it will take a month?
yes
internet connection
how many models do you have to upload?
I don't know about it
i don't think it has anything to do with my connection it's colab so it clearly needs to be worked around in the coding department
6
i meant the drive uploading...
u replied to my message about the webui thing being fixed tho
That's not too much
?
my brain is abt to burn
i'm not willing to upload them tho i'm waiting for the webui version to get fixed
DIOCANE
that's what u replied to with "internet connection"
So wait for someone to fix it
But I don't think that there is not any difference!
yes i simply came in here to ask if someone already has a fixed link or one that works in general lol
there is tho bc in the webui version i don't need to upload anything to drive or huggingface
But we are here to help you with alternative(s)
thank u for the effort i was just asking for a new link tho. u don't seem to have one yet so thank u for now
But you need to upload it on Webui ! But if you are using non webui . You just have to paste a single link and it's done
Your welcome! But you can also try new things!
i am not looking to upload it elsewhere and make a link tho so
Okay. So keep waiting! If you find our suggestions are useful you can use it!
but thats Dr Jr...
i said that the drive uploadation is influencede by internet connection
Ayo? @tender pond level 2 !!! 
hello?
Ayo? @woven furnace level 1 !!! 
u replied to my reply to that convo tho
Ayo? @turbid badger level 4 !!! 
no one replied to my question 😭
@copper pebble
can someone help me?
tho
sup
so i'm following this tutorial https://www.youtube.com/watch?v=oOBjntI2xK0
i'm stuck on the part after installing RVC GUI. i had to install another thing so i can open the file. so then now it's unzipped. but everything i tried clicking on just opens more files. i don't know how to get the program itself to open.
just dont use RVC GUI cuz is pretty outdated.. use ilaria rvc or aicovergen
u can find guides for those here #1159513888199540817
thank you 😭
-colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HF, by r3gf Huggingface Spaces
- AICoverGen, by r3gf Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
- Advanced RVC Inference, by neuclya Huggingface Spaces
i'm still just opening files 😭
https://discord.com/channels/1159260121998827560/1175615544037212200 this is the colab guide
when i click on the program
Ayo? @woven furnace level 2 !!! 
u dont need that
it's aicovergen?
huh
this is a colab
it's confusing
not really 😭
do someone have any working colab interference?
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HF, by r3gf Huggingface Spaces
- AICoverGen, by r3gf Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
- Advanced RVC Inference, by neuclya Huggingface Spaces
yh it does
how
Ayo? @dim rain level 1 !!! 
how to use RVC v2 in real-time?
Unstable af but it works for me
I have found 8 results for the search mariah...
But it sounds robotic why is that? My ai model
I set it to 350 epoch but it sounds robotic which epoch do i set it to
How i load my audio in the new version of rvc
What new version?
Has it failed to train index?
No it hasnt its just my ai model sound so robotic
just copy the path of the audio and paste it where it tells you to
Do you have that bc i want to use to try it out
only with path? okey
Ayo? @warm yarrow level 1 !!! 
ty Brazilian mod
How long was your dataset
you're welcome :)
2mins inductivegrub said to put it to 300-350 epoch
yeah you should probably get more dataset
if you can
if not then train more
Bc im trying to make josh dataset
Josh peck from drake and josh
Ayo? @hidden drum level 8 !!! 
Do you have a 5.1 of drake and josh
yeah you can definitely get more imo
nope, sadly
Bc goyo is gone sadly
So idk how to get voices from drake and josh
free isolator
crowd removal can remove laughs, demucs dnr can remove the bg noise
pls create an account so u dont get long queues
I did but for the crowd removal and remove laughs do i use demcs dnr
yeah u can, if it isn't effective with the laughs try the crowd removal
What model is crowd removal
MVSep Crowd Removal
I hate long queues its like so annoying
But ill try that for sure
Abt when theres back to back talking going what do i use for that which model when 2 ppl from the show are talking back to each other
Don't think there's a model for that, so you'll have to manually trim out those parts
Oh damn okay
Time to cook
Good luck on the model btw :)
yo that's copyrighted
but yeah you gotta remove reverb
oh okay
and btw you're welcome ;)
i wont post the model with the copyright on here
It's alright :)
naw i aint tryna make this server get deleted again due to copyright so i aint gonna post it here
Yeah fair lol
bc this server got deleted once once is enough if it gets deleted again i wont have any ai music to work on
yeah exactly!
like remember what happended to the google colab it wasnt working bc google was tryna take it down bc so many ppl arent paying for it lol
Yeah i do, that was a terrible time ngl
ohhh
i think that might be copyrighted too 😭
Oh shoot
Nope
Naw its fine
Fr terrible time
RVC Guides (How to Make AI Cover)
Translation by country
theres a problem with my rvc, for some reason whenever i try to convert a file the program just closes
Yeah thats when you dont pay for google colab
Anyone knows whats this about?
index -1 is out of bounds for axis 0 with size 0
-> Freshly trained model, dunno what happened there
i dont use google collab at all
Wait what? lol
This happens on your local isntance?
yea
it just closes after a minute of trying
Ayo? @rigid spoke level 1 !!! 
there were errors on my original rvc gui but now it just closes
If it has worked before, i cant tell you without checking but if not, i guess a broken installation
probably
what gpu?
not entirely sure
Im not really aware if RVC will run with AMD gpus (i think there are methods nowadays but you gotta do some extra stuff).
So that could also be your problem if youre not using NVIDIA gpu
Ayo? @gray crow level 2 !!! 
i think its intel gpu so idk
Check in task manager
How do i open the rvc Gui
Im new to this and does downloading models normally take long to download or what?
How do i get the download Link?
i think you open the batch file
hi can someone help me real quick on Google Collab
ValueError: rate must be specified when data is a numpy array or list of audio samples.
Ayo? @nova plaza level 1 !!! 
Bro im new but i need to find links with mega or something. Over here i only find huggingface or some shit. I know im stupid but can anyone help me with it?
Don't. GUI is really outdated. Use an updated version
Uhh it shouldn't. But that depends on your internet speed
Ayo? @hard latch level 1 !!! 
it was because
For what exactly?
my microsoft edge had to many tabs open
Why do you want Mega links exactly?
The versions of RVC that support model download through links also support links from hugging face
Or Google Drive
open the .bat
Can anyone help?
"Detecting latest model...
Copying model files...
NameError Traceback (most recent call last)
<ipython-input-5-960c768e55b5> in <cell line: 48>()
48 if(not skip_models):
49 print("Copying model files...")
---> 50 if(save_only_latest_ckpt):
51 TSTEP=2333333
52 get_ipython().system('cp "{DATASET_PATH_COLAB}/D_{TSTEP}.pth" "{DATASET_PATH_DRIVE}"')
NameError: name 'save_only_latest_ckpt' is not defined"
When trying to export the model
is that on the googlecollab
damn i really only know local training mb
It's fine
Ayo? @ashen glen level 2 !!! 
if you have a ok pc i can explain how to train locally if you want
on a mac ahaha
holdup
there’s a mangio strain for mac 🙂
it didn't work when i tried it sadly
can someone send me rvc colab link
the one im using is outdated and the runtime keeps getting disconnected
-colab
Suggestions for @empty saddle
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HF, by r3gf Huggingface Spaces
- AICoverGen, by r3gf Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
- Advanced RVC Inference, by neuclya Huggingface Spaces
which one do i use
Training or covers
cover
First or 2nd
did you run set training variables and did the dependencies step run fine
Oh weird
Alright, let me know what goes wrong exactly
Hope you can train your model
omg wait ur helper? mj am i bugging if i ask u rn
?
do i ONLY need a .pth file and the training data to save a "checkpoint" for rvc disconnected colab? what else do i need
I saved a .pth of early training from the weights folder but thats it
Can I use that .pth alone to like. make a model from earlier in the training
You need to have the D and G pths
the final ones I get from exporting at the end??
I can use that for the checkpoints?
If you didn't export model... you probably didn't get the model
yeah
those are the checkpoints
But I don't think you can use them for something other than training
- if you wanted to test a previous model it's probably gone
no i mean
ok look this is all the files i got when i exported right. you see g and d is step 5600
I saved a .pth from like 2k steps but idk if thats how you are supposed to do it
I turned off the "save only last checkpoint"
so where are they??
i only got these 5600 step ones
You only got the last steps because you didn't export specifically those steps
Heya, i keep getting into an error message when trying to start the "start_http.bat" file
It loads up for a bit, the RVC opens with a white screen, then in the command box it says
"[344:1229/215737.904:ERROR:gpu_process_host.cc(954)] GPU process exited unexpectedly: exit_code=-1073741515"
over and over again until it says.
"GPU process isn't usable. Goodbye."
I am running Windows 11 Home with 64 Bit
Mainboard: B550M AORUS ELITE
Cpu: AMD Ryzen 5 5600 6-Core Processor 3.50 GHz
GPU: Zotac Geforce RTX 3060 8GB
and 32gb of Ram
I downloaded the right version (i think) and when i try to run it
"MMVCServerSIO_win_onnxgpu-cuda_v.1.5.3.17b.zip" is the name of the version i downloaded
I would like to provide images, but i don't seem to be able to do that because i've rarely chatted in this server before
You have to insert the step number where Export model tells you to to get them
OHHH I CAN EXPORT CHECKPOINTS AFTER I FINISH TRAINING? LIKE SAVE PAST MODELS AND EXPORT?
Yeah
Full AI Voice Model Training Guide (Local)
Link: YouTube
Credits: Christopher Villanueva
Model training with Mainline RVC
Link: Rentry
credits: Raven (ravencutie21)
AICoverGen Colab Guide
Link: Google Docs
Credits: Eddy (Spanish Helper)
Create a model with RVC disconnected (colab)
Link: Google Docs
Credits: Angetyde
How To Make an AI Cover With Ilaria RVC
Link: Rentry
Credits: 👽 Julia (ailen2091)
Just insert step and epoch count
OHHH OMG THANK U THAT MAKES SENSE UGH
;)
ur a lifesaver tysm and uh ya
You're welcome :)
@molten pecan you said i could ping you 
Ayo? @worn nebula level 1 !!! 
ah now i am able to upload images too
Yas
You trying to open mangio?
Or applio?
i don't know a lot about this, i am new to this mostly
what's the difference and how do i know which one i am trying to open?
They're trying to open W-Okada
Ah the usernames
I dowloaded it from w-okada
Ah
Then ask on #🔍│help-w-okada
Hopefully someone will answer you
oki doki, still thanks :3
Juice WRLD
Ok thank you
Ayo? @sharp gulch level 1 !!! 
it's basically changing the pitch
so if I’m changing my voice (male) to another singer (female) = increase but
female to male = decrease right?
yeah
also the index rate the higher it is, the closer it is to the model and the lower it’s closer to the original vocal?
in terms of accents and how things are said, yep
how i donwload it
what do you wanna do
oh so you need the W-Okada Voice changer first
to then use the models
what GPU do you have
oooh
you're using it on colab i get it
u gotta download the model on ur pc, extract, and upload the pth like this:
on the little model tab (this rectangle in the top of the screen) click on edit, see a blank model and upload the pth there
yeah so you can upload the pth to the virtual machine
idk how to do it
Ayo? @vagrant oar level 1 !!! 
i just explained how
you click on edit (besides the big rectangle on top, that's the model bar), then find a blank model, click on upload, then it shows model and index with upload buttons, just upload both and the model should be installed.
mj do you know if this is possible? #🔊│ai-development message
to train an index to be stronger
Ayo? @uneven scroll level 4 !!! 
@proper shale just pinging so u see it
They just meant that, to make an accent strong, you need the index
And not necessarily making the index stronger. You can do that with the search feature ratio option in any RVC inferencer
oh. it isnt possible to like. make an index using one person's voice and apply it to another .pth??
will that break it
You can mix and match indexes
As far as I know
ooo cool. and uh one last thing um
Please help me, the standard voices that were in the program immediately work for 300-400 res, but which I download 20k +
So lets say if im doing an AI cover and feature retrieval 1.0 still doesn't add that much accent. Is there any way to give it more influence
this is the last question sry
Oh i don't think there's much you can do when that happens
Convert them to onnx, reupload the onnx version of the model and use that one instead of the .pth
oh okay. makes sense. thats all i was curious about thx
This is because you're on AMD
Glad to help :)
But how to do it?
"Export to onnx" button
this so stressful, one minute it’s working and now when i try it again, it doesn’t work
i did the same thing last time, idk why it’s not working this time. anyone help?
You are using RVC Disconnected?
Using the Easy 👨 - 10/25
it was working fine like an hour ago 😭
Huh I never heard of that
I think you should use RVC disconnected if you want to make a model
Ohh then
Use this one
So I wanna make the AI models I've got to do some TTS but not singing, what's the best avenue for that?
What is the best inference? for inferring vocals?
You know the local inference tab. Which one is best for inferring vocals. Maybe I'm not using the right one
Which one is best to infer vocals? RVC MANGIO? APPLIO? RVC BETA? OTHERS?
I have mostly rvmpe models and don't know if I'm inferring them correctly
Suno has a model to do that, plus he has one for TTS Bark
Is there a way to do a batch inference? Like, convert a whole folder of small audio clips?
i can't seem to find any working colab or huggingface that works, can someone link a huggingface working link that i can use
-colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HF, by r3gf Huggingface Spaces
- AICoverGen, by r3gf Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
- Advanced RVC Inference, by neuclya Huggingface Spaces
nope
its the newes i just downloaded it
where would someone put a .npy file that came with a model? I don't remember seeing these. Edit: P sure you just ignore them but I'm making sure I'm right.
Person probably included it accidentally
RVC Guides (How to Make AI Cover)
Translation by country
Can someone help me with the traceback errors? im trying to train a model locally and every time i import a file to seperate the vocals i get an error
Ayo? @steady mica level 1 !!! 
is anyone experienced in video face swapping? I've been learning how to do it but am looking for advice. DM me if you are knowledgable!
Ayo? @pale arrow level 1 !!! 
Hi! your talking about deepfakes right?
talkin bout dez nuts in yo mouf
damn
sent you a dm i’m down to explain how to make deepfakes if that’s what your talking about it does take a while though bare in mind
talkin bout dez nuts in yo mouf
can someone help me and send me a link of what they use to make ai covers like the proccess
for hugging face?
does anyone know how to install applio for amd? before i had a working version which broke from update but all the installers keep having the same start up screen and breaking at the end. already tried exe installer of 3.0, 4.0 and 5.0 as well as 2.0 windows bat, 3.0 old and 3.0 amd which all have the same start up screen which either usually breaks or runs cpu without any of the option selections
Ayo? @foggy sand level 2 !!! 
also running the manager usually results in this
can someone do an ai voice for me? the program i use isnt working for some reason and i need this done by tn 😭
how do i completely uninstall applio and all its dependencies
does applio still work?
Locally?
if so do you have site link for the github applio
yeah
Should
i get this error messge it kinda long u guys mind?
failed:Protobuf parsing failed.
Traceback (most recent call last):
File "restapi\MMVC_Rest_Fileuploader.py", line 71, in post_update_settings
File "voice_changer\VoiceChangerManager.py", line 315, in update_settings
File "voice_changer\VoiceChangerManager.py", line 321, in update_settings
File "voice_changer\VoiceChangerV2.py", line 155, in update_settings
File "voice_changer\RVC\RVCr2.py", line 73, in update_settings
File "voice_changer\RVC\RVCr2.py", line 51, in initialize
File "voice_changer\RVC\pipeline\PipelineGenerator.py", line 42, in createPipeline
File "voice_changer\RVC\pitchExtractor\PitchExtractorManager.py", line 25, in getPitchExtractor
File "voice_changer\RVC\pitchExtractor\PitchExtractorManager.py", line 45, in loadPitchExtractor
File "voice_changer\RVC\pitchExtractor\RMVPEOnnxPitchExtractor.py", line 28, in init
File "onnxruntime\capi\onnxruntime_inference_collection.py", line 383, in init
File "onnxruntime\capi\onnxruntime_inference_collection.py", line 424, in _create_inference_session
onnxruntime.capi.onnxruntime_pybind11_state.InvalidProtobuf: [ONNXRuntimeError] : 7 : INVALID_PROTOBUF : Load model from pretrain/rmvpe.onnx failed:Protobuf parsing failed.
so what is my problem
Ayo? @turbid epoch level 1 !!! 
why i had this iuuse
iusse
fr i cant even spell it
i will sleep and i hope somone respond tomorrow
Y'all when I use rvc gui's RVC-GUI batch file, it ends up with an error in the cmd prompt saying "python.exe: can't open file 'C:\Windows\System32\rvcgui.py': [Errno 2] No such file or directory." Any help?
RVC GUI is outdated
Use Orginal RVC or a fork like applio
Oh damn
-local
- Applio-RVC-Fork, by IA Hispano GitHub
- Mangio-RVC-Fork, by Mangio621 Huggingface
- RVC Studio, by SayanoAI Huggingface
- AICoverGen, by SociallyIneptWeeb GitHub
- Replay, by Replay Team Website
- Original RVC, by the RVC-Project team GitHub
You can find more info on the #1159513888199540817 channel. If you can't find your answer, feel free to ask for help in #✨│ai-help. Credits to Faze Masta and Antasma for compiling these links.
guys i'm creating a model
the guide says something about Mode Collapse
what's that
Hello, Is there a real-time voice changer for RVC?
Yeah but Okada is recommended compared to it
Alright I'll head over there
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
lida 0.0.10 requires kaleido, which is not installed.
llmx 0.0.15a0 requires cohere, which is not installed.
llmx 0.0.15a0 requires openai, which is not installed.
llmx 0.0.15a0 requires tiktoken, which is not installed.
orbax-checkpoint 0.4.4 requires jax>=0.4.9, but you have jax 0.3.25 which is incompatible.
pandas-gbq 0.19.2 requires google-auth-oauthlib>=0.7.0, but you have google-auth-oauthlib 0.4.6 which is incompatible.
plotly 5.15.0 requires tenacity>=6.2.0, but you have tenacity 5.1.5 which is incompatible.
plotnine 0.12.4 requires numpy>=1.23.0, but you have numpy 1.22.0 which is incompatible.
pywavelets 1.5.0 requires numpy<2.0,>=1.22.4, but you have numpy 1.22.0 which is incompatible.
??
RVC Guides (How to Make AI Cover)
Translation by country
what the hell do i do
you know who else does you do? MY MOM!
which rvc is the best one?
you know who else is the best one ?? MY MOM!
which rvc is the best
you know who else is the best? MY MOM!
i use mainline
lmao
what is the best girl voice
you know who else is the best girl voice? MY MOM!
agreed
Error downloading file: ENOENT: no such file or directory, open 'C:\Users---\Desktop/install_Applio-windows.bat
"Windows protected your PC
Microsoft Defender SmartScreen prevented an unrecognized app from starting. Running this app might put your PC at risk.
More info"
shut up windows idc
More info
Run anyways
you know who else will try applio again? MY MOM!
you know who else wants to be quiet? MY MOM!
...
you know who else was dropped on the head as a baby? MUSCLE MAN!
is this important?: ERROR: Could not build wheels for lxml, which is required to install pyproject.toml-based projects
@violet heron is this important
ERROR: Could not build wheels for lxml, which is required to install pyproject.toml-based projects
muscles
Ayo? @willow arch level 4 !!! 
i had this same issue did u get it figured out?
hello! im trying to put Shaq's voice into the 300 This Is Sparta! scene but the vocals aren't working for when he says "This is sparta". would this be a matter of settings or model not being trained on the specific frequency required?
What the best fork other than apllio
also is my roku tv's hardware powerful enough to play cyberpunk 2077 at max settings?
What do you think Sherlock?
you know who else does you think Sherlock ?? MY MOM!
Yes!!!
why is my thing "user\onedrive\desktop"
why is onedrive therer
i hate onedrive sooooo much
There's no need to download a new web browser.
Microsoft recommends using Microsoft Edge for a fast, secure, and modern web experience that can help save you time and money.
Try now
you know who else recommends using Microsoft Edge for a fast , secure , and modern web experience that can help save you time and money . try now? MY MOM!
torch is so god damn annoyinf
why do i had to downgrade to python 3.10.6
it worked whenevr i do that
is there a way to convert 40k model into 48k?
just straight to resampling it
but still looks 40k sampling audio in spectrogram (tbh pointless unless there are some superhumans able to hear above 20k frequencies)
there are basically 3 options
Ayo? @clever geode level 1 !!! 
in sample rate
32k, 40k, 48k
i want to convert an already trained .pth model from 40k to 48k
do i have to train it again lol?
yeah have to redo from preprocessing step if it's what you mean
less sampling rate, less likely to have glitched sibilances
istg idk what preprocessing step is XD
i just train
i just dont wanna train the model again, just finding a way to convert an already trained model
if i download from one of the links for a voice, can i do a voice to voice generated thing in this server as well? for contxt im trying to make a character sing a song but all the ai webshites are saying theyre free and fucking lying so itsnot letting me do what im trying to do
-train
Suggestions for @clever geode
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HF, by r3gf Huggingface Spaces
- AICoverGen, by r3gf Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
- Advanced RVC Inference, by neuclya Huggingface Spaces
the trained models as final product can't be altered other than to fuse models (original RVC and Applio have that feature)
can a 40k sample model be fused with another model into 48k sample with this interface?
what is opt_path in RVC easyGUI
how do i train a ai's voice to be better quality or whatever?
thank you
Its where you want the output to be
Like "/content/drive/MyDrive/output_audio.wav"
guys guys guys
so is there any way to separate music from vocals in cloud?
like, kaggle or colab idk
https://mvsep.com/ has some best separation models
^
nah its like I need to separate
there's also a bunch of colabs for those things, they occupy a bit of space on your Google Drive but they are free and get no queues.
there's also UVR and stuff
like I need to separate a 4 hours long thing
damn
that'll probably not work i think
ok 2 hours will be fine tbh
split it in at most 10 mins each
Ayo? @proud elbow level 15 !!! 
I'll see if there is a batch separation
because separating every single part manually
is pain
that may be premium perk
i get an error when using mangio rvc when choosing file path in the train section can someone help
When i add an huggingface link to the RVC i get this message: ----> 4 from mega import Mega. It fails over there and gives an error. Can anyone help me? Im new btw
how to import custom voice
RVC Guides (How to Make AI Cover)
Translation by country
Please help, what to do if I accidentally closed Huggingface page when process is going? How to return?
Does anyone have appolio collab link?
Probably using an outdated Colab. try using the newer ones
-colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HF, by r3gf Huggingface Spaces
- AICoverGen, by r3gf Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
- Advanced RVC Inference, by neuclya Huggingface Spaces
Applio's Colab is probably outdated and will not work as intended unless you have a Colab Pro subscription.
Hi, everybody. Should I remove pauses or RVC does it itself? I know that rvc cutes audio for some parts but does it remove pauses?
You have to do that yourself, and Audacity has a Trim Silences feature. Should be simple
What Colab are you using
And one more question. Dataset can include 1 file?
Yep, honestly better than multiple files
Ok, thank you
i tried to resume training in colab and it started over at 0 again, is that normal?
I watched an installation tutorial video, downloaded and even installed mods, but the voice is not output to the device, for example, I have headphones, my headphones are not in the applications in the input device, and there is both a cable and headphones in the output, the question is how to put a cable into the input device?
Hm, maybe the D/G files didn't save properly
Or, you messed up the settings
What application
they arent there, but it loaded my tensorboard
I would like to know what should be put in the output device and what in the input device
Ayo? @west badge level 1 !!! 
Ok sure but what application are you even using
GitHub Voice Changer
oh, so W-Okada
The input output settings should be like this in W-Okada:
Input - Your mic
Output - CABLE Input
And in any other application:
Input - CABLE Output
Output: Your headphones
I downloaded the cable add-on
or whatever ur virtual audio cable is, make sure it's the output in W-Okada and input in the program you wanna use
the problem is that there are no headphones in the input device
I didn't find them there
Im using W-Okada
You don't need the headphones, the input should be your microphone
Alrighty, what's the issue
try searching for it in weights.gg or #🔍│find-models
I would like the output device to be a cable and I would listen through headphones
I cant find it can u please share it
You can use the monitor option and put your headphones there so you can hear yourself
It probably doesn't exist then
Maybe #1159289738314919936, request it
it exits on youtube I have downloaded the ZIP file but I dont have the URL to put in the voice changer
exists*>
Ayo? @tropic wharf level 1 !!! 
new here
Okay so thank you
hey
Oh just upload it somewhere then
On your Google drive
can i put hte link in the rcv generator then?
yeah
my microphone is in my headphones
so I don't know what to do
Ayo? @west badge level 2 !!! 
Can anyone help me? Im not sure if it detects my GPU. All i can see where i should select the gpu is: GPU(dml) cpu, gpu0
Are you using the AMD version?
If you have an NVIDIA GPU the right version is the one with a GPU dropdown
My GPU is a 3070 and my CPU is a r5 5600x
should i use the the amd one?
Nope, you're probably on the wrong version
The right version is onnxgpu-CUDA. This is a backup of a very stable version https://huggingface.co/RavenCutie21/OkadaVersion15Backups/resolve/main/MMVCServerSIO_win_onnxgpu-cuda_v.1.5.3.15.zip
Thank you
You're welcome! If anything goes wrong explain in #🔍│help-w-okada
Our helpers will try their best to answer ASAP
did u move the .bat outside of the RVC folder?
does the folder have any spaces in its name?
no the folder itself
Ayo? @brittle wing level 1 !!! 
- Applio-RVC-Fork, by IA Hispano GitHub
- Mangio-RVC-Fork, by Mangio621 Huggingface
- RVC Studio, by SayanoAI Huggingface
- AICoverGen, by SociallyIneptWeeb GitHub
- Replay, by Replay Team Website
- Original RVC, by the RVC-Project team GitHub
You can find more info on the #1159513888199540817 channel. If you can't find your answer, feel free to ask for help in #✨│ai-help. Credits to Faze Masta and Antasma for compiling these links.
https://rentry.org/ilarvc_inf_guide my ila rvc rentry is almost at 2k views ^-^
Yayyy
umm everyone how i can fix this one "If you clear the information being managed by this app, it may be recoverable." like is a problem that make it can connect to my input
Ayo? @timber lantern level 1 !!! 
You using okada?
oh ye hihi sorryyy
hello, i have a problem with any rvc model, they're just dont work except beatrice model
my gpu is RTX 4060 Laptop, and Ryzen 7 7335H
Did you download the DirectML version
nope
MMVCServerSIO_win_onnxgpu-cuda_v.1.5.3.17b.zip
Did you select your GPU?
yes
qwerty
