#✨│ai-help
1 messages · Page 26 of 1
aint that for index training
yes
ur referring to the audio selections right?
im not the most tech savvy person do i dont rlly know how to answer this so ill just describe how i got everything to where it was
i started with my audio files which were mp3 and i converted them to wav files using cloudconverter and then downloaded them. after that i went to rvc disconnected and when i got to the point where the rvcdisconnected folder popped up i put a zipped version of that file into the folder
Ayo? @cerulean dew level 3 !!! 
thats most likely the problem
shouldve reexported it in audacity
so how far back do i need to go to do that, can i just do that with the wav file?
Why does it matter how I got the file tho? Why does cloudconvert not work just as well?
Omg ur my savior tho it actually worked
Because codec mismatching
well tysm ive been trying to fix this for 2 days lol
its working now
but the epochs r taking forever since they r actually functioning now lmao
ill be waiting a while
I have found 97 results for the search riggy...
Owner: Kareem AQ
Uploaded: <t:1694444760:R>
This model can be found on the Kits.AI platform, visit their page for more information.
💾 @lethal prism, sent you a DM with the model information!
why is there like that electronic parts
in some parts of my voice
and then
in some
its very clear
hello if someone could help me with this error
AttributeError: 'NoneType' object has no attribute 'tobytes'
thanks
this is full thing
<All keys matched successfully>
Traceback (most recent call last):
File "C:\Users\samus\Downloads\Mangio-RVC-v23.7.0\my_utils.py", line 96, in load_audio
ffmpeg.input(file, threads=0)
File "C:\Users\samus\Downloads\Mangio-RVC-v23.7.0\runtime\lib\site-packages\ffmpeg_run.py", line 325, in run
raise Error('ffmpeg', out, err)
ffmpeg._run.Error: ffmpeg error (see stderr output for detail)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Users\samus\Downloads\Mangio-RVC-v23.7.0\infer-web.py", line 292, in vc_single
audio = load_audio(input_audio_path0, 16000, DoFormant, Quefrency, Timbre)
File "C:\Users\samus\Downloads\Mangio-RVC-v23.7.0\my_utils.py", line 103, in load_audio
raise RuntimeError(f"Failed to load audio: {e}")
RuntimeError: Failed to load audio: ffmpeg error (see stderr output for detail)
Traceback (most recent call last):
File "C:\Users\samus\Downloads\Mangio-RVC-v23.7.0\runtime\lib\site-packages\gradio\routes.py", line 437, in run_predict
output = await app.get_blocks().process_api(
File "C:\Users\samus\Downloads\Mangio-RVC-v23.7.0\runtime\lib\site-packages\gradio\blocks.py", line 1349, in process_api
data = self.postprocess_data(fn_index, result["prediction"], state)
File "C:\Users\samus\Downloads\Mangio-RVC-v23.7.0\runtime\lib\site-packages\gradio\blocks.py", line 1283, in postprocess_data
prediction_value = block.postprocess(prediction_value)
File "C:\Users\samus\Downloads\Mangio-RVC-v23.7.0\runtime\lib\site-packages\gradio\components.py", line 2586, in postprocess
file_path = self.audio_to_temp_file(
File "C:\Users\samus\Downloads\Mangio-RVC-v23.7.0\runtime\lib\site-packages\gradio\components.py", line 360, in audio_to_temp_file
temp_dir = Path(dir) / self.hash_bytes(data.tobytes())
AttributeError: 'NoneType' object has no attribute 'tobytes'
Ayo? @rugged loom level 1 !!! 
RVC is now working, sorry for the inconvenience
Guys
Can I ask something?
How many epochs I need to train a 30min dataset?
Studio acapella
ayo, if my model doehave falseto singing in dataset, why the fck then when I run interference with me singing falseto, model sing it too??
RVC Guides (How to Make AI Cover)
Translation by country
Did you save weights to drive?
Did you do export/save model?
can u tell me how to do
It’s a cell below index training
what about this
Ignore those
ai
Ayo? @placid storm level 8 !!! 
thanks @violet heron
@empty dust I'm tryna make smooth criminal but there are so many voice cracks
those are the settings
idk how to work them anyways
Send the file you are trying to use
Yeah
overtrain?
Yeah, wait a minute
alr thanks
hp5 is for harmonies. hp6 is for backup
Ayo? @tough ice level 2 !!! 
Make sure you remove the reverb first!
Dude, the file quality is terrible.
really? What do I do to fix it?
Ayo? @ancient cloak level 2 !!! 
It will give you both things
I just use default settings inn uvr 5.6
Both the harmonies only and the lead vocals
Depends on what you select as your output
That's the problem
is it available for iphone
Which thing?
For AI covers?
yeah
You can do it on mobile but it's a little slow
It's recommended to do it on a fast computer
For mobile you can use Ilaria RVC
@molten pecan what settings do I put on UVR5.6 for the best quality?
and how do i get that??
My bad I was searching the link
There are plenty of guides in #1159513888199540817
Good luck!
Idk
bro wdym idk I thought someone would know about this lol
thank you
Ayo? @cursive magnet level 1 !!! 
Idk what to do since some covers im making have so much scratchiness and voice cracks.
You could try running the harmonies again with hp5 or hp6
?
can you use ROD in colab?
Use RVMPE
does anyone know what feature did kits.ai used when they started? i made some cool models there but cant see any info ffs. Was it mangio crepe rvc 1 or rvc 2? what was it??
can show d/total
also zoom in the graph a lot more please. set smoothing to 0.97
that’s a old pic
Of my old model
I’ll train another model soon I’ll give more pics
that graph looks too smooth. lower it to like 0.95-0.97
well for future note, use less graph smoothing. You are missing all the local minimum and maximums
how about mine?
dataset don’t look the best
youre gonna have to maximize the graph a bit to see
and ur at 80k steps????
whats the graph smoothng at?
ye bro ur dataset don’t look the best
0.987
try 0.95
But looks like a 1hr+ dataset?
model won’t come out clean
Ye is at Epoch: 81 the max I put is 100
🤦🏿♂️
60k looks like a possible good point. if that is 81 epoch then you have like a 2hr dataset?
Regardless
Might need to continue training to see if the graph is actually reaching minimums.
There is no reason to say the model isnt good
Yk those greyed out orange lines behind the highlighted orange one
You have no information to determine that outside of the dataset size
I think someone told me that but
When they got super high and low peaks
It’s most likely that it’s not gonna come out as good
Idk it happened to me but idk how true it will be for him
Let’s see
Rather ask for samples instead of just saying it wont be good
Ye let’s just see if it’s true
but easily you can comparegood graphs with others no?
just as an example
Where is the d?
Every model is different
best to send samples of dataset or inference
I will send like a demo when it hits 100 epochs is that?
I'd see a inference at 60k steps
it would it be bad if I told you the Save frequency is at 50 💀
Ayo? @hot lagoon level 6 !!! 
thats pretty bad, in the low end i save a 5/10 as the models dont even take up that much space and i just delete later.
I mean id totally pause that rn and change it to 5 and hope
The peak and dips isnt even that bad. I checked with my known good models and many have +-6 g/total
your graph is just so smoothed out and zoomed out
so go back to the 50 epoch then try a Save frequency of 5? just sure I'm understanding this
no you cant go back to 50 and resume training. If you are at like 81 epoch, you should be able to cancel training, change save frequency to 5 and it should save at 85,90,95 and so on after you start the training again.
also can you give me a tip to know where overtarining beings?
whats the best colab or other cloud based Real Time voice changer
-colab
Suggestions for @brittle wing
- AICoverGen-NoWebUI, by Ardha Google Colab
- RVC Disconnected, Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- 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
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.
-realtime
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
my rvc does not work even tho i have all the things since when i runthe .bat it says press any key then when i do it closes
idk
Ayo? @errant spindle level 1 !!! 
i just downloaded the pkg from github
no i did not
i right click then i tried to run the .bat
RVC Guides (How to Make AI Cover)
Translation by country
Ayo? @brittle wing level 1 !!! 
Is there something that will assist my while singing live ? Does anyone know about a VSt or something RVC related that will make your voice sound way way better while singing live ?
Ayo? @crisp plover level 4 !!! 
INFO:beta:Saving model and optimizer state at epoch 10 to ./logs\beta\G_2333333.pth
Process Process-1:
Traceback (most recent call last):
File "C:\Users\strin\Desktop\Applio-RVC-Fork\Applio-RVC-Fork\runtime\lib\site-packages\torch\serialization.py", line 441, in save
_save(obj, opened_zipfile, pickle_module, pickle_protocol)
File "C:\Users\strin\Desktop\Applio-RVC-Fork\Applio-RVC-Fork\runtime\lib\site-packages\torch\serialization.py", line 668, in _save
zip_file.write_record(name, storage.data_ptr(), num_bytes)
RuntimeError: [enforce fail at C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\caffe2\serialize\inline_container.cc:476] . PytorchStreamWriter failed writing file data/2203: file write failed
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "multiprocessing\process.py", line 315, in _bootstrap
File "multiprocessing\process.py", line 108, in run
File "C:\Users\strin\Desktop\Applio-RVC-Fork\Applio-RVC-Fork\lib\infer\modules\train\train.py", line 327, in run
train_and_evaluate(
File "C:\Users\strin\Desktop\Applio-RVC-Fork\Applio-RVC-Fork\lib\infer\modules\train\train.py", line 640, in train_and_evaluate
utils.save_checkpoint(
File "C:\Users\strin\Desktop\Applio-RVC-Fork\Applio-RVC-Fork\lib\infer\infer_libs\train\utils.py", line 153, in save_checkpoint
torch.save(
File "C:\Users\strin\Desktop\Applio-RVC-Fork\Applio-RVC-Fork\runtime\lib\site-packages\torch\serialization.py", line 442, in save
return
File "C:\Users\strin\Desktop\Applio-RVC-Fork\Applio-RVC-Fork\runtime\lib\site-packages\torch\serialization.py", line 291, in exit
self.file_like.write_end_of_file()
RuntimeError: [enforce fail at C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\caffe2\serialize\inline_container.cc:337] . unexpected pos 255835072 vs 255834960
Ayo? @spare saffron level 1 !!! 
I have no clue what this means but Applio has worked for training models up until now.
How can I use ai on a Android?
I don't think you can now
Oh why nott
[Voice Changer] generate new embedder. (no embedder)
[Voice Changer] Loading index...
Traceback (most recent call last):
File "voice_changer\VoiceChanger.py", line 301, in loadModel
File "voice_changer\RVC\RVC.py", line 84, in loadModel
File "voice_changer\RVC\RVC.py", line 153, in prepareModel
File "voice_changer\RVC\pipeline\PipelineGenerator.py", line 54, in createPipeline
UnboundLocalError: local variable 'inferencer' referenced before assignment
[Voice Changer] Model Load Error! Check your model is valid. local variable 'inferencer' referenced before assignment
help
how do i open the program i already have the files installed
Which one
Go-web.bat
it do not work
Ayo? @errant spindle level 2 !!! 
Seems like it couldn't load a model
when i click run i go thru the firewall thing and it tells me to press key
and when i do it just close itself
Is go-web.bat inside the folder?
yes
Have you installed requirements?
what are they?
Like, runtime folder
You probably haven't
There should be a tutorial on git on how to install requirements
Or you can just download it from huggingface
If you download it from huggingface it already has all the requirements and you don't have to install them manually
it do the same things
when i try to run batch file it says press key and when i do it closes
Did you extract it into your disk C?
OOOOH
You were just launching it from archive?
idk how it works i just want to shitpost
Well you have to learn how it works to use it, like any other program
No idea why that error happens
damn.
Hi guys can i make ai cover in my phone lol
Probably no
Thanks btw
mhhh i saw some people doing that
Do rvc inference spaces work?
If yes then it's possible
dunno
ilaria rvc its having some troubles i heard
but maybe others work
Simpl how long u been an Helper?
Around a month
Then I was a jun mod for 2 days
And then Ila promoted me xd
Because I found many racist/nazi profiles with blackcat
i see
I hope they'll promote blackcat to a mod soon too, he worked way more in last 3 months than I did
illaria not working
yuh
my voice changer native client isn't opening
this number keep rising
last time it reach over 1000
RVC Guides (How to Make AI Cover)
Translation by country
I forgot to make index file while running on colab and the saves are all gone, except for .pth
is there a way to make index file from existing model?
yea, just use the same settings (training variables on rvc disconnected), load up all the resuming steps (on rvc disconnected), then just train index
Which version of voice-changer is that ? Also which CPU ?
We're trying to figure this one out, .16 introduced the issue, .16a supposedly fixed it
cpu i5 3470
version 1.5.3.16a
Anyone pls share Google colab
that one is not gonna work
Wack, try .15
do you have a link for it?
Do you have an AMD or Nvidia GPU ?
gtx 1060 3g
Nvidia
thx
hi
Trying to run this and getting the same error
https://github.com/Mangio621/Mangio-RVC-Fork/issues/135
where do I download the app
Ayo? @floral vale level 1 !!! 
yea why not
ok
There is no download link
there is
where
oh it called RVC
I downloaded the Original RVC, by the RVC-Project team and I extract it but there are so many files what one do I click
go-web.bat
yes
where do I setup my mic?
no you just launch it
mic?
no it's for training
I want to use voice like minecraft villager and everyone hear me
why didn't you tell me that first 💀
download the other program called w-okada voice changer, i'll give you the link just tell me what gpu and cpu do you have
wdym gpu cpu?
Ayo? @floral vale level 2 !!! 
your pc specs
Processor: 12th Gen Intel(R) Core(TM) i5-12400F 2.50 GHz
Grapichs Card: NVIDIA GeForce RTX 3060
Memory (RAM): 16.0 GB
System Type: 64-bit
is thats all
@modern oxide
ok I take 5 minutes to download 3 GB file so Wait
Ok I downloaded and extract what do I open now?
there is an exe file, you just open it and wait till it downloads everything that it needs
I got so much files
there is start_http.bat and start_https.bat
what I click to start
d
there is too many links on #1159949278270193734 which one do I need to download the voice changer? Also is the voice changer free?
why
the bat scripts are there for a reason
the mmvcserversio executable is just a python interpreter for the main file
uhhhhhhhh
you won't get the flags without running it through the bat scripts
dunno i installed it like that and it works completely fine
do I close this now it almost done?
do not close it
ok
probably some hardcoded shit then
wouldn't be surprised either
no one?
Ayo? @dusk harbor level 1 !!! 
#🔍│help-w-okada pinned messages
yeah the channels are confusing x)
thank!
@sand iris @modern oxide what I do it does not work I don't hear my self
pinned message doesn't say it but, is it completely free or are some things behind a paywall?
It's free
gotcha, thanks!
The code is even available
you choose your audio devices in input and output
smoke?
Ayo? @digital jay level 1 !!! 
twork
is there is good setttings or what
used to seeing so many voice changers with paywalls, cant trust it anymore lol. Thanks again
there is a guide in pinned messages in #🔍│help-w-okada
?
where does that mention anything about my issue
anyway i stopped the training cell and saved the model
seemed to go succesfully
gonna try again, hopefully it didnt break
uhhh does this look bad
smoothing at 0.987
i think it might still be going
no lol
i stopped it yesterday
at epoch 175
uh yeah maybe
d/total and mel looks fine
and i think g is also fine
cuz
if i zoom in
it doesnt actually go up by a lot
ill wait until 200 epoch
oh and also any idea about this
does this mean itll disconnect (but not delete) runtime once the task is finished?
because when i stopped the task i just reconnected and the files from the runtime was still there
and it seems to have saved the model correctly
uhm
179 epoch
d/total is going down rapidly
mel and kl also
i guess its fine
You need to select your input and output
I did but now I only hear myself others won't hear me changed they will hear normal
Ayo? @floral vale level 3 !!! 
@modern oxide can you help me
You need to download a virtual audio cable
what is that
Basically a driver for transferring audio
You set okadas output as the cable
And the app you want to use as the cable
like obs?
wdym
It gets audio from an output and turns it into a input
It’s needed when you want to use the voice changer on something like discord
but how can I do it here
btw
I installed a villager sound but it does not sound like its what is wrong
Output should be the virtual cable I told you to download
download what
Input on discord should be the virtual audio cable
Virtual audio cable
i think its overtraining
what settings did u put?
40k sample rate. 450 epochs
the rest i left as default
dataset is an hour long, consists of 6 .wav
thats the problem
this is what epoch 198 is looking like:
1h is wayy to much
yh u dont need 1h dataset for good models
even 5 minutes r good enough
what if i stop right now
would it be fine
yh that doesnt matter
if u wanna work with big dataset maybe u should try 15/max 20 min datasets
i just want a model that sounds realistic
like i said before u can get high quality models even with just 5 minutes dataset
okay so
lets say i did
10 minutes
how long would training take
compared to an hour
once did 10 minutes 250 or 300 epochs and it took like 2 hrs
ohhh thats what u meant
i think u need to retrain
with the new dataset
://
the screenshots i took were from 175+ epoch
i have the 175 epoch model saved in drive
which was fine
in tensorboard at least
havent actually tried them yet
alright ill try it in like
rvc
rn
btw i have a ton of stuff now
in drive
u using rvc disconnected??
what files do i need
uh yeah for training
.pth and .index (the added one)
no just the one with the name of ur character
/the name of ur dataset
rvc disconnected has 4hrs runtime
what does that mean
i dunno if you could have done it
with 1hrs and 450 epochs
the model that u were training
what does "has 4 hours runtime" mean
is there like a limit on disconnected or something
that u can train just for 4 hours
for free users of google colab
u can run cells for just 4 hours
then it disconnect u
what happens after 4 hours?
does it like not work again on ur google account
and you have to make a new one
or change
it disconnect ur runtime and recharges after 24 hours
oh okay then
Ayo? @brittle wing level 6 !!! 
but on that colab should be some resumes cells
i kbow i was using them
thanku lol
im just slightly confused cuz i havent touched this stuff in a while
otherwise youll need to retrain 
dw
omg ilaria rvc
Looks alright
dunno if it works
ilaria said it does
so
ok so
model is on huggingface yay
now
let me
test
yh i wasnt sure cuz yesterday few things happened
uhhhh
wat
why isnt it working im confused
help im lost again 😭
what the fuck
sigh
im at the verge of giving up 😭
why is this so hard
whats ur model called??
did u refresh??
swagrvcmode
liike
bruh
why isnt it working
i refresh and my model doesnt appear
logs say it downloaded the thing
try to duplicate the space
im gonna send u the link fy
a
uhm
how am i supposed to do it ;-;
i paste in the link, i press the button
and then i go back to check, isnt there
yh but i meant on hf
yh
i was abt to write it
.pth and .index in a folder> zip the folder> ur huggin face> + model> files and version> upload files> upload ur zip> commit to change> and then copy the download link
a
sighhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhh
fuck it whatever
this whole ai stuff is taking more time than expected 😭
i wish the guides were clearer on this...
a lot of things arent mentioned
maybe i should do one for this type of things
poop
youre not the only one

if my model doesnt come out good imma be pissed LMAO
good luck soldier

Thank you!
On Applio, when training, what should I put in the section "Provide the GPU indexes." should I just leave it at 0?
Oh, I see. I tend to look over things like that. It says the GPU I have is 0.
"0 NVIDIA GeForce RTX 3060"
Put 0 then
Yeah, I did. Thanks!
Also, is there some sort of documentation on the settings I should use for my GPU? I'm just following the Training RVC V2 models guide made for Collab.
RVC Guides (How to Make AI Cover)
Translation by country
anybody knows what the issue is here?
Ayo? @uncut field level 2 !!! 
I've reinstalled Applio three times now and everytime it gets to Epoch 10 and tries to save at the checkpoint it gives me this error. Someone please help.
INFO:barnmetro:Saving model and optimizer state at epoch 10 to ./logs\barnmetro\G_2333333.pth
Process Process-1:
Traceback (most recent call last):
File "C:\Users\strin\Desktop\Applio-RVC-Fork\runtime\lib\site-packages\torch\serialization.py", line 441, in save
_save(obj, opened_zipfile, pickle_module, pickle_protocol)
File "C:\Users\strin\Desktop\Applio-RVC-Fork\runtime\lib\site-packages\torch\serialization.py", line 668, in _save
zip_file.write_record(name, storage.data_ptr(), num_bytes)
RuntimeError: [enforce fail at C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\caffe2\serialize\inline_container.cc:476] . PytorchStreamWriter failed writing file data/2184: file write failed
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "multiprocessing\process.py", line 315, in _bootstrap
File "multiprocessing\process.py", line 108, in run
File "C:\Users\strin\Desktop\Applio-RVC-Fork\lib\infer\modules\train\train.py", line 359, in run
train_and_evaluate(
File "C:\Users\strin\Desktop\Applio-RVC-Fork\lib\infer\modules\train\train.py", line 656, in train_and_evaluate
utils.save_checkpoint(
File "C:\Users\strin\Desktop\Applio-RVC-Fork\lib\infer\infer_libs\train\utils.py", line 153, in save_checkpoint
torch.save(
File "C:\Users\strin\Desktop\Applio-RVC-Fork\runtime\lib\site-packages\torch\serialization.py", line 442, in save
return
File "C:\Users\strin\Desktop\Applio-RVC-Fork\runtime\lib\site-packages\torch\serialization.py", line 291, in exit
self.file_like.write_end_of_file()
RuntimeError: [enforce fail at C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\caffe2\serialize\inline_container.cc:337] . unexpected pos 249166784 vs 249166676
so what to do now?
did you start the training?
then just wait till it finishes
yeah
how do i know if its finished and where is gonna be my model saved?
if you're using disconnected you'll have to press the export cell, if you're using easy colab you'll find your model in your drive account
yeah its the easy colab
then just wait till it finishes, everything will automatically save to your drive 
nice 
there gonna be an index file, the model itself will be in project-main - assets - weights
how long can i expect for it to train a 50 epoch model?
i set the save frequency to 50
like a couple minutes probably
i know. it should be like 400-500?
ok. just gonna wait
yeah somewhat around that
whats the easiest way to train a voice model without installation on a pc?
yeah collab
alr
Ayo? @winged fulcrum level 2 !!! 
-colab
- AICoverGen-NoWebUI, by Ardha Google Colab
- RVC Disconnected, Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- 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
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.
btw nothing appeared in the folder until now
D seems fine
I'd tell them to check KL
And Mel
i need a good training notebook
Ayo? @obtuse glen level 1 !!! 
shut the fuck up
_ _
same
always the inanimate cartoon objects ppl fans with the inexplicable rage/j
RVC Disconnected is the best one
send in dms
it's in #1159949278270193734 too
hi I'm new here, can someone help me to make my own models ?
wheres the chekcpoint files?
ok
#1159513888199540817 can help
@proper shalethx
G and D
wait they have the ckpt in them?
they are the ckpt
its saying it cant find a valid .pth file
Ayo? @obtuse glen level 2 !!! 
OMG IT FUCKING WORKS
ahhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhh
those are the d/g files, not the weights pths
use the amen break e90 s810 one
ok
D/G are training only
Hello, I am not very informed about the RVC, in fact I do not know what version I have, what I do know is that it is going very badly in terms of ms everything sounds very robotic, I do not know if the version of the program you install is old or idk, I have rtx 4070 and hyperX quadcast.
help:( srry if I didn't explain, my English is not good.
ma
@brittle wing how did the model turn out??
check here #1159513888199540817 (pinned one reccomended)
I just installed RVC_GUI, I run the .bat file and the cmd prompt opens up with "Running with the runtime Python, please wait..." and nothing happens. How do I fix it?
What do you mean by "(pinned one reccomended)"?
😦
oh thats not pinned nomore sorry hah
hello guys, i need a model for my rihanna-diamonds ai cover.But whenever i try it with different models,it stays bad.Like do u guys have any recommendations for high note songs?
whenever i try to reach high notes,it's getting interrupted
Ayo? @rain coyote level 1 !!! 
Illaria RVC has quite literallynever worked for me
i dont know why it just never id
it takes forever to process
and if i refresh anything
i will get
nonstop errors
its having problems i think
is there any other ai cover service i can use
cuz i have tried illaria rvc on multiple occasions
if u didnt try to duplicate the space
https://huggingface.co/spaces/TheStinger/Ilaria_RVC?duplicate=true heres the link for duplication btw
I want to delete all of this how
Ohhhh you are using w-okada
I thought you were using RVC
whats better?
Try clicking that grey Edit button
This only pops up ik
RVC is for converting audio files with a model. W-Okada is for real-time voice conversion with a microphone
Ah I don't know then
Try asking on #🔍│help-w-okada
Congrats!
xD ty
Works! ty for ur time tho!@
HOSTING INDUCTIVEGRUB HELP DESK
use added
what do you mean
just use the pth and the index
there's no pth tho, it's just those 2 files
oh

i mean my gf is the one using the program but she's not in here, and we're worried about that file before anything else
@mighty parcel do you maybe know what it is?
Sorry you are not allowed to have grillfriends in the server
amazing behaviour
You are going to get banned
what
No sex life allowed here
was i not supposed to ping one of the mods for help, i didn't mean to break any rules
tensorboard log file
na its fine
its harmless, and whoever left it in is just dumb
no need to fear over it, it's just a log file leftover, and is what is read when you want to see the graphs for the training stats
thank you!!
example of what a logs folder looks like from a trained model
people are just goofy and upload files they dont need to
these is how my folder looks like
I just can't find any index file
you have to click the train index button, it is not ran when clicking train model
wait what
Ayo? @meager dome level 1 !!! 
in the GUI?
need some help
What is it?
no i was askinh you jokingly
ok I found where, but how do I upload the trained model files?
I trained it a month ago and forgot to get the index file
you'd need the original settings n stuff
hey uh this is probably a stupid question but how do you train models-
mainly just name and rvc version and sample rate
-rvc
Hey, @proper sorrel!
👇 Here are some useful resources to help you learn how to make ai covers
Translation by country
You have plenty of guides on #1159513888199540817 too
It's not a stupid question - no question is stupid! Check #1159513888199540817!
It's ok - first time is always a lil bit complicated haha
Well i used to do it on the webui!
How many epoch for million second long song
but yknow-
google killed it so hard
do I upload the model zip here or something?
I don't remember a thing from the last time I trained it
what?
like my question is where do I put the trained model's files before making the settings for getting the index file
oh ur using...
yeahhh like i get why and all but im not tryna take anyones job im just tryna make a funny
theyre already there
if this works to train index then ill be surprised
Welp, sadly nothing is free in this world
look
Are there any suggestions on what i should use to train a model?
Ayo? @proper sorrel level 1 !!! 
oh u should've inserted that in a previous step
like extracted the zip
RVC Disconnected in #1159949278270193734
that one actually works
if you've already done this step the path should be /content/dataset/
I didn't do that step so I don't see it
yeah you should've
can I do it now?
Ayo? @meager dome level 2 !!! 
like the model's trained, I just don't have the index file
I trained the model one month ago
yeah you can do it
make sure everythings correct
just in case
and it should work
ok then how do I do it
I don't have everything correctly cuz it trains the index in 1.5 seconds
oookay that definitely isnt normal
yeah
zip yeah
that one doesnt work either. plus its like 50 mb? i dont think it should be that small
look, this is the zip, it has only wam files
bruh
now I put the path here
but the train index doesn't work
the train model does
it's training it again
it doesn't
"baza de date"?
yeah it s like data base in romanian
that's how I named it
oooh no wait
yeah?
you need to extract it first
using the extract dataset stwp
stop the webui for a while and do that
- make the 'dataset' folder in Google drive and move your zip there
yo anyone help me download the voice changer lol
ok, bear with me for one second
so I made the folder and I'll move the zip here
ok, I uploaded it
I asume I have to run this cell
Ayo? @meager dome level 3 !!! 
Yup
ok, now?
I still get some error
maybe I should rerun the cell with gradio
that's what I did
now u just use this as ur path:
/content/dataset
asks for the folder and not the file, btw
that
or maybe it isn t an error
is not an error
it's ok it's ok
is this an error?
i think it is cause it still won't train the index
did you check for the model to have pitch guidance?
is it that important?
tick that if you haven't
literally wont train model otherwise
where should I tick
its that broken 😭
"Whether the model has pitch guidance"
it was ticked
oh then probably the wavs u have are screwing up
you're right
maybe that's the problem
wait I just saw something
this is the right training folder path
cause look
or nevermind
don't mind it
nooope thats actually the wrong one
i found it out now
it should be /content/dataset only
yeah I put it like that
I unticked the
and now I am training the model all over again
thats just gonna ruin your model
if I stop the training and click on train feature index it still doesn't work
this is so hard
RVC Guides (How to Make AI Cover)
Translation by country
Yo @cobalt oyster
quick question are these settings good for covers with 300 epochs rmvpe models
With clean audios n stuff
RVC GUI keeps giving me this error when im trying to convert things how do I fix it?
looks like this on the GUI itself
whats the ideal number of epochs to use for a singular wav file?
Ayo? @hexed dew level 1 !!! 
well how long is ur vid? the size of that one file is also important
around 2 mins but the sample has almost all phoentic sounds
Probably go for somewhere between 250-300
I dont want to overfit the model
Ah okay it was set to 500 at default am I just able to use the checkpoints at 250?
theres is any way to make voice with AI with mobile?
everything works the same itll just be less epochs to load
gotchu thanks, can i run the index training while still running the training codeblock? im at around 120 epochs and I want to just test the model on rvc now.
idk ive never tried interrupting the training to do that
Like train a voice?
Use google colab, I recommend the RVC Disconnected colab
Whats the google collab trainin link?
-colab RVC Disconnected
Suggestions for @lyric agate
- AICoverGen-NoWebUI, by Ardha Google Colab
- RVC Disconnected, Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
- 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
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.
Yo thanks bro
Hi I trained a model but when I download it from the colab link and load it into rvc gui I get this:
so i also get this error frequently
i have no idea what causes it, but if u go back tomorrow it usually fixes itself
i dont think thats what causes it tho bc I had this issue on a model that was working fine just the other day
When I try load the model in it says "Please select a model and input audio file"
I think there might be an issue with the actual zip file itself
hmm i just tried my different models, all of which have worked at least once, some i have made at least 5 covers with and none of them r working when im having this error
so maybe we r experiencing a different error
For a model youve trained can I see the pathing?
mine seems to be related to available space, but i dont know how to clear the space necessary to continue making covers
Yeah Im unsure how to delete models on RVC gui either
how do i do that?
show u the pathing
just send me a screenshot of the folder path and contents
Maybe because the zip file has a folder in itself
Ayo? @hexed dew level 2 !!! 
Im not sure
Ayo? @cerulean dew level 4 !!! 
idk i literally got this model to work yesterday
and there were no issues
made this the other day
but now rvc gui is just being stubborn
and wont let me do literally anything
how did you create the model? using rvc disconeected or
yes
how many epochs did you use
300
yeah it seems to be very inconsistent
but I cant even load my model in
i think i might have fixed it?
i still dont know exactly what the problem is but i accidentally have a ton of different version of the rvc folder downloaded and i think only one of them works
idk why thats the case
torch.cuda out of memory
thats what the code says
idk how to fix that
thats probably a gpu problem
how do i fix that tho
i keep seeing that online but i have no idea how im meant to fix that
try to run on cpu instead of gpu
how?
on rvc gui
