conn error
i have tried again on the colab. this the error output
model.bin: 91% 2.82G/3.09G [01:06<00:06, 41.7MB/s]
model.bin: 92% 2.83G/3.09G [01:06<00:06, 41.9MB/s]
model.bin: 92% 2.84G/3.09G [01:06<00:05, 42.9MB/s]
model.bin: 92% 2.85G/3.09G [01:07<00:05, 41.6MB/s]
model.bin: 93% 2.86G/3.09G [01:07<00:05, 41.9MB/s]
model.bin: 93% 2.87G/3.09G [01:07<00:05, 42.1MB/s]
model.bin: 93% 2.88G/3.09G [01:07<00:04, 42.1MB/s]
model.bin: 94% 2.89G/3.09G [01:08<00:04, 41.6MB/s]
model.bin: 94% 2.90G/3.09G [01:08<00:04, 42.0MB/s]
model.bin: 94% 2.92G/3.09G [01:08<00:04, 42.4MB/s]
model.bin: 95% 2.93G/3.09G [01:08<00:03, 42.5MB/s]
model.bin: 95% 2.94G/3.09G [01:09<00:03, 41.3MB/s]
model.bin: 95% 2.95G/3.09G [01:09<00:03, 41.8MB/s]
model.bin: 96% 2.96G/3.09G [01:09<00:03, 35.1MB/s]
model.bin: 96% 2.98G/3.09G [01:10<00:02, 43.6MB/s]
model.bin: 97% 2.99G/3.09G [01:10<00:02, 43.2MB/s]
model.bin: 97% 3.00G/3.09G [01:10<00:02, 43.1MB/s]
model.bin: 97% 3.01G/3.09G [01:10<00:01, 42.8MB/s]
model.bin: 98% 3.02G/3.09G [01:11<00:01, 42.2MB/s]
model.bin: 98% 3.03G/3.09G [01:11<00:01, 42.3MB/s]
model.bin: 99% 3.04G/3.09G [01:11<00:01, 42.5MB/s]
model.bin: 99% 3.05G/3.09G [01:11<00:00, 42.4MB/s]
model.bin: 99% 3.06G/3.09G [01:12<00:00, 41.8MB/s]
model.bin: 100% 3.07G/3.09G [01:12<00:00, 41.9MB/s]
model.bin: 100% 3.09G/3.09G [01:12<00:00, 42.5MB/s]
Existing language matches target language
Unable to load any of {libcudnn_ops.so.9.1.0, libcudnn_ops.so.9.1, libcudnn_ops.so.9, libcudnn_ops.so}
Invalid handle. Cannot load symbol cudnnCreateTensorDescriptor
have you faced something like this? i will try docker but i am afraid that i will face the same problem? will i ?
You probably won’t get that error on the docker
That’s a cuDNN version error for google colab
They constantly update colab and break shit
The docker is like a mini virtual machine, everything is already set up and ready to go in a virtual env
Nothing ever changes about it cause it’s like a snapshot of a virtual machine
But first how much Vram does your GPU have
Always bet on docker lol
i have gtx 1650 and 4 gb of vram
This will not run on your computer
why is that and what shoul i do instead bro?
uhhhhh I know I got a solution somewhere under all these papers....
my vram is not enogh to run it or what? i didnt understand why it wont run on my pc.
here
This is the huggingface space that the docker is based on
your gona have to rent clone it and rent out a gpu from huggingface, its like 40 cents an hour and it usually only takes me 30 minutes or so to train a model.
https://huggingface.co/spaces/drewThomasson/xtts-finetune-webui-gpu
duplicate that space and select a gpu to run it on all of the options should do, then when your done just pause the space so they stop charging you for using their gpu
my vram is not enogh to run it or what? i didnt understand why it wont run on my pc.
you do not have enough Vram to run the fine tuning...
you might be able to with 8 gb vram
but 4gb?
no you need more vram
fine-tuning a model takes like double or quadruple the vram it takes to run normally,
so... yeah
it wont run or it will run very very slowly, which is it? and also this link you sent me says the authos had paused this space?
no it literally will not run
because I paused the space im not charging myself gpu money
you have to duplicate the space you cant use my space theres a button for it in the three buttons things
here ill test the Google Colab idk
I have tried to duplicate it but it gave error:
E: Unable to locate package libcudnn8
E: Unable to locate package libcudnn8-dev
--> ERROR: process "/bin/sh -c apt-get update && \txargs -r -a /tmp/packages.txt apt-get install -y && \tapt-get install -y curl && \tcurl -fsSL https://deb.nodesource.com/setup_20.x | bash - && \tapt-get install -y nodejs && \trm -rf /var/lib/apt/lists/* && apt-get clean" did not complete successfully: exit code: 123
great...
ok fixing the Google Colab I made for y'all cause... Google Colab is amazing
are you fixing colab rn? if it so, when it will be ready bro?
idk I have no idea what im doing I built the colab for that so long ago
i feel like my brain will explode right now. so frustrated. do u have any other recommendations ?
I mean I told you I could just do it for you and send you the fine-tuned file in the mean time lol
I'm confused you said you didn't have the audio ready, then what are you trying to fine-tune it on right now?
i didnt record my own voice yet. but i downloaded some turkish voice datas from the internet and i was trying to fine tune them to see if its gonna work or not but i didnt even have a chance to try it. i dont have good enogugh environment right now to record a good quality voice.
fck me i think it set it for cpu. how do i undone it?
click settings
bro when i am done with the space how can i pause it? it always says running on t4 and i dont want to be charged extra for nothing? can u help pls?
Go into settings
Click pause
Or delete it
Which is also in settinfs
i cant see pause or delete here. Am i looking in the wrong place? btw i wanna ask u sth. before i select the t4 gpu. it asked me to verify my payment and it charged me 10 usd and it said it will be paid back to you once we verify the payment method. but i didnt get 10 usd back. do u know when will i get it or should i send them a mail or what?
You should eventually get your $10 back I did
I didn’t get any email about it but I no longer see the charge on my card for it
The pause button is in settings you have to click settings to go into settings
yup worked for me just duplicated and trained a model for myself
seen here the third version of death from puss and boots
https://huggingface.co/drewThomasson/death_from_puss_and_boots_xtts/tree/main/V3__6_epoches
what worked bro? i couldnt catch.
The space you duplicated