Software Engineering Courses (SECourses)•3y ago

hii,anyone knows why ozen its transcribing my uploaded voice for training in different language inst

hii,anyone knows why ozen its transcribing my uploaded voice for training in different language instead of the speaking language as how the whisper is doing it

OnlyOP•11/1/23, 12:59 AM

i have edited ozen.py and modified the default model to medium and also changed from cuda to cpu as i dont have a gpu at the moment.Thanks!

OnlyOP•11/1/23, 1:16 AM

Lightning automatically upgraded your loaded checkpoint from v1.5.4 to v2.1.0. To apply the upgrade to your files permanently, run

python -m pytorch_lightning.utilities.upgrade_checkpoint C:\Users\Hp\.cache\torch\pyannote\models--pyannote--segmentation\snapshots\2ffce0501d0aecad81b43a06d538186e292d0070\pytorch_model.bin

python -m pytorch_lightning.utilities.upgrade_checkpoint C:\Users\Hp\.cache\torch\pyannote\models--pyannote--segmentation\snapshots\2ffce0501d0aecad81b43a06d538186e292d0070\pytorch_model.bin

Model was trained with pyannote.audio 0.0.1, yours is 3.0.1. Bad things might happen unless you revert pyannote.audio to 0.x.

OnlyOP•11/1/23, 1:16 AM

could be because of pyannote?

OOnly Lightning automatically upgraded your loaded checkpoint from v1.5.4 to v2.1.0. T...

Furkan Gözükara SECourses•11/1/23, 11:30 AM

i dont know this

OOnly hii,anyone knows why ozen its transcribing my uploaded voice for training in dif...

Furkan Gözükara SECourses•11/1/23, 11:30 AM

you can edit files to change language

Furkan Gözükara SECourses•11/1/23, 11:30 AM

accurate

FFurkan Gözükara SECourses you can edit files to change language

OnlyOP•11/1/23, 1:42 PM

hmm,i will try to find out,as i said i set the model to medium so its ok with multilingual audios...i thinked maybe the training is done in english somehow and thats why the audio was transcribed in english, what about the traing proccess its working only if i have gpu right?as i tryed to start the training and i receive error that i there is no gpu

Jehovah•11/1/23, 2:47 PM

Hello.

Startup problem - Auto Windows Installer For SDXL Background Replacement for Product Images

A matching Triton is not available, some optimizations will not be enabled.
Error caught was: No module named 'triton'
Initializing captioner...
Initializing upscaler...
Initializing segmenter...
Initializing depth estimator...
Initializing depth ControlNet...
Initializing autoencoder...
Initializing SDXL pipeline...
Loading pipeline components...: 100%|████████████████████████████████████████████████████| 7/7 [00:08<00:00, 1.26s/it]
Traceback (most recent call last):
File "D:\pimages\background-replacement\app.py", line 150, in <module>
num_inference_steps = gr.Slider(precision=0,minimum=1, maximum=300,value=30, default=30,step=1, label="Num Inference Steps")
File "D:\pimages\background-replacement\venv\lib\site-packages\gradio\component_meta.py", line 146, in wrapper
return fn(self, **kwargs)
TypeError: Slider.init() got an unexpected keyword argument 'precision'
To continue, press any key. . .

help me solve the problem
Thank you

Jehovah•11/1/23, 3:09 PM

JJehovah Hello.🤝 Startup problem - Auto Windows Installer For SDXL Background Replaceme...

Furkan Gözükara SECourses•11/1/23, 3:16 PM

hello

Furkan Gözükara SECourses•11/1/23, 3:16 PM

what is your python version

Furkan Gözükara SECourses•11/1/23, 3:17 PM

can you private message me the image you are trying your settings

Furkan Gözükara SECourses•11/1/23, 3:17 PM

i am gonna do a fresh install and test now

Furkan Gözükara SECourses•11/1/23, 3:18 PM

doing a fresh install

FFurkan Gözükara SECourses i am gonna do a fresh install and test now

Jehovah•11/1/23, 3:21 PM

JJehovah Click to see attachment

Furkan Gözükara SECourses•11/1/23, 3:21 PM

3.10.6 looking good

Furkan Gözükara SECourses•11/1/23, 3:21 PM

where did you install inside c drive?

Furkan Gözükara SECourses•11/1/23, 3:22 PM

ah i think the reason is

Furkan Gözükara SECourses•11/1/23, 3:22 PM

gradio version

Jehovah•11/1/23, 3:22 PM

drive D

Furkan Gözükara SECourses•11/1/23, 3:22 PM

yep

Furkan Gözükara SECourses•11/1/23, 3:22 PM

that must be gradio

Furkan Gözükara SECourses•11/1/23, 3:22 PM

going to fix noıw

FFurkan Gözükara SECourses going to fix noıw

Jehovah•11/1/23, 3:23 PM

Thanks!

Furkan Gözükara SECourses•11/1/23, 3:24 PM

i hate gradio

Furkan Gözükara SECourses•11/1/23, 3:24 PM

they break all existing apps

JJehovah Thanks!

Furkan Gözükara SECourses•11/1/23, 3:27 PM

fixed

Furkan Gözükara SECourses•11/1/23, 3:27 PM

you need to activate venv and do

Furkan Gözükara SECourses•11/1/23, 3:27 PM

pip install gradio==3.50.2

Furkan Gözükara SECourses•11/1/23, 3:27 PM

or git pull

Furkan Gözükara SECourses•11/1/23, 3:27 PM

and execute install again

FFurkan Gözükara SECourses you need to activate venv and do

Jehovah•11/1/23, 3:38 PM

Please, can you provide more details?
how to activate venv, in which bat write git pull
should I install pip install gradio==3.50.2
to a folder? background-replacement\venv\Lib\site-packages\gradio

JJehovah Please, can you provide more details? how to activate venv, in which bat write g...

Furkan Gözükara SECourses•11/1/23, 3:40 PM

this.bat114B

Furkan Gözükara SECourses•11/1/23, 3:40 PM

save this inside same folder and execute

Jehovah•11/1/23, 3:40 PM

Am I doing the right thing?

FFurkan Gözükara SECourses Click to see attachment

Jehovah•11/1/23, 3:41 PM

thanks

Kasparov Abi•11/1/23, 5:45 PM

guys does any of you have upscaler workflow for a ready video

KKasparov Abi guys does any of you have upscaler workflow for a ready video

Furkan Gözükara SECourses•11/1/23, 11:18 PM

you can simply extract every frame

Furkan Gözükara SECourses•11/1/23, 11:18 PM

then upscale

Furkan Gözükara SECourses•11/1/23, 11:18 PM

takes long time when not multithreaded

Brandon•11/2/23, 2:22 AM

Depending on my settings, I frequently see this kind of pattern in clothing, close up and far away, has anyone seen it before / know what it may be from?

Brandon•11/2/23, 2:25 AM

almost like a snakeskin pattern lol

BBrandon Depending on my settings, I frequently see this kind of pattern in clothing, clo...

Furkan Gözükara SECourses•11/2/23, 12:11 PM

yep

Furkan Gözükara SECourses•11/2/23, 12:11 PM

100% result of LoRA

Cruncho•11/6/23, 6:27 PM

Hi guys, I'm new here, I'm trying to make a swap-face video using the google colab option (because i'm not a lot into programing) and it doesn't work. It shows a lot of error messages that I would be glad to share with you.
Can you provide some help in this regard?

CCruncho Hi guys, I'm new here, I'm trying to make a swap-face video using the google col...

Furkan Gözükara SECourses•11/6/23, 8:21 PM

ignor all errors

Furkan Gözükara SECourses•11/6/23, 8:21 PM

i just tested yesterday evening

Furkan Gözükara SECourses•11/6/23, 8:21 PM

working great

Furkan Gözükara SECourses•11/6/23, 8:22 PM

retropigs•11/8/23, 12:48 AM

Hey, im trying to follow the kaggle tutorial, but when I run the final cell with the webui.shwebui.sh, it runs for a second, then errors with ERROR: Operation cancelled by userERROR: Operation cancelled by user, and then the whole notebook turns off, and I need to start again. Any advice?

hii,anyone knows why ozen its transcribing my uploaded voice for training in different language inst

Similar Threads