Відео

Phenomenal. subscribed

Todayy hummmmmm

Is it possible to install open-webui & ollama in another drive (like d drive)

Does it suports multi-speaker? I have a Piper voice that is multi-speaker and I'd like to retrain it for MeloTTS using cloud compute. This thing is a Frankenstein between VITS2 and some other archs, but I wonder if VITS2 has really improved upon VITS.

so funny hhah

Thanks for the vid. I'm getting stuck with these errors: torchaudio 0.13.0 requires torch==1.13.0, but you have torch 1.13.1+cu117 which is incompatible. torchtext 0.14.0 requires torch==1.13.0, but you have torch 1.13.1+cu117 which is incompatible. torchvision 0.14.0 requires torch==1.13.0, but you have torch 1.13.1+cu117 which is incompatible If a change the version I get this during training: 024-11-06 13:32:30.686677: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:485] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2024-11-06 13:32:30.708767: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:8454] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered Any help would be appreciated.

What do I do if cuda is not available(my says false)even do I downloaded it??

It would be nice if you could make a tutorial to use MaskGCT TTS locally on windows

Any luck with this on Windows?

mann, you are the best guide

I love it, Thanks for your video

Can you do the bailando 3d dance generator as soon as possible😊

Hey, thanks for this, I have a problem, I want to change the enviroment variable back to true as I want a login page but when I change it to true it just doesnt change, how to change it?

How do you install this on an airgapped computer? I believe I've downloaded all the files I need. I don't want to bother with any garbage like "pipinstall" and "bistros". I just want to copy and paste the files into my second computer and have it work. Have they succeeded in making such tasks impossible?

....you and your ducks :D

thank you so much, this tutorial was extremely clear and useful ! you won a sub !

\driving_audio_1.wav" --pretrained_clip_DINet_path=./asserts/clip_training_DINet_256mouth.pth DINet: DINet: (base) C:\Users\USER\OneDrive\Desktop\DINet> Message: Could not find a part of the path 'C:\Users\USER\OneDrive\Desktop\DINet\asserts\examples\test1'. Stack Trace: at System.IO.__Error.WinIOError(Int32 errorCode, String maybeFullPath) at System.IO.Directory.Delete(String fullPath, String userPath, Boolean recursive, Boolean checkHost) at System.IO.Directory.Delete(String path, Boolean recursive) at DINet_UI.Form1.<btnGenerate_Click>d__10.MoveNext()

Ditto for me, LOL

7:37 :D

make: *** No rule to make target 'run'. Stop. This is the only error left and i am pretty sure it will work.

This is actually awesome, no more having to create weird modelfiles, and then because the format i typed in is wrong ,it doesnt work properly

just stopped by to say LOL!

Not able to locate One-click installer. can you please help with that? Thanks in Advance

Traceback (most recent call last): File "inference.py", line 33, in <module> raise ('wrong video path : {}'.format(opt.source_video_path)) TypeError: exceptions must derive from BaseException

Hi! Thank you for the tutorial-it's been really helpful so far! I encountered an issue while following along. When I run the command python -m llava.serve.controller --host 0.0.0.0 --port 10000, I get the following error: OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized. OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g., by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround, you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. I'm not sure how to proceed to fix this. Could you please help me understand how to resolve this error? Thanks in advance!

is this your real voice?

oh maaaaaaaaaaan, i missed you voice ;))

Thanks for the video, very nice step by step. But having problems to run using CPU 😔

how i can change the language? please i can't understand how

Whats the pc requirement? Must i have an nvidea Gpu?

Will it work if I train in Applio, then use those in MeloTTS?

I click on run.bat and nothing happens. The program does not start. I did everything as in the video

can piper be trained without wsl?

is this cpu only?

how to do it locally. without any colab?

LVCD: Reference-based Lineart Video Colorization with Diffusion Models released their code, but I don't know how to use it... It seems to be something revolutionary. It would be cool if you took a look at this. You are always our salvation😅

is there a way to use it as local API?

how can i update it without uninstalling then reinstalling?

I followed these instructions, it was hard enough, and in the GUI I just get an Error message. 3h down the drain...

tell pls how to stress vowels in words?

Could you pls tell how to stress vowels in words?

Thank you so much!

A belated 'Thank You' from a NEW Subscriber !

NEW Subscriber BUT Long Time Piper User !

Sir there is only Pretrained ckpt file but no last ckpt file i can't find file?

i have 8gb graphics card is it ok. Gforce RTX 8 GB

excatly what software we need to install already to my pc

i am unable to get last ckpt in drive folder please metion it clearly can you please i have 20 wav file but it is my first time? Thank you

If I use this method, will it run on the CPU or GPU?

This is some great work. Thanks for sharing your progress through example. I was looking forward to using fine tuning to come up with some variations of the same voice and some kind of program to know when to switch or vary the outputs similar to real human speech. This yelling voice works amazing and I look forward to what else you come up with.