RVC2 Disconnected

[deep wharf]

Is there another RVC2 Disconnected alternative avaliable, The colab say reaches end of life

[zinc swan]

Yeah rvc disconnected is forever discontinued and won't ever be updated again

First of all, did you check your PC GPU to see if it's good enough for local training?

Because google colab is a cloud (remote good PC) service for people with bad pcs

[deep wharf]

I only have Intel CPU, I don't have good GPU

[zinc swan]

alright then

Train (make) RVC Models on cloud:

1. Prepare the Dataset
2. Setup RVC:
   Choose a cloud way to use RVC,

• Google Colabs (4 hours of daily gpu for free, not much hours, but easy to use):
  • Applio (ui)
  • Mainline (UI)
• Kaggles (a bit harder to use and needs phone number but gives 30 hours weekly of better gpus):
  • Mainline (UI)
  • Applio by Vidal (UI)
  • Applio by Shirou (UI, no guide as of right now)
• Lightning.ai (Kinda hard, needs login, no issue with web uis or anything, but only free 15 credits monthly):
  • Applio (UI)
  • Mainline (UI, No guide as of right now)

3. Be sure to know about the tensorboard

Google Colab = Easier but risk of getting disconnected
Kaggle = Harder but way more gpu time
If you are looking for the easiest way and for free, is using https://weights.gg which ofc uses RVC

RVC Inference (use models) on pre-recorded audio on Cloud

You can use either:

• Weights.gg: Easiest Possible Ever Automatic
• Ilaria RVC Zero: Fastest free on cloud
• Applio (ui)

[humble citrus]

there is a guide for Vidals kaggle notebook btw https://docs.aihub.gg/rvc/cloud/applio-kaggle/

[zinc swan]

Ohh I didn't check that, great, thanks for letting me know!!

will edit it

[humble citrus]

yw

[humble citrus]

also the tensorboard link was updated and is https://docs.aihub.gg/rvc/resources/training/#tensorboard now instead of the old one you had which was: https://docs.ai-hub.wtf/rvc/resources/epochs-tensorboard/

[zinc swan]

Updated!

[cedar iron]

How does mine still work?

[olive copper]

it's like giving more fresh air to the AM4 platform while the DDR4 kit production has stopped

[cedar iron]

Ikr

[zinc swan]

it's at the end of life, it couild even work now but would never get fixed if it's broken nor updates that make it better unlike applio and mainline, just use one of those bro that colab is literally unmaintained

[cedar iron]

If I use Applio No UI, it fills up my google drive storage instantly when I train

I’ll try the mainline later

[zinc swan]

It's better u ask vidal

Also let's stop talking here, if you need help make your own posts