return torch.batch_norm(
torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 232.00 MiB. GPU 0 has a total capacty of 4.00 GiB of which 0 bytes is free. Of the allocated memory 2.42 GiB is allocated by PyTorch, and 859.48 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting max_split_size_mb to avoid fragmentation. See documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONF
#APPLIO | Does anyone know why this error occurs? It used to work, now it won't let me do anything.
1 messages · Page 1 of 1 (latest)
APPLIO | Does anyone know why this error occurs? It used to work, now it won't let me do anything.
batch size too big for ur GPU VRAM
you should try training at b_s 2 which will take long oor use colab
I have a i5, 16 gb de ram and a Nvdia 3050 Ti
What I don't understand is why I can't use it if it was working fine, with the same model, same songs, nothing new except that now it doesn't work.... I will see the batch size but it seemed strange to me that it worked until I restarted the pc and now it does not work.
a 3060 Ti does not have only 4 gigs of VRAM
afaik it has 8
That's exactly why I wonder why it worked in the morning and now it doesn't.
do you have more than one gpu? hm
that explains it then
I just don't understand why it worked and now it doesn't...
u should use Google Colab then, it is most likely better for training than the 3050
Do you know of any available and good colab?
RVC Disconnected is a good one
-rvc
Documentation
Credits: AI HUB FRANCE
✨ More guides
Full AI Voice Model Training Guide (Local)
Link: YouTube
Credits: Christopher Villanueva
Model training with Mainline RVC
Link: Rentry
credits: Raven (ravencutie21)
AICoverGen Colab Guide
Link: Google Docs
Credits: Eddy (Spanish Helper)
Create a model with RVC disconnected (colab)
Link: Google Docs
Credits: Angetyde
How To Make an AI Cover With Ilaria RVC
Link: Rentry
Credits: 👽 Julia (ailen2091)
☁️ Google Colabs
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- easyGUI, by rejects Google Colab
🤗 Hugginface Spaces
- Ilaria RVC, by thestingerx Hugginface Spaces
- RVC-HFv2, by r3gm Huggingface Spaces
- AICoverGen, by r3gm Huggingface Spaces
- Advanced RVC Inference, by r3gm Huggingface Spaces
- RVC v2 Huggingface version, by Clebersla Huggingface Spaces
More commands: -audio, -local, -overtrain, -realtime, -rvc, -help
Link
Thanks!!
Even online they are causing me errors wtf....
Ayo? @scarlet nimbus level 2 !!! 
you can force cpu
naaah u cant train on cpu lol
specific pc info? and if you can an image of you setings in train
for train in appilo i thnik yu need the use the same bach of vram or lower
4 gb right ?
yep
Lenovo legion 5
i5 (11) 16 gb ram, 3050 nvidia
do you use more then 4bach?
Truth be told, I have experimented with machine learning not on this machine but now testing here, I have only used Applio and tried to simply do a voice morph, I am not trying to go more complex than that.