mrq/ai-voice-cloning
31
74
Fork 43
Code Issues 222 Pull Requests 5 Packages Projects Releases Wiki Activity

Colab: CUDA out of memory error before any voice is produced and when "Use CUDA for Voice Fixer" is turned off #477

New Issue
Open
opened 2024-02-22 19:46:05 +00:00 by sheriffbrackett · 0 comments
sheriffbrackett commented 2024-02-22 19:46:05 +00:00
Copy Link

see title

When using the provided colab notebook, before I have processed any voice, I get this error:

CUDA out of memory. Tried to allocate 17.31 GiB. GPU 0 has a total capacty of 14.75 GiB of which 9.92 GiB is free. Process 34983 has 4.83 GiB memory in use. Of the allocated memory 4.48 GiB is allocated by PyTorch, and 215.02 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

It has been suggested in another issue that unchecking the "Use CUDA for Voice Fixer" option is the solution. However, I have tried this and still I receive the error.

Any help would be appreciated.

see title When using the provided colab notebook, before I have processed any voice, I get this error: CUDA out of memory. Tried to allocate 17.31 GiB. GPU 0 has a total capacty of 14.75 GiB of which 9.92 GiB is free. Process 34983 has 4.83 GiB memory in use. Of the allocated memory 4.48 GiB is allocated by PyTorch, and 215.02 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 It has been suggested in another issue that unchecking the "Use CUDA for Voice Fixer" option is the solution. However, I have tried this and still I receive the error. Any help would be appreciated.
fgevfe.png
687 KiB
gg.png
131 KiB
fgevfe.png gg.png
sheriffbrackett changed title from CUDA out of memory error before any voice is produced and when "Use CUDA for Voice Fixer" is turned off on Colab to Colab: CUDA out of memory error before any voice is produced and when "Use CUDA for Voice Fixer" is turned off 2024-02-22 19:46:44 +00:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels   
bug

Something is not working

  
duplicate

This issue or pull request already exists

  
enhancement

New feature

  
help wanted

Need some help

  
insufficient info

Need more information

  
invalid

Something is wrong

  
news

To make up for a lack of a way to provide any news-like

  
not a bug

For non-bug things

  
question

More information is needed

  
wontfix

This won't be fixed

No Label
bug
duplicate
enhancement
help wanted
insufficient info
invalid
news
not a bug
question
wontfix
Milestone
Clear milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
No Assignees
1 Participants
Notifications
Due Date
The due date is invalid or out of range. Please use the format 'yyyy-mm-dd'.

No due date set.

Dependencies

No dependencies set.

Reference: mrq/ai-voice-cloning#477
No description provided.
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?