dmet/ai-voice-cloning
1
0
Fork 0
forked from mrq/ai-voice-cloning
Code Pull Requests Activity

download dvae.pth for the people who managed to somehow put the web UI into a state where it never initializes TTS at all somehow

Browse Source
This commit is contained in:
mrq 2023-03-07 02:47:10 +00:00
parent 0f0b394445
commit 0f31c34120
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/utils.py
View File

@ -985,6 +985,9 @@ def run_training(config_path, verbose=False, gpus=1, keep_x_past_datasets=0, pro
global training_state
if training_state and training_state.process:
return "Training already in progress"
# ensure we have the dvae.pth
get_model_path('dvae.pth')
# I don't know if this is still necessary, as it was bitching at me for not doing this, despite it being in a separate process
torch.multiprocessing.freeze_support()