Retrieval-based-Voice-Conversion-WebUI
Retrieval-based-Voice-Conversion-WebUI copied to clipboard
cant find inferencing voice
i put all the settings and used one-click training and i got: "added_IVF985_Flat_nprobe_1_IbrahemHefny_v2.index All processes have been completed!" but i couldnt find the model from the "Inferencing voice" slider even though i found the voice model in the log file please help
Press the big Button on the Inference Tab called "Refresh Voice list and Index path" You should now be able to choose your Model on the Top Left, below "Inferencing voice:" Also make sure to select your Index File, from "Auto-detect index path and select from the dropdown:"
Press the big Button on the Inference Tab called "Refresh Voice list and Index path" You should now be able to choose your Model on the Top Left, below "Inferencing voice:" Also make sure to select your Index File, from "Auto-detect index path and select from the dropdown:"
i have already pressed it but it still doesnt show up in the dropdown. i can only select the index file but cant pick from the "inferencing voice" dropdown
I have the same issue, and I dont have the drop menu where I can choose my file to train. Please help!!
same issue. Any solution?
I'm also experiencing this problem.
Same problem here as well. I have trained the model, it got all files in its own folder, but no matter what, it doesn't appear in the Inference dropdown.
Same issue. Following for solution
I solved this issue by making sure everything was at the root of my C drive.
Any solution to this? I have no idea where to put index files such that I don't have to re-copy a path into the browser for every model. Not exactly helpful for using the web UI remotely.
Following.
I do have the same problem even after clicking refreshing
After some suffering, I found the solution: the weights directory is linked to the wrong path. Put your .pth file in assets/weights Follow steps by @sethtallen https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/611 but just use /assets/weights instead of /weights
If you have a custom path for the index or weights files:
- You can change the env vars in the .env file which is in this repo I changed the weight_root to weights here so I could upload my pth file to the /weights directory.
OPENBLAS_NUM_THREADS = 1
no_proxy = localhost, 127.0.0.1, ::1
# You can change the location of the model, etc. by changing here
# this is the path where the pth files go
weight_root = weights
weight_uvr5_root = assets/uvr5_weights
# this is the path where the index files go
index_root = logs
outside_index_root = assets/indices
rmvpe_root = assets/rmvpe
Important!! The developers should add this to the documentation so people can modify it before they run any scripts. @sethtallen