xtts-webui
xtts-webui copied to clipboard
How do you use the fine tuned models (not load, but USE)
I can train in the webui but i cant use the models! Both the api and the webui use the .wav file for speakers not the finetuned model even when its loaded. EDIT: As I say I can load the model in the webui once trained but I have to select a speaker wav file, it wont let me use the fine tuned model. Same issue with the api, you can load it fully but when you send a json packet you have to include the speaker wav file and thus bypass the fine tuning.
Can you give some instructions on how to use the fine tuned model please.