StarGANv2-VC
StarGANv2-VC copied to clipboard
My recommendation results are not true
I hope to infer one person's voice to another person's voice, but the inference result does not match the actual sound of the uploaded file, is it due to weight? Or what?
I don't understand your question. What do you mean by does not match the actual sound?
我不明白你的问题。与实际声音不符是什么意思?
Inference logic: Convert the audio of A's speech to the audio of B's speech, and obtain the audio of B imitating A's speech; The problem is "B imitates A's voice and doesn't want B's original voice"
use a longer reference sample or increase your training data. both will help