Giters

serp-ai / bark-with-voice-clone

🔊 Text-prompted Generative Audio Model - With the ability to clone voices

Home Page:https://serp.ai/tools/bark-text-to-speech-ai-voice-clone-app

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Training Model (Semantics)

bastiansurya77 opened this issue · comments

commented

I had the data of multiple ~8 seconds audio clips (.wav). If I understand it correctly, do I need to generate the semantics output, fine output and course output to able to train it using my own dataset? and is it able to generate a natural synthetis audio by training it using my own datasets?