I finetuned the other voice using less than 50 seconds of total audio so that I can use it with piper tts in this example.
Piper TTS Github: github.com/rhasspy/piper
PiperUI Github: github.com/natlamir/PiperUI
0:00 Intro
0:53 Gathering Dataset
2:27 Training Notebook
8:02 Inference Notebook
10:18 Export Notebook
11:29 Extract and Use Model
4 июл 2024