part of digital human, synthesis of audio. You can use the Jupter notebook to recurrent the project. You can replace long_audio_transcribe.py and short_audio_transcribe.py, if you want to train chinese audios.
Clone character voice from 10+ short audios
Clone character voice from long audio(s) >= 3 minutes (one audio should contain single speaker only)
Clone character voice from videos(s) >= 3 minutes (one video should contain single speaker only)
Clone character voice from BILIBILI video links (one video should contain single speaker only)