项目地址: babysor/MockingBird: AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time (github.com)https://github.com/babysor/MockingBird
步骤:
1. 数据集制作
2. 项目环境搭建
3. 模型训练
注意应在train文件夹内新建一文件夹存放数据。
python synthesizer_train.py mandarin /SV2TTS/synthesizer
4. 启动程序
python demo_toolbox.py