Moshi: a speech-text foundation model for real-time dialogue
Paper • 2410.00037 • Published • 20
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Chinese-Mimi 是一个针对中文语音优化的声码器模型,它基于 Moshi 框架中的 Mimi 组件进行改进,在超过 10,000 小时的高质量 WenetSpeech4TTS 语音数据集上进行渐进式预训练。
SDK下载
#安装ModelScope
pip install modelscope
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('zruiii/Chinese-Mimi')
Git下载
#Git模型下载
git clone https://www.modelscope.cn/zruiii/Chinese-Mimi.git