v3ucn
v3ucn
接口api添加dpo参数,添加main入口推理方法可复用
接口api增加跨域功能,方便接入其他应用,避免触发同源策略
Hi,Thank you for your open source project, but the pre-training model downloaded by default does not seem to support Chinese, and the trained model cannot produce Chinese voice.
当前逻辑对于老显卡不友好,比如NVIDIA T500,即使修改配置文件,is_half变量也会被反复赋值为True,导致推理的音频没有声音,现在改为自动判断当前设备是否支持半精度直接赋值逻辑
当前的版本在Windows下测试,如果whisper模型不存在,会在C:\Users\用户名\.cache\huggingface\hub下载模型,占用C盘空间
解决中文语音推理声音忽大忽小的问题 https://github.com/myshell-ai/MeloTTS/issues/45

rt,原版修改workers会报警告
Add parameters for theme color **Is this PR adding new feature or fix a BUG?** Add feature **Is this pull request related to any issue? If yes, please link the...
解决并发请求接口时,音色互相串的问题