cjangcjengh / ttsmodels Goto Github PK

Hello, I am currently learning data in Korean. vits can't pronounce properly even though it's 100 epochs. I'm curious about the intermediate learning process of model 6, 'Fox Waiting for You'. Thank You :)

软件环境我自己去找，你能给出一个标准能跑起来的软件环境

the outputs are amazing (and wow the database is huge)(also the output was like instant)
so planning to clone my own voice. Is there any program you can share.

thank you

在下載Jp的七人模型後，並不能有效生成語音，只會發出意義不明的短暫聲音。
但是我在使用中+日的模型時，能夠讓七海發出"你好"的中文語音，但在該模型使用中，日文仍不能有效產生語音。

Unable to use Japanese voice to generate output message.
However, I was able to use CH&JP model to generate a Chinese voice message "你好"。
Hope to hear from you soon.

Chinese & Japanese的模型无法生成中文和日文音频，但英文可以。

This link below is outdated:
https://sjtueducn-my.sharepoint.com/:u:/g/personal/cjang_cjengh_sjtu_edu_cn/Ee_mfaDUIltBv49uESNZC8ABe47OeIC1P53n0p4vDcdhsg?e=h171Yl

w2v2-how-to里的链接也挂了，“zenodo.org 未发送任何数据。”
如果允许的话，可以提供一下镜像链接或者文件链接吗？