AIFSH comments

Results 6 comments of


                                            AIFSH

感谢大佬开源这个工程，想请教个问题

按道理 30 秒就能出效果

我想知道同时微调多个说话人会怎么样

这里有多人微调效果，可以看看哦【《降世神通：最后的气宗》AI国语配音| NativeSpeakerUI挑战多人场景下的GPT-SoVITS训练推理1条龙-哔哩哔哩】 https://b23.tv/XuhBvaJ

[Help needed!] There's clear box region around the mouth when using personal video

> It's a bit problematic for me to send the code. However, I can send the modifications. Take them as rough guidelines rather than exact. Read about how to use...

1. 希望添加一个推理界面换模型的方法，类似hiyori 2 能类似Bert 那样在一个模型里，可以训练出多个说话人么

这个实现了多人说话的训练和推理【NativeSpeakerUI挑战多人场景下的GPT-SoVITS训练推理1条龙】 https://www.bilibili.com/video/BV1DC4y1r7gP/?share_source=copy_web&vd_source=453c36b4abef37acd389d4c01b149023

能否增加上传srt字幕文件，自动生成音频文件的功能

这里有对srt字幕文件的支持 [【《荒野乱斗》游戏米科AI同声传译国语配音|NativeSpeakerUI手把手教程】]( https://www.bilibili.com/video/BV1m7421K7CS/?share_source=copy_web&vd_source=453c36b4abef37acd389d4c01b149023)

the comfyUI custom_node that recommended was not able to work well

https://github.com/AIFSH/ComfyUI-MuseTalk_FSH fix OOM,you may try