GPT-SoVITS

GPT-SoVITS copied to clipboard

AttributeError: module 'PIL.Image' has no attribute 'ANTIALIAS'

3

训练的时候报错：AttributeError: module 'PIL.Image' has no attribute 'ANTIALIAS' ``` Traceback (most recent call last): File "/apdcephfs/private_raymondguo/tts/GPT-SoVITS/GPT_SoVITS/s2_train.py", line 566, in main() File "/apdcephfs/private_raymondguo/tts/GPT-SoVITS/GPT_SoVITS/s2_train.py", line 53, in main mp.spawn( File "/apdcephfs/private_raymondguo/tts/GPT-SoVITS/env/lib/python3.10/site-packages/torch/multiprocessing/spawn.py", line 240,...

potatoker

感谢大佬开源如此优秀的项目 【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/hM3wmEF

AIFSH

深度融合 gpt-sovits，训练推理 1 条龙

2

感谢大佬开源如此优秀的项目 我进行了深度融合，让它训练推理丝滑一条龙，用例视频见下方 B站链接 【《交错战线》银羽AI日语同声传译配音 | 连夜睡服GPT-SoVITS，让它在NativeSpeakerUI里面提供同声传译1条龙服务-哔哩哔哩】 https://b23.tv/0dxSWpQ

AIFSH

KakaruHayate

超长文本自动切片+生成, 如txt格式的书籍可以挂机一晚

bruce2233

Sometime "is_hp3" doesn't work. And the output position is incorrect.

KamioRinn


liaozhi0520

添加音频降噪功能，去除电音和杂音

4

添加音频降噪功能，去除电音和杂音

v3ucn

ubuntu下docker安装后api.py启动报错

2

root@cdb17e5279aa:/workspace# pip list | grep feature feature-extractor 0.0.1 docker中查看已安装feature-extractor root@cdb17e5279aa:/workspace# python api.py -dr "123.wav" -dt "一二三" -dl "中文" Traceback (most recent call last): File "/workspace/api.py", line 14, in from feature_extractor...

tjsztj

目前的推理需要辅助音频和文本，想问下是否可以不需要辅助音频，只需要选择训练时的音色类别，来推理合成音频就行

Polaris231