GPT-SoVITS icon indicating copy to clipboard operation
GPT-SoVITS copied to clipboard

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Results 1028 GPT-SoVITS issues
Sort by recently updated
recently updated
newest added

有大佬遇到过,这种现在有什么方法解决吗?现在都到了V4的版本,有人测试出比较好的参数吗? 求大佬解答一下

哪位大佬知道 如果我用apiv2启动 怎么制定用自己预训练的模型 下面这个配置有人可以讲讲每个参数啥意思吗 自定义的话是不是改这个custom就行了 ![Image](https://github.com/user-attachments/assets/a6c6faa0-7db6-4693-9e24-2181fcdc9a91)

我使用onnx_export.py导出v3、v4是是成功的,但是推理的时候声音是没有的,以下是我的代码

"C:\Users\Riley\AppData\Local\Programs\Python\Python310\python.exe" GPT_SoVITS/inference_webui.py "Auto" Traceback (most recent call last): File "C:\AI\GPT-SoVITS-v3lora-20250228\GPT_SoVITS\inference_webui.py", line 103, in from AR.models.t2s_lightning_module import Text2SemanticLightningModule File "C:\AI\GPT-SoVITS-v3lora-20250228\GPT_SoVITS\AR\models\t2s_lightning_module.py", line 11, in from AR.models.t2s_model import Text2SemanticDecoder File "C:\AI\GPT-SoVITS-v3lora-20250228\GPT_SoVITS\AR\models\t2s_model.py", line 20,...

The webui of GPT-SoVITS has been updated, and I'm not sure which button to press and how to set up files or models in this ui. It would be better...

推理的时候风扇都不会转的,播放音频的时候开始狂转了,查看任务管理器也没找到任何高占用的进程,我用的是50系显卡那个整合包

fast_inference还在维护吗?这个项目是否适合实时推理,首包延迟能到多少?

![Image](https://github.com/user-attachments/assets/02126831-7027-4f23-aeff-24fb9103c473)