Chiikawa (chiikawa) Xiao Hachi GPT-SoVITS model

Advance note: This model is trained with the GPT-SoVITS V2 V2 V2 version. If you plan to use it on V1, loading failures or other issues may occur, so it's best to use the newly released V2 version.

When using, please place the model files in the corresponding folders. The RVC version of the model is already in training, including support for Chinese and Japanese.

The folder includes

:

Model files

A training dataset and a test speech dataset

Listening experience

<!--[if lt IE 9]>document.createElement('audio');<![endif]-->

Project screenshot

Training log

All the raw datasets above are manually extracted and produced, so the results are better. However, since these are daily conversions, the sound may sound a bit awkward. This is similar to gacha—just draw a few more times, or you can select test datasets from the raw datasets we provide for inference.