---
language:
- ja
- zh
- en
pipeline_tag: text-to-speech
---
# Style-Bert-VITS2 base model

The base model of [Style-Bert-VITS2](https://github.com/litagin02/Style-Bert-VITS2).

- These models are essentially the safetensors versions of [Bert-VITS2](https://github.com/fishaudio/Bert-VITS2) 2.1 base models (emo-related key in G_0 deleted).
- Hence all credits go to the original authors of Bert-VITS2 2.1 base models and [Fish Audio](https://github.com/fishaudio).