---
language: ko
tags:
- text-to-speech
- VITS
license: mit
---

# Model Card for VITS Model

## Model Description
This model is a Variational Inference Text-to-Speech (VITS) model trained on Korean datasets.

## Usage
To use this model with the Huggingface Inference API, follow the steps below:

### Inference API
```python
from transformers import pipeline

tts = pipeline(model="path_to_your_model")
output = tts("안녕하세요")