---
license: cc-by-nc-4.0
datasets:
- OOPPEENN/56697375616C4E6F76656C5F44617461736574
- amphion/Emilia-Dataset
- litagin/ehehe-corpus
- joujiboi/japanese-anime-speech
language:
- ja
base_model:
- HKUSTAudio/Llasa-1B-Multilingual
pipeline_tag: text-to-speech
---

# Galgame-Llasa-1B-v2

## Overview

This is the version 2 of the Galgame-Llasa-1B, a Text-to-Speech (TTS) model fine-tuned for Japanese. This model is based on [HKUSTAudio/Llasa-1B-Multilingual](https://huggingface.co/HKUSTAudio/Llasa-1B-Multilingual).

## What's New in v2?

This version has been trained on a larger and more diverse dataset, including the original Galgame dataset and other sources.

As a result, v2 offers several key improvements over the previous version:

- **Improved Kanji Reading:** The model now handles the reading of Kanji characters more accurately.
- **Enhanced Prosody:** The generated speech has more natural intonation and expressiveness.
- **Greater Voice Diversity:** The model can produce a wider range of voice styles than previous version.

## License

This model is licensed under the **CC-BY-NC-4.0**.