---
license: mit
datasets:
- MuGemSt/hoyo_music
language:
- zh
- en
metrics:
- accuracy
library_name: adapter-transformers
tags:
- art
- music
- code
- text-generation-inference
---

# 简介 Intro
米哈游音乐生成模型是基于 Tunesformer 架构开发的创新型音乐创作模型。该模型经过在米哈游音乐二创钢琴数据集上的训练，专门用于生成受米哈游社区用户创作内容启发的音乐。目前，训练数据仅限于从《原神》和《崩铁》等米哈游旗下游戏的音乐二创中提取的 abc 乐谱切片数据。借助 Tunesformer 模型，米哈游音乐生成模型旨在捕捉米哈游游戏宇宙中独特音乐风格的精髓，代表了先进技术和艺术创意的融合。

The hoyoMusic model is an innovative music generation model developed based on the Tunesformer architecture. The model has been trained on the MiHoYo music second creation piano dataset and is specifically designed to generate music inspired by user-created content from the MiHoYo user community. Currently, the training data is limited to abc score slices extracted from the music of MiHoYo's games such as Genshin Impact and Star Rail. With the Tunesformer model, the hoyoMusic model aims to capture the essence of the unique musical styles in the HoYoverse, which represents a fusion of advanced technology and artistic creativity.

## 在线体验 Demo
<https://www.modelscope.cn/studios/MuGemSt/hoyoMusic>

## 使用 Usage
```python
from modelscope import snapshot_download
model_dir = snapshot_download("MuGemSt/hoyoMusic")
```

## 维护 Maintenance
```bash
git clone git@hf.co:MuGemSt/hoyoMusic
cd hoyoMusic
```

## 数据集 Dataset
<https://www.modelscope.cn/datasets/MuGemSt/hoyoMusic>

## 镜像 Mirror
<https://www.modelscope.cn/models/MuGemSt/hoyoMusic>

## 参考引用 Reference
[1] <https://musescore.org><br>
[2] <https://genshin-impact.fandom.com/wiki/Genshin_Impact_Wiki><br>
[3] <https://honkai-star-rail.fandom.com/wiki/Honkai:_Star_Rail_Wiki><br>
[4] <https://www.modelscope.cn/models/MuGemSt/tunesformer>