Metadata-Version: 2.1
Name: audioldm2
Version: 0.0.3
Summary: This package is written for text-to-audio/music generation.
Home-page: https://github.com/haoheliu/audioldm2
Author: Haohe Liu
Author-email: haoheliu@gmail.com
License: MIT
Platform: UNKNOWN
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: Implementation :: CPython
Classifier: Programming Language :: Python :: Implementation :: PyPy
Requires-Python: >=3.7.0
Description-Content-Type: text/markdown
License-File: LICENSE


# AudioLDM 2

A proper choice of seed is important for model performance.

## Installation

You will need to have python >= 3.7 and CUDA support to run AudioLDM2 

```shell
    pip install audioldm2=0.0.2
```

## Sound effect and Music Generation

- Generate based on a text prompt

```shell
audioldm2 -t "Musical constellations twinkling in the night sky, forming a cosmic melody."
```

- Generate based on a list of text

```shell
audioldm2 -tl batch.lst
```



