Audiocraft音频生成深度学习库
Audiocraft 是用于音频生成的深度学习库。它使用深度学习进行音频处理和生成,具有最先进的 EnCodec 音频压缩器/分词器,以及 MusicGen——简单且可控的音乐生成大模型,具有文本和旋律调节功能。
运行 Audiocraft 的环境要求:
- Python 3.9
- PyTorch 2.0.0
- 内存至少为 16 GB 的 GPU(对于中型模型)
如需安装 Audiocraft,运行以下命令:
# Best to make sure you have torch installed first, in particular before installing xformers.
# Don't run this if you already have PyTorch installed.
pip install 'torch>=2.0'
# Then proceed to one of the following
pip install -U audiocraft # stable release
pip install -U git+https://git@github.com/facebookresearch/audiocraft#egg=audiocraft # bleeding edge
pip install -e . # or if you cloned the repo locally
评论