文本生成音乐，可以通过文本描述生成“在风声中吹口哨”、“警报器和嗡嗡作响的引擎接近后走远”等特殊声音效果。
Zach Evans
c61cc65257
Add 'drop_last=True' to DataLoader
|
8 months ago | |
|---|---|---|
| audio_diffusion | 1 year ago | |
| dataset | 1 year ago | |
| viz | 1 year ago | |
| .gitignore | 1 year ago | |
| Dance_Diffusion.ipynb | 8 months ago | |
| Finetune_Dance_Diffusion.ipynb | 9 months ago | |
| LICENSE | 1 year ago | |
| README.md | 1 year ago | |
| defaults.ini | 1 year ago | |
| setup.py | 1 year ago | |
| train_uncond.py | 8 months ago |
README.md
sample-generator
Tools to train a generative model on arbitrary audio samples
Dance Diffusion notebook: 
Dance Diffusion fine-tune notebook:
Prerequisites
Dance Diffusion requires Python 3.7+
You can install the required packages by running pip install . from the root of the repo
Todo
- Add inference notebook
- Add interpolations to nobebook
- Add fine-tune notebook
- Add guidance to notebook