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 d242fd9679 Merge pull request #23 from twobob/indexing 3 days ago
audio_diffusion 9b861991a7 Fix imports in training file 5 months ago
dataset 6aa8fdfffa Adding jmann-large and glitch models [v0.9] 4 months ago
viz 27b9e2cdfd Adding audio diffusion code 6 months ago
.gitignore dbc09f6e22 Initial commit 8 months ago
Dance_Diffusion.ipynb 02fc1b8fcb amend TOC 3 days ago
Finetune_Dance_Diffusion.ipynb 0d913f9481 Update Finetune_Dance_Diffusion.ipynb 3 days ago
LICENSE dbc09f6e22 Initial commit 8 months ago
README.md fa8e5c8087 Update README.md 3 months ago
defaults.ini 74aa9dff7c set save_wandb to none 3 months ago
setup.py 35c7fb3389 Update setup.py 4 months ago
train_uncond.py 104a27782f fix import 2 months ago

README.md

sample-generator

Tools to train a generative model on arbitrary audio samples

Dance Diffusion notebook: Open In Colab

Dance Diffusion fine-tune notebook: Open In Colab

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