Add content to README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,29 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- audio-generation
|
| 5 |
+
library_name: diffusers
|
| 6 |
+
base_model: harmonai/jmann-small-190k
|
| 7 |
---
|
| 8 |
+
|
| 9 |
+
Blunstron is a model I made for Harmonai's Dance Diffusion.
|
| 10 |
+
The dataset is less than five minutes of the song Old and Wise by The Alan Parsons Project, yet it performs very well and does not overfit.
|
| 11 |
+
Old and Wise is sung by Colin Blunstone, hence the name Blunstron.
|
| 12 |
+
|
| 13 |
+
# Why
|
| 14 |
+
I put music out for free on YouTube containing lots of tiny samples (in imitation of a musician named Todd Edwards),
|
| 15 |
+
and I've sampled Old and Wise a LOT because I like the auditory textures in it. I'm kind of running out of potential chops,
|
| 16 |
+
so I decided to generate a practically infinite supply of them with AI.
|
| 17 |
+
|
| 18 |
+
# How
|
| 19 |
+
I finetuned this on Google Colab for around two hours. I kind of dislike how the word "finetune" is used for Dance Diffusion, since unlike
|
| 20 |
+
Dreambooth with Stable Diffusion, it effectively changes the entire model, while Dance Diffusion models (including this one) effectively
|
| 21 |
+
become an entirely different model when fine-tuned for long enough.
|
| 22 |
+
|
| 23 |
+
# Audio Characteristics
|
| 24 |
+
- Deep, ethereal, soft auditory texture
|
| 25 |
+
- Mostly chords, not much melody
|
| 26 |
+
- Colin Blunstone-like vocals
|
| 27 |
+
- Occasional drum hits
|
| 28 |
+
|
| 29 |
+
A few examples are provided in the files of this git repo called blunstron-test-x.wav.
|