Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: text-to-audio
|
| 3 |
+
tags:
|
| 4 |
+
- audio
|
| 5 |
+
- mozart
|
| 6 |
+
- piano
|
| 7 |
+
- concert
|
| 8 |
+
- music
|
| 9 |
+
- generation
|
| 10 |
+
- open
|
| 11 |
+
- open-source
|
| 12 |
+
- cpu
|
| 13 |
+
- local
|
| 14 |
+
- tiny
|
| 15 |
+
- small
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
+
# Welcome to TinyMozart v2 85M!
|
| 19 |
+
This model is an unconditional MIDI classic piano music generator trained on the Google MAESTRO V3 MIDI dataset.
|
| 20 |
+
<br>
|
| 21 |
+
Note, that this is the **second** version of our TinyMozart model series.
|
| 22 |
+
|
| 23 |
+
## How to use it
|
| 24 |
+
To use this model and generate your own music, just download `model.pt` and `use.py` and run it with Python3. Have fun :D
|
| 25 |
+
|
| 26 |
+
## Training code
|
| 27 |
+
Use `train.py`.
|
| 28 |
+
|
| 29 |
+
## Training data
|
| 30 |
+
We trained on [https://storage.googleapis.com/magentadata/datasets/maestro/v3.0.0/maestro-v3.0.0-midi.zip](https://storage.googleapis.com/magentadata/datasets/maestro/v3.0.0/maestro-v3.0.0-midi.zip).
|
| 31 |
+
|
| 32 |
+
## Limitations
|
| 33 |
+
We know, this model isn't perfect, but it's a good beginning to understand how to generate music with AI models.
|