Update README.md
#2
by
reach-vb
HF staff
- opened
README.md
CHANGED
|
@@ -5,11 +5,7 @@ tags:
|
|
| 5 |
license: cc-by-nc-4.0
|
| 6 |
---
|
| 7 |
|
| 8 |
-
# MusicGen -
|
| 9 |
-
|
| 10 |
-
We further release a set of stereophonic capable models. Those were fine tuned for 200k updates starting
|
| 11 |
-
from the mono models. The training data is otherwise identical and capabilities and limitations are shared with the base modes. The stereo models work by getting 2 streams of tokens from the EnCodec model, and interleaving those using
|
| 12 |
-
the delay pattern.
|
| 13 |
|
| 14 |
MusicGen is a text-to-music model capable of generating high-quality music samples conditioned on text descriptions or audio prompts.
|
| 15 |
It is a single stage auto-regressive Transformer model trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz.
|
|
|
|
| 5 |
license: cc-by-nc-4.0
|
| 6 |
---
|
| 7 |
|
| 8 |
+
# MusicGen - Melody - Large 3.3B
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
|
| 10 |
MusicGen is a text-to-music model capable of generating high-quality music samples conditioned on text descriptions or audio prompts.
|
| 11 |
It is a single stage auto-regressive Transformer model trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz.
|