Fix typo in model card
#11
by
maharshipandya
- opened
README.md
CHANGED
@@ -15,7 +15,7 @@ widget:
|
|
15 |
|
16 |
# MusicGen - Medium - 1.5B
|
17 |
|
18 |
-
MusicGen is a text-to-music model capable of
|
19 |
It is a single stage auto-regressive Transformer model trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz.
|
20 |
Unlike existing methods, like MusicLM, MusicGen doesn't require a self-supervised semantic representation, and it generates all 4 codebooks in one pass.
|
21 |
By introducing a small delay between the codebooks, we show we can predict them in parallel, thus having only 50 auto-regressive steps per second of audio.
|
|
|
15 |
|
16 |
# MusicGen - Medium - 1.5B
|
17 |
|
18 |
+
MusicGen is a text-to-music model capable of generating high-quality music samples conditioned on text descriptions or audio prompts.
|
19 |
It is a single stage auto-regressive Transformer model trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz.
|
20 |
Unlike existing methods, like MusicLM, MusicGen doesn't require a self-supervised semantic representation, and it generates all 4 codebooks in one pass.
|
21 |
By introducing a small delay between the codebooks, we show we can predict them in parallel, thus having only 50 auto-regressive steps per second of audio.
|