Fix typo in model card

#11
Files changed (1) hide show
  1. README.md +1 -1
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 genreating 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.
 
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.