Text-to-Audio
Audiocraft
magnet
Corbanp commited on
Commit
21e2e4a
1 Parent(s): 2559c59

Revise grammar

Browse files

This is not a serious pull request, but in English a double negative doesn't emphasize the statement but reverses it, similar to the logical not operator. If this was intended, consider revising the sentence into a positive form to clarify.

Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -20,7 +20,7 @@ widget:
20
 
21
  MAGNeT is a text-to-music and text-to-sound model capable of generating high-quality audio samples conditioned on text descriptions.
22
  It is a masked generative non-autoregressive Transformer trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz.
23
- Unlike prior work, MAGNeT doesn't require neither semantic token conditioning nor model cascading, and it generates all 4 codebooks using a single non-autoregressive Transformer.
24
 
25
  MAGNeT was published in [Masked Audio Generation using a Single Non-Autoregressive Transformer](https://arxiv.org/abs/2401.04577) by *Alon Ziv, Itai Gat, Gael Le Lan, Tal Remez, Felix Kreuk, Alexandre Défossez, Jade Copet, Gabriel Synnaeve, Yossi Adi*.
26
 
 
20
 
21
  MAGNeT is a text-to-music and text-to-sound model capable of generating high-quality audio samples conditioned on text descriptions.
22
  It is a masked generative non-autoregressive Transformer trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz.
23
+ Unlike prior work, MAGNeT requires neither semantic token conditioning nor model cascading, and it generates all 4 codebooks using a single non-autoregressive Transformer.
24
 
25
  MAGNeT was published in [Masked Audio Generation using a Single Non-Autoregressive Transformer](https://arxiv.org/abs/2401.04577) by *Alon Ziv, Itai Gat, Gael Le Lan, Tal Remez, Felix Kreuk, Alexandre Défossez, Jade Copet, Gabriel Synnaeve, Yossi Adi*.
26