Open rishikksh20 opened 10 months ago
This paper : https://arxiv.org/pdf/2401.01099.pdf , suggest better masking strategy with Grouped Acoustic Token like HiFi-Codec which results far better quality that Soundstorm.
This paper : https://arxiv.org/pdf/2401.01099.pdf , suggest better masking strategy with Grouped Acoustic Token like HiFi-Codec which results far better quality that Soundstorm.