Table 7 The training configuration of the BigVGAN
Adam optimizer \(\beta _1\) | 0.9 |
Adam optimizer \(\beta _2\) | 0.98 |
Adam optimizer \(\epsilon\) | \(10^{-8}\) |
Weight decay | 0.01 |
Batch size | 32 |
Training steps | 100,000 |
Adam optimizer \(\beta _1\) | 0.9 |
Adam optimizer \(\beta _2\) | 0.98 |
Adam optimizer \(\epsilon\) | \(10^{-8}\) |
Weight decay | 0.01 |
Batch size | 32 |
Training steps | 100,000 |