| { | |
| "component": "audio_vae", | |
| "channels": 1, | |
| "decoder_dim": 1536, | |
| "decoder_rates": [ | |
| 16, | |
| 8, | |
| 5, | |
| 3 | |
| ], | |
| "depthwise": true, | |
| "encoder_dim": 128, | |
| "encoder_rates": [ | |
| 3, | |
| 5, | |
| 8, | |
| 16 | |
| ], | |
| "fix_std": 0.15, | |
| "frame_rate": 12.5, | |
| "logvar_max": 20.0, | |
| "logvar_min": -30.0, | |
| "posterior_type": "sigma", | |
| "sample_rate": 24000, | |
| "std_dist_type": "gaussian", | |
| "use_noise_block": false, | |
| "vae_dim": 64, | |
| "weight_init_value": 0.02 | |
| } | |