compressionkit E2A2 codec, redistributed from danjacobellis/E2A2 with the author's permission
4e60ba0 | { | |
| "codec": "E2A2", | |
| "format": "e2a2_hub1", | |
| "source_checkpoint": "e2a2a_g7.pth", | |
| "modality": "audio", | |
| "dim": 1, | |
| "input_channels": 2, | |
| "ps": [ | |
| 256, | |
| 256, | |
| 128, | |
| 64, | |
| 32, | |
| 16, | |
| 8 | |
| ], | |
| "group_sizes": [ | |
| 4, | |
| 5, | |
| 6, | |
| 6, | |
| 12, | |
| 9, | |
| 9 | |
| ], | |
| "cumulative_channels": [ | |
| 4, | |
| 9, | |
| 15, | |
| 21, | |
| 33, | |
| 42, | |
| 51 | |
| ], | |
| "n_groups": 7, | |
| "affine": true, | |
| "linear_input": false, | |
| "decoder_configs": [ | |
| { | |
| "decoder_ps": 128, | |
| "decoder_dim": 1024, | |
| "decoder_kernel_size": 3, | |
| "decoder_depth": 12, | |
| "decoder_mlp_ratio": 4, | |
| "decoder_layerscale": true, | |
| "decoder_layerscale_init": 1e-06 | |
| }, | |
| { | |
| "decoder_ps": 128, | |
| "decoder_dim": 1024, | |
| "decoder_kernel_size": 3, | |
| "decoder_depth": 12, | |
| "decoder_mlp_ratio": 4, | |
| "decoder_layerscale": true, | |
| "decoder_layerscale_init": 1e-06 | |
| }, | |
| { | |
| "decoder_ps": 128, | |
| "decoder_dim": 1024, | |
| "decoder_kernel_size": 3, | |
| "decoder_depth": 24, | |
| "decoder_mlp_ratio": 4, | |
| "decoder_layerscale": true, | |
| "decoder_layerscale_init": 1e-06 | |
| }, | |
| { | |
| "decoder_ps": 128, | |
| "decoder_dim": 1024, | |
| "decoder_kernel_size": 3, | |
| "decoder_depth": 24, | |
| "decoder_mlp_ratio": 4, | |
| "decoder_layerscale": true, | |
| "decoder_layerscale_init": 1e-06 | |
| }, | |
| { | |
| "decoder_ps": 128, | |
| "decoder_dim": 1024, | |
| "decoder_kernel_size": 3, | |
| "decoder_depth": 24, | |
| "decoder_mlp_ratio": 4, | |
| "decoder_layerscale": true, | |
| "decoder_layerscale_init": 1e-06 | |
| }, | |
| { | |
| "decoder_ps": 128, | |
| "decoder_dim": 1024, | |
| "decoder_kernel_size": 3, | |
| "decoder_depth": 24, | |
| "decoder_mlp_ratio": 4, | |
| "decoder_layerscale": true, | |
| "decoder_layerscale_init": 1e-06 | |
| }, | |
| { | |
| "decoder_ps": 128, | |
| "decoder_dim": 1024, | |
| "decoder_kernel_size": 3, | |
| "decoder_depth": 24, | |
| "decoder_mlp_ratio": 4, | |
| "decoder_layerscale": true, | |
| "decoder_layerscale_init": 1e-06 | |
| } | |
| ], | |
| "macroregion": 16384, | |
| "stream_mode": "all_detail", | |
| "compander": "softsign", | |
| "compander_bits": 6, | |
| "alphabet": [ | |
| -31, | |
| 31 | |
| ], | |
| "input_range": [ | |
| -1, | |
| 1 | |
| ], | |
| "sample_rate": 44100, | |
| "val_normalize": "peak" | |
| } |