{ "format_version": 1, "layers": 8, "kv_heads": 16, "head_dim": 64, "window": 72, "states": [ { "name": "pre_conv", "shape": [ 1, 512, 2 ] }, { "name": "upsample.0.1.dwconv", "shape": [ 1, 1024, 6 ] }, { "name": "upsample.1.1.dwconv", "shape": [ 1, 1024, 6 ] }, { "name": "decoder.0", "shape": [ 1, 1024, 6 ] }, { "name": "decoder.1.block.1", "shape": [ 1, 768, 8 ] }, { "name": "decoder.1.block.2.conv1", "shape": [ 1, 768, 6 ] }, { "name": "decoder.1.block.3.conv1", "shape": [ 1, 768, 18 ] }, { "name": "decoder.1.block.4.conv1", "shape": [ 1, 768, 54 ] }, { "name": "decoder.2.block.1", "shape": [ 1, 384, 5 ] }, { "name": "decoder.2.block.2.conv1", "shape": [ 1, 384, 6 ] }, { "name": "decoder.2.block.3.conv1", "shape": [ 1, 384, 18 ] }, { "name": "decoder.2.block.4.conv1", "shape": [ 1, 384, 54 ] }, { "name": "decoder.3.block.1", "shape": [ 1, 192, 4 ] }, { "name": "decoder.3.block.2.conv1", "shape": [ 1, 192, 6 ] }, { "name": "decoder.3.block.3.conv1", "shape": [ 1, 192, 18 ] }, { "name": "decoder.3.block.4.conv1", "shape": [ 1, 192, 54 ] }, { "name": "decoder.4.block.1", "shape": [ 1, 96, 3 ] }, { "name": "decoder.4.block.2.conv1", "shape": [ 1, 96, 6 ] }, { "name": "decoder.4.block.3.conv1", "shape": [ 1, 96, 18 ] }, { "name": "decoder.4.block.4.conv1", "shape": [ 1, 96, 54 ] }, { "name": "decoder.6", "shape": [ 1, 96, 6 ] } ], "inputs": [ "codes", "offset", "past", "conv_0", "conv_1", "conv_2", "conv_3", "conv_4", "conv_5", "conv_6", "conv_7", "conv_8", "conv_9", "conv_10", "conv_11", "conv_12", "conv_13", "conv_14", "conv_15", "conv_16", "conv_17", "conv_18", "conv_19", "conv_20" ], "outputs": [ "audio", "present", "next_conv_0", "next_conv_1", "next_conv_2", "next_conv_3", "next_conv_4", "next_conv_5", "next_conv_6", "next_conv_7", "next_conv_8", "next_conv_9", "next_conv_10", "next_conv_11", "next_conv_12", "next_conv_13", "next_conv_14", "next_conv_15", "next_conv_16", "next_conv_17", "next_conv_18", "next_conv_19", "next_conv_20" ] }