Restructure audio_vae: add encoder/ and decoder/ subfolders

audio_vae/decoder/config.json

@@ -0,0 +1,25 @@
+{
+    "attn_resolutions": [],
+    "attn_type": "vanilla",
+    "causality_axis": "height",
+    "ch": 128,
+    "ch_mult": [
+        1,
+        2,
+        4
+    ],
+    "dropout": 0.0,
+    "give_pre_end": false,
+    "is_causal": true,
+    "mel_bins": 64,
+    "mel_hop_length": 160,
+    "mid_block_add_attention": false,
+    "norm_type": "pixel",
+    "num_res_blocks": 2,
+    "out_ch": 2,
+    "resamp_with_conv": true,
+    "resolution": 256,
+    "sample_rate": 16000,
+    "tanh_out": false,
+    "z_channels": 8
+}

audio_vae/decoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:919f03edd099c5393eb5889be8abd74bf283a98081bce9859cf5d49f57a5c7fa
+size 63836681

audio_vae/decoder/model.safetensors.index.json

@@ -0,0 +1,65 @@
+{
+  "metadata": {
+    "total_size": 63830788
+  },
+  "weight_map": {
+    "conv_in.conv.bias": "model.safetensors",
+    "conv_in.conv.weight": "model.safetensors",
+    "conv_out.conv.bias": "model.safetensors",
+    "conv_out.conv.weight": "model.safetensors",
+    "mid.block_1.conv1.conv.bias": "model.safetensors",
+    "mid.block_1.conv1.conv.weight": "model.safetensors",
+    "mid.block_1.conv2.conv.bias": "model.safetensors",
+    "mid.block_1.conv2.conv.weight": "model.safetensors",
+    "mid.block_2.conv1.conv.bias": "model.safetensors",
+    "mid.block_2.conv1.conv.weight": "model.safetensors",
+    "mid.block_2.conv2.conv.bias": "model.safetensors",
+    "mid.block_2.conv2.conv.weight": "model.safetensors",
+    "per_channel_statistics.mean_of_means": "model.safetensors",
+    "per_channel_statistics.std_of_means": "model.safetensors",
+    "up.0.block.0.conv1.conv.bias": "model.safetensors",
+    "up.0.block.0.conv1.conv.weight": "model.safetensors",
+    "up.0.block.0.conv2.conv.bias": "model.safetensors",
+    "up.0.block.0.conv2.conv.weight": "model.safetensors",
+    "up.0.block.0.nin_shortcut.conv.bias": "model.safetensors",
+    "up.0.block.0.nin_shortcut.conv.weight": "model.safetensors",
+    "up.0.block.1.conv1.conv.bias": "model.safetensors",
+    "up.0.block.1.conv1.conv.weight": "model.safetensors",
+    "up.0.block.1.conv2.conv.bias": "model.safetensors",
+    "up.0.block.1.conv2.conv.weight": "model.safetensors",
+    "up.0.block.2.conv1.conv.bias": "model.safetensors",
+    "up.0.block.2.conv1.conv.weight": "model.safetensors",
+    "up.0.block.2.conv2.conv.bias": "model.safetensors",
+    "up.0.block.2.conv2.conv.weight": "model.safetensors",
+    "up.1.block.0.conv1.conv.bias": "model.safetensors",
+    "up.1.block.0.conv1.conv.weight": "model.safetensors",
+    "up.1.block.0.conv2.conv.bias": "model.safetensors",
+    "up.1.block.0.conv2.conv.weight": "model.safetensors",
+    "up.1.block.0.nin_shortcut.conv.bias": "model.safetensors",
+    "up.1.block.0.nin_shortcut.conv.weight": "model.safetensors",
+    "up.1.block.1.conv1.conv.bias": "model.safetensors",
+    "up.1.block.1.conv1.conv.weight": "model.safetensors",
+    "up.1.block.1.conv2.conv.bias": "model.safetensors",
+    "up.1.block.1.conv2.conv.weight": "model.safetensors",
+    "up.1.block.2.conv1.conv.bias": "model.safetensors",
+    "up.1.block.2.conv1.conv.weight": "model.safetensors",
+    "up.1.block.2.conv2.conv.bias": "model.safetensors",
+    "up.1.block.2.conv2.conv.weight": "model.safetensors",
+    "up.1.upsample.conv.conv.bias": "model.safetensors",
+    "up.1.upsample.conv.conv.weight": "model.safetensors",
+    "up.2.block.0.conv1.conv.bias": "model.safetensors",
+    "up.2.block.0.conv1.conv.weight": "model.safetensors",
+    "up.2.block.0.conv2.conv.bias": "model.safetensors",
+    "up.2.block.0.conv2.conv.weight": "model.safetensors",
+    "up.2.block.1.conv1.conv.bias": "model.safetensors",
+    "up.2.block.1.conv1.conv.weight": "model.safetensors",
+    "up.2.block.1.conv2.conv.bias": "model.safetensors",
+    "up.2.block.1.conv2.conv.weight": "model.safetensors",
+    "up.2.block.2.conv1.conv.bias": "model.safetensors",
+    "up.2.block.2.conv1.conv.weight": "model.safetensors",
+    "up.2.block.2.conv2.conv.bias": "model.safetensors",
+    "up.2.block.2.conv2.conv.weight": "model.safetensors",
+    "up.2.upsample.conv.conv.bias": "model.safetensors",
+    "up.2.upsample.conv.conv.weight": "model.safetensors"
+  }
+}

audio_vae/encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "ch": 128,
+  "in_channels": 2,
+  "ch_mult": [
+    1,
+    2,
+    4
+  ],
+  "num_res_blocks": 2,
+  "attn_resolutions": [],
+  "resolution": 256,
+  "z_channels": 8,
+  "double_z": true,
+  "n_fft": 1024,
+  "norm_type": "pixel",
+  "causality_axis": "height",
+  "dropout": 0.0,
+  "mid_block_add_attention": false,
+  "sample_rate": 16000,
+  "mel_hop_length": 160,
+  "is_causal": true,
+  "mel_bins": 64,
+  "resamp_with_conv": true,
+  "attn_type": "vanilla"
+}

audio_vae/encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4653689ea1cd5f814e8b8ec630c1b94c6d027040ccafae9db19544b0abbf2d20
+size 42671257