encoder-weights.json

{
  "repo_id": "Aratako/MioCodec-25Hz-24kHz",
  "torch": "2.10.0+cu128",
  "sources": {
    "miocodec": {
      "file": "model.safetensors",
      "bytes": 523087956,
      "sha256": "60483759cde136451d53ff5a2f7e283c015758ab540de9037b5d4519366a7705"
    },
    "wavlm": {
      "file": "wavlm_base_plus.pth",
      "bytes": 377604347,
      "sha256": "136a3e720c04f2c77bf7a4dc6a3868b14d5a2c145a988114b733cb1a8428be98"
    }
  },
  "resample": {
    "orig": 3,
    "new": 2,
    "width": 10
  },
  "tensors": {
    "resample.kernel": [
      2,
      1,
      23
    ],
    "wavlm.feature_extractor.conv_layers.0.conv.weight": [
      512,
      1,
      10
    ],
    "wavlm.feature_extractor.conv_layers.0.layer_norm.weight": [
      512
    ],
    "wavlm.feature_extractor.conv_layers.0.layer_norm.bias": [
      512
    ],
    "wavlm.feature_extractor.conv_layers.1.conv.weight": [
      512,
      512,
      3
    ],
    "wavlm.feature_extractor.conv_layers.2.conv.weight": [
      512,
      512,
      3
    ],
    "wavlm.feature_extractor.conv_layers.3.conv.weight": [
      512,
      512,
      3
    ],
    "wavlm.feature_extractor.conv_layers.4.conv.weight": [
      512,
      512,
      3
    ],
    "wavlm.feature_extractor.conv_layers.5.conv.weight": [
      512,
      512,
      2
    ],
    "wavlm.feature_extractor.conv_layers.6.conv.weight": [
      512,
      512,
      2
    ],
    "wavlm.encoder.feature_projection.layer_norm.weight": [
      512
    ],
    "wavlm.encoder.feature_projection.layer_norm.bias": [
      512
    ],
    "wavlm.encoder.feature_projection.projection.weight": [
      768,
      512
    ],
    "wavlm.encoder.feature_projection.projection.bias": [
      768
    ],
    "wavlm.encoder.transformer.pos_conv_embed.conv.weight": [
      768,
      48,
      128
    ],
    "wavlm.encoder.transformer.pos_conv_embed.conv.bias": [
      768
    ],
    "wavlm.encoder.transformer.layer_norm.weight": [
      768
    ],
    "wavlm.encoder.transformer.layer_norm.bias": [
      768
    ],
    "wavlm.encoder.transformer.layers.0.attention.attention.in_proj_weight": [
      2304,
      768
    ],
    "wavlm.encoder.transformer.layers.0.attention.attention.in_proj_bias": [
      2304
    ],
    "wavlm.encoder.transformer.layers.0.attention.attention.out_proj.weight": [
      768,
      768
    ],
    "wavlm.encoder.transformer.layers.0.attention.attention.out_proj.bias": [
      768
    ],
    "wavlm.encoder.transformer.layers.0.attention.gru_rel_pos_linear.weight": [
      8,
      64
    ],
    "wavlm.encoder.transformer.layers.0.attention.gru_rel_pos_linear.bias": [
      8
    ],
    "wavlm.encoder.transformer.layers.0.attention.gru_rel_pos_const": [
      1,
      12,
      1,
      1
    ],
    "wavlm.encoder.transformer.layers.0.attention.rel_attn_embed.weight": [
      320,
      12
    ],
    "wavlm.encoder.transformer.layers.0.layer_norm.weight": [
      768
    ],
    "wavlm.encoder.transformer.layers.0.layer_norm.bias": [
      768
    ],
    "wavlm.encoder.transformer.layers.0.final_layer_norm.weight": [
      768
    ],
    "wavlm.encoder.transformer.layers.0.final_layer_norm.bias": [
      768
    ],
    "wavlm.encoder.transformer.layers.0.feed_forward.intermediate_dense.weight": [
      3072,
      768
    ],
    "wavlm.encoder.transformer.layers.0.feed_forward.intermediate_dense.bias": [
      3072
    ],
    "wavlm.encoder.transformer.layers.0.feed_forward.output_dense.weight": [
      768,
      3072
    ],
    "wavlm.encoder.transformer.layers.0.feed_forward.output_dense.bias": [
      768
    ],
    "wavlm.encoder.transformer.layers.1.attention.attention.in_proj_weight": [
      2304,
      768
    ],
    "wavlm.encoder.transformer.layers.1.attention.attention.in_proj_bias": [
      2304
    ],
    "wavlm.encoder.transformer.layers.1.attention.attention.out_proj.weight": [
      768,
      768
    ],
    "wavlm.encoder.transformer.layers.1.attention.attention.out_proj.bias": [
      768
    ],
    "wavlm.encoder.transformer.layers.1.attention.gru_rel_pos_linear.weight": [
      8,
      64
    ],
    "wavlm.encoder.transformer.layers.1.attention.gru_rel_pos_linear.bias": [
      8
    ],
    "wavlm.encoder.transformer.layers.1.attention.gru_rel_pos_const": [
      1,
      12,
      1,
      1
    ],
    "wavlm.encoder.transformer.layers.1.layer_norm.weight": [
      768
    ],
    "wavlm.encoder.transformer.layers.1.layer_norm.bias": [
      768
    ],
    "wavlm.encoder.transformer.layers.1.final_layer_norm.weight": [
      768
    ],
    "wavlm.encoder.transformer.layers.1.final_layer_norm.bias": [
      768
    ],
    "wavlm.encoder.transformer.layers.1.feed_forward.intermediate_dense.weight": [
      3072,
      768
    ],
    "wavlm.encoder.transformer.layers.1.feed_forward.intermediate_dense.bias": [
      3072
    ],
    "wavlm.encoder.transformer.layers.1.feed_forward.output_dense.weight": [
      768,
      3072
    ],
    "wavlm.encoder.transformer.layers.1.feed_forward.output_dense.bias": [
      768
    ],
    "global_encoder.backbone.embed.weight": [
      384,
      768,
      7
    ],
    "global_encoder.backbone.embed.bias": [
      384
    ],
    "global_encoder.backbone.norm.weight": [
      384
    ],
    "global_encoder.backbone.norm.bias": [
      384
    ],
    "global_encoder.backbone.convnext.0.gamma": [
      384
    ],
    "global_encoder.backbone.convnext.0.dwconv.weight": [
      384,
      1,
      7
    ],
    "global_encoder.backbone.convnext.0.dwconv.bias": [
      384
    ],
    "global_encoder.backbone.convnext.0.norm.weight": [
      384
    ],
    "global_encoder.backbone.convnext.0.norm.bias": [
      384
    ],
    "global_encoder.backbone.convnext.0.pwconv1.weight": [
      1152,
      384
    ],
    "global_encoder.backbone.convnext.0.pwconv1.bias": [
      1152
    ],
    "global_encoder.backbone.convnext.0.pwconv2.weight": [
      384,
      1152
    ],
    "global_encoder.backbone.convnext.0.pwconv2.bias": [
      384
    ],
    "global_encoder.backbone.convnext.1.gamma": [
      384
    ],
    "global_encoder.backbone.convnext.1.dwconv.weight": [
      384,
      1,
      7
    ],
    "global_encoder.backbone.convnext.1.dwconv.bias": [
      384
    ],
    "global_encoder.backbone.convnext.1.norm.weight": [
      384
    ],
    "global_encoder.backbone.convnext.1.norm.bias": [
      384
    ],
    "global_encoder.backbone.convnext.1.pwconv1.weight": [
      1152,
      384
    ],
    "global_encoder.backbone.convnext.1.pwconv1.bias": [
      1152
    ],
    "global_encoder.backbone.convnext.1.pwconv2.weight": [
      384,
      1152
    ],
    "global_encoder.backbone.convnext.1.pwconv2.bias": [
      384
    ],
    "global_encoder.backbone.convnext.2.gamma": [
      384
    ],
    "global_encoder.backbone.convnext.2.dwconv.weight": [
      384,
      1,
      7
    ],
    "global_encoder.backbone.convnext.2.dwconv.bias": [
      384
    ],
    "global_encoder.backbone.convnext.2.norm.weight": [
      384
    ],
    "global_encoder.backbone.convnext.2.norm.bias": [
      384
    ],
    "global_encoder.backbone.convnext.2.pwconv1.weight": [
      1152,
      384
    ],
    "global_encoder.backbone.convnext.2.pwconv1.bias": [
      1152
    ],
    "global_encoder.backbone.convnext.2.pwconv2.weight": [
      384,
      1152
    ],
    "global_encoder.backbone.convnext.2.pwconv2.bias": [
      384
    ],
    "global_encoder.backbone.convnext.3.gamma": [
      384
    ],
    "global_encoder.backbone.convnext.3.dwconv.weight": [
      384,
      1,
      7
    ],
    "global_encoder.backbone.convnext.3.dwconv.bias": [
      384
    ],
    "global_encoder.backbone.convnext.3.norm.weight": [
      384
    ],
    "global_encoder.backbone.convnext.3.norm.bias": [
      384
    ],
    "global_encoder.backbone.convnext.3.pwconv1.weight": [
      1152,
      384
    ],
    "global_encoder.backbone.convnext.3.pwconv1.bias": [
      1152
    ],
    "global_encoder.backbone.convnext.3.pwconv2.weight": [
      384,
      1152
    ],
    "global_encoder.backbone.convnext.3.pwconv2.bias": [
      384
    ],
    "global_encoder.backbone.final_layer_norm.weight": [
      384
    ],
    "global_encoder.backbone.final_layer_norm.bias": [
      384
    ],
    "global_encoder.pooling.attn.0.weight": [
      128,
      384,
      1
    ],
    "global_encoder.pooling.attn.0.bias": [
      128
    ],
    "global_encoder.pooling.attn.2.weight": [
      384,
      128,
      1
    ],
    "global_encoder.pooling.attn.2.bias": [
      384
    ],
    "global_encoder.pooling.proj.weight": [
      128,
      768
    ],
    "global_encoder.pooling.proj.bias": [
      128
    ],
    "global_encoder.pooling.norm.weight": [
      128
    ],
    "global_encoder.pooling.norm.bias": [
      128
    ]
  },
  "bytes": 117303232,
  "sha256": "a35b4eaec345dde0e9abb2a7aa2c8c66e7a39d4ab53afce584568b5a616a0abd"
}