config.json

{
  "acoustic_model_config": {
    "codebook_dim": 8,
    "codebook_loss_weight": 1.0,
    "codebook_size": 1024,
    "commitment_loss_weight": 0.25,
    "decoder_hidden_size": 1024,
    "downsampling_ratios": [
      8,
      5,
      4,
      2
    ],
    "encoder_hidden_size": 64,
    "hidden_size": 256,
    "hop_length": 320,
    "model_type": "dac",
    "n_codebooks": 9,
    "quantizer_dropout": 0,
    "sampling_rate": 16000,
    "upsampling_ratios": [
      8,
      5,
      4,
      2
    ]
  },
  "architectures": [
    "XcodecModel"
  ],
  "block_dilations": [
    1,
    1
  ],
  "channel_ratios": [
    1,
    1
  ],
  "codebook_dim": 1024,
  "codebook_size": 1024,
  "decoder_channels": 768,
  "encoder_channels": 768,
  "initializer_range": 0.02,
  "input_channels": 768,
  "kernel_size": 3,
  "model_type": "xcodec",
  "output_channels": 768,
  "sample_rate": 16000,
  "semantic_model_config": {
    "_name_or_path": "microsoft/wavlm-base-plus",
    "activation_dropout": 0.0,
    "adapter_kernel_size": 3,
    "adapter_stride": 2,
    "add_adapter": false,
    "apply_spec_augment": true,
    "architectures": [
      "WavLMModel"
    ],
    "attention_dropout": 0.1,
    "classifier_proj_size": 256,
    "codevector_dim": 256,
    "contrastive_logits_temperature": 0.1,
    "conv_bias": false,
    "conv_dim": [
      512,
      512,
      512,
      512,
      512,
      512,
      512
    ],
    "conv_kernel": [
      10,
      3,
      3,
      3,
      3,
      2,
      2
    ],
    "conv_stride": [
      5,
      2,
      2,
      2,
      2,
      2,
      2
    ],
    "ctc_loss_reduction": "sum",
    "ctc_zero_infinity": false,
    "diversity_loss_weight": 0.1,
    "do_stable_layer_norm": false,
    "feat_extract_activation": "gelu",
    "feat_extract_norm": "group",
    "feat_proj_dropout": 0.1,
    "feat_quantizer_dropout": 0.0,
    "final_dropout": 0.0,
    "freeze_feat_extract_train": true,
    "hidden_act": "gelu",
    "hidden_dropout": 0.1,
    "hidden_size": 768,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-05,
    "layerdrop": 0.05,
    "mask_channel_length": 10,
    "mask_channel_min_space": 1,
    "mask_channel_other": 0.0,
    "mask_channel_prob": 0.0,
    "mask_channel_selection": "static",
    "mask_feature_length": 10,
    "mask_feature_min_masks": 0,
    "mask_feature_prob": 0.0,
    "mask_time_length": 10,
    "mask_time_min_masks": 2,
    "mask_time_min_space": 1,
    "mask_time_other": 0.0,
    "mask_time_prob": 0.05,
    "mask_time_selection": "static",
    "max_bucket_distance": 800,
    "model_type": "wavlm",
    "no_mask_channel_overlap": false,
    "no_mask_time_overlap": false,
    "num_adapter_layers": 3,
    "num_attention_heads": 12,
    "num_buckets": 320,
    "num_codevector_groups": 2,
    "num_codevectors_per_group": 320,
    "num_conv_pos_embedding_groups": 16,
    "num_conv_pos_embeddings": 128,
    "num_ctc_classes": 80,
    "num_feat_extract_layers": 7,
    "num_hidden_layers": 12,
    "num_negatives": 100,
    "output_hidden_size": 768,
    "proj_codevector_dim": 256,
    "replace_prob": 0.5,
    "tdnn_dilation": [
      1,
      2,
      3,
      1,
      1
    ],
    "tdnn_dim": [
      512,
      512,
      512,
      512,
      1500
    ],
    "tdnn_kernel": [
      5,
      3,
      3,
      1,
      1
    ],
    "tokenizer_class": "Wav2Vec2CTCTokenizer",
    "torch_dtype": "float32",
    "use_weighted_layer_sum": false,
    "vocab_size": 32,
    "xvector_output_dim": 512
  },
  "strides": [
    1,
    1
  ],
  "target_bandwidths": [
    0.5,
    1,
    1.5,
    2,
    4
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.56.0.dev0",
  "unit_kernel_size": 3
}