config.json

{
  "model_type": "tera_analy",
  "architectures": [
    "TeraAnaly"
  ],
  "auto_map": {
    "AutoConfig": "modeling_tera_analy.TeraAnalyConfig",
    "AutoModel": "modeling_tera_analy.TeraAnaly"
  },
  "encoder_config": {
    "activation_dropout": 0.0,
    "adapter_act": "relu",
    "adapter_kernel_size": 3,
    "adapter_stride": 2,
    "add_adapter": true,
    "apply_spec_augment": false,
    "architectures": [
      "Wav2Vec2BertForCTC"
    ],
    "attention_dropout": 0.0,
    "bos_token_id": 1,
    "classifier_proj_size": 768,
    "codevector_dim": 768,
    "conformer_conv_dropout": 0.1,
    "contrastive_logits_temperature": 0.1,
    "conv_depthwise_kernel_size": 31,
    "ctc_loss_reduction": "mean",
    "ctc_zero_infinity": true,
    "diversity_loss_weight": 0.1,
    "dtype": "float32",
    "eos_token_id": 2,
    "feat_proj_dropout": 0.0,
    "feat_quantizer_dropout": 0.0,
    "feature_projection_input_dim": 160,
    "final_dropout": 0.1,
    "hidden_act": "swish",
    "hidden_dropout": 0.0,
    "hidden_size": 1024,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "layer_norm_eps": 1e-05,
    "layerdrop": 0.0,
    "left_max_position_embeddings": 64,
    "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_prob": 0.0,
    "max_source_positions": 5000,
    "model_type": "wav2vec2-bert",
    "num_adapter_layers": 1,
    "num_attention_heads": 16,
    "num_codevector_groups": 2,
    "num_codevectors_per_group": 320,
    "num_hidden_layers": 24,
    "num_negatives": 100,
    "output_hidden_size": 1024,
    "pad_token_id": 44,
    "position_embeddings_type": "relative_key",
    "proj_codevector_dim": 768,
    "right_max_position_embeddings": 8,
    "rotary_embedding_base": 10000,
    "tdnn_dilation": [
      1,
      2,
      3,
      1,
      1
    ],
    "tdnn_dim": [
      512,
      512,
      512,
      512,
      1500
    ],
    "tdnn_kernel": [
      5,
      3,
      3,
      1,
      1
    ],
    "transformers_version": "5.5.3",
    "use_intermediate_ffn_before_adapter": false,
    "use_weighted_layer_sum": false,
    "vocab_size": 47,
    "xvector_output_dim": 512
  },
  "vocab": {
    "[PAD]": 44,
    "[UNK]": 43,
    "|": 0,
    "а": 1,
    "б": 2,
    "в": 3,
    "г": 4,
    "д": 5,
    "е": 6,
    "ж": 7,
    "з": 8,
    "и": 9,
    "й": 10,
    "к": 11,
    "л": 12,
    "м": 13,
    "н": 14,
    "о": 15,
    "п": 16,
    "р": 17,
    "с": 18,
    "т": 19,
    "у": 20,
    "ф": 21,
    "х": 22,
    "ц": 23,
    "ч": 24,
    "ш": 25,
    "щ": 26,
    "ъ": 27,
    "ы": 28,
    "ь": 29,
    "э": 30,
    "ю": 31,
    "я": 32,
    "ё": 33,
    "ғ": 34,
    "ҙ": 35,
    "ҡ": 36,
    "ң": 37,
    "ҫ": 38,
    "ү": 39,
    "һ": 40,
    "ә": 41,
    "ө": 42
  },
  "global_layers": [
    4,
    8,
    16,
    24
  ],
  "use_prosody_features": true,
  "labels": {
    "emotion": [
      "neutral",
      "angry",
      "positive",
      "sad",
      "other"
    ],
    "gender": [
      "female",
      "male",
      "child"
    ]
  },
  "ctc": {
    "layer": 16,
    "blank": 44,
    "hidden_size": 1024,
    "output_size": 47
  },
  "heads": {
    "emotion": {
      "dimension": 8200,
      "widths": [
        256
      ]
    },
    "age": {
      "dimension": 8360,
      "widths": [
        128
      ],
      "frames": [
        {
          "layer": 8,
          "width": 256,
          "projection_dim": 64,
          "global_dim": 8360,
          "frame_stride": 2
        }
      ],
      "blend_weight": 0.75
    },
    "gender": {
      "dimension": 8200,
      "widths": [
        128
      ],
      "frames": [
        {
          "layer": 8,
          "width": 256,
          "projection_dim": 64,
          "global_dim": 8360,
          "frame_stride": 2
        }
      ],
      "blend_weight": 1.0
    },
    "stress": {
      "dimension": 3085,
      "widths": [
        1024
      ],
      "layer": 16
    }
  },
  "source": {
    "encoder": "AigizK/w2v-bert-2.0-bashkort-russian-omnivoice",
    "encoder_revision": "e4c4278904c6359e9ac769cf04575be68f99ed4e",
    "model_fingerprint": "111dc574069315e437a08a5708e50d86a249a0830de40748b2cb32567d1154b0",
    "original_heads_sha256": "3da1e89e531e306481eac8d17222d4024d2f03f6234f5f106740365c41a96b12",
    "original_ctc_sha256": "a9ed240881a46352415d9eb6f5e78bcd32a19186b3e4f42fdfdece0856791b02",
    "encoder_finetuned": false
  }
}