config.json

{
  "architectures": [
    "ToneForCTC"
  ],
  "ctc_loss_reduction": "mean",
  "ctc_zero_infinity": true,
  "decoder_params": {
    "feat_in": 384,
    "vocabulary": [
      "а",
      "б",
      "в",
      "г",
      "д",
      "е",
      "ё",
      "ж",
      "з",
      "и",
      "й",
      "к",
      "л",
      "м",
      "н",
      "о",
      "п",
      "р",
      "с",
      "т",
      "у",
      "ф",
      "х",
      "ц",
      "ч",
      "ш",
      "щ",
      "ъ",
      "ы",
      "ь",
      "э",
      "ю",
      "я",
      " "
    ]
  },
  "encoder_params": {
    "chunk_size": 10,
    "conv_kernel_size": 31,
    "d_model": 384,
    "dropout": 0.1,
    "dropout_att": 0.1,
    "feat_in": 64,
    "ff_expansion_factor": 4,
    "mhsa_state_size": 30,
    "mhsa_stateless_layers": 14,
    "n_heads": 8,
    "n_layers": 16,
    "reduction_factor": 2,
    "reduction_kernel_size": 3,
    "reduction_position": 6,
    "rope_dim": 32,
    "should_recompute_att_scores": [
      true,
      false,
      false,
      false,
      false,
      false,
      false,
      true,
      false,
      false,
      false,
      false,
      false,
      false,
      true,
      true
    ],
    "subsampling_conv_channels": [
      32,
      64
    ],
    "subsampling_kernel_size": [
      [
        11,
        21
      ],
      [
        11,
        11
      ]
    ],
    "subsampling_strides": [
      [
        1,
        1
      ],
      [
        3,
        1
      ]
    ],
    "upsample_position": 14
  },
  "feature_extraction_params": {
    "n_fft": 160,
    "n_mels": 64,
    "preemphasis_coefficient": 0.97,
    "sample_rate": 8000,
    "window_size": 0.02,
    "window_stride": 0.01
  },
  "pad_token_id": 34,
  "torch_dtype": "float32",
  "transformers_version": "4.41.2"
}