config.json

{
  "model_type": "gigaam",
  "model_name": "v3_rnnt",
  "sample_rate": 16000,
  "preprocessor": {
    "sample_rate": 16000,
    "features": 64,
    "win_length": 320,
    "hop_length": 160,
    "n_fft": 320,
    "center": false
  },
  "encoder": {
    "feat_in": 64,
    "n_layers": 16,
    "d_model": 768,
    "subsampling": "conv1d",
    "subs_kernel_size": 5,
    "subsampling_factor": 4,
    "ff_expansion_factor": 4,
    "self_attention_model": "rotary",
    "pos_emb_max_len": 5000,
    "n_heads": 16,
    "conv_kernel_size": 5,
    "conv_norm_type": "layer_norm"
  },
  "head_type": "rnnt",
  "head": {
    "decoder": {
      "pred_hidden": 320,
      "pred_rnn_layers": 1,
      "num_classes": 34
    },
    "joint": {
      "enc_hidden": 768,
      "pred_hidden": 320,
      "joint_hidden": 320,
      "num_classes": 34
    }
  },
  "vocabulary": [
    " ",
    "а",
    "б",
    "в",
    "г",
    "д",
    "е",
    "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"
  ],
  "tokenizer_model": "tokenizer.model"
}