{
  "_attn_implementation_autoset": true,
  "architectures": [
    "AnuvaniLidForAudioClassification"
  ],
  "auto_map": {
    "AutoConfig": "configuration_anuvani_lid.AnuvaniLidConfig",
    "AutoModelForAudioClassification": "modeling_anuvani_lid.AnuvaniLidForAudioClassification"
  },
  "conv_kernel_size": 31,
  "d_ff": 2048,
  "d_model": 512,
  "hop_length": 160,
  "id2label": {
    "0": "assamese",
    "1": "bengali",
    "2": "bodo",
    "3": "dogri",
    "4": "english",
    "5": "gujarati",
    "6": "hindi",
    "7": "kannada",
    "8": "kashmiri",
    "9": "konkani",
    "10": "maithili",
    "11": "malayalam",
    "12": "manipuri",
    "13": "marathi",
    "14": "nepali",
    "15": "odia",
    "16": "punjabi",
    "17": "sanskrit",
    "18": "santali",
    "19": "sindhi",
    "20": "tamil",
    "21": "telugu",
    "22": "urdu"
  },
  "label2id": {
    "assamese": 0,
    "bengali": 1,
    "bodo": 2,
    "dogri": 3,
    "english": 4,
    "gujarati": 5,
    "hindi": 6,
    "kannada": 7,
    "kashmiri": 8,
    "konkani": 9,
    "maithili": 10,
    "malayalam": 11,
    "manipuri": 12,
    "marathi": 13,
    "nepali": 14,
    "odia": 15,
    "punjabi": 16,
    "sanskrit": 17,
    "santali": 18,
    "sindhi": 19,
    "tamil": 20,
    "telugu": 21,
    "urdu": 22
  },
  "layer_agg_per_channel_scale": false,
  "layer_agg_pre_layernorm": false,
  "layer_aggregation": true,
  "model_type": "anuvani_lid",
  "n_fft": 512,
  "n_heads": 8,
  "n_layers": 17,
  "n_mels": 80,
  "pad_to": 16,
  "pos_emb_max_len": 5000,
  "preemph": 0.97,
  "sample_rate": 16000,
  "subsampling_conv_channels": 512,
  "transformers_version": "4.46.3",
  "win_length": 400
}