{
  "hidden_size": 768,
  "num_hidden_layers": 12,
  "num_attention_heads": 12,
  "intermediate_size": 3072,
  "hidden_dropout": 0.1,
  "attention_dropout": 0.1,
  "activation_dropout": 0.0,
  "layer_norm_eps": 1e-05,
  "feat_extract_norm": "group",
  "feat_extract_activation": "gelu",
  "feat_proj_dropout": 0.0,
  "use_rope": true,
  "rope_theta": 10000.0,
  "sample_rate": 16000,
  "teacher_model_name": "TuKoResearch/AuriStream100M_40Pred_BigAudioDataset_500k",
  "teacher_hidden_size": 768,
  "conv_dim": [
    512,
    512,
    512,
    512,
    512,
    512,
    512
  ],
  "conv_stride": [
    5,
    2,
    2,
    2,
    2,
    2,
    2
  ],
  "conv_kernel": [
    10,
    3,
    3,
    3,
    3,
    2,
    2
  ],
  "conv_bias": false,
  "model_type": "distilled_speech",
  "auto_map": {
    "AutoConfig": "configuration_distilled_speech.DistilledSpeechConfig",
    "AutoModel": "modeling_distilled_speech.DistilledSpeechModel"
  },
  "architectures": [
    "DistilledSpeechModel"
  ],
  "training_step": 100000
}