{
  "architectures": [
    "PhonoQForFeatureRecognition"
  ],
  "auto_map": {
    "AutoConfig": "configuration_phonoq.PhonoQConfig",
    "AutoModel": "modeling_phonoq.PhonoQForFeatureRecognition"
  },
  "conv_kernel_size": 31,
  "dropout": 0.1,
  "feature_names": [
    "silence",
    "stop",
    "nasal",
    "rhotic",
    "fricative",
    "affricate",
    "approximant",
    "lateral",
    "vowel",
    "high",
    "mid",
    "low",
    "front",
    "central",
    "back",
    "labial",
    "alveolar",
    "velar",
    "palatal",
    "postalveolar",
    "voiceless",
    "voiced"
  ],
  "ffn_expansion": 4,
  "hidden_dim": 512,
  "model_type": "phonoq",
  "num_heads": 4,
  "num_layers": 2,
  "relpos_max_distance": 128,
  "relpos_num_buckets": 32,
  "torch_dtype": "float32",
  "transformers_version": "4.51.3",
  "wav2vec_model_name": "facebook/wav2vec2-xlsr-53-espeak-cv-ft"
}