config.json

{
  "activation_dropout": 0.1,
  "apply_spec_augment": true,
  "architectures": [
    "SpeechJEPAModel"
  ],
  "attention_dropout": 0.1,
  "auto_map": {
    "AutoConfig": "configuration_speech_jepa.SpeechJEPAConfig",
    "AutoModel": "modeling_speech_jepa.SpeechJEPAModel",
    "AutoModelForCTC": "modeling_speech_jepa.SpeechJEPAForCTC"
  },
  "conv_bias": false,
  "conv_dim": [
    512,
    512,
    512,
    512,
    512,
    512,
    512
  ],
  "conv_kernel": [
    10,
    3,
    3,
    3,
    3,
    2,
    2
  ],
  "conv_stride": [
    5,
    2,
    2,
    2,
    2,
    2,
    2
  ],
  "ctc_loss_reduction": "mean",
  "ctc_zero_infinity": true,
  "dtype": "float32",
  "feat_extract_norm": "group",
  "final_dropout": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-06,
  "layerdrop": 0.05,
  "mask_feature_length": 64,
  "mask_feature_min_masks": 0,
  "mask_feature_prob": 0.0,
  "mask_time_length": 10,
  "mask_time_min_masks": 2,
  "mask_time_prob": 0.065,
  "max_position_embeddings": 8192,
  "model_type": "speech_jepa",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "rope_theta": 10000.0,
  "transformers_version": "5.2.0",
  "use_weighted_layer_sum": false,
  "vocab_size": 29
}