config.json

{
    "speechbrain_interface": "EncoderASR",
    "activation_dropout": 0.1,
    "apply_spec_augment": true,
    "architectures": [
        "Wav2Vec2Model"
    ],
    "attention_dropout": 0.1,
    "bos_token_id": 1,
    "conv_bias": true,
    "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": "sum",
    "ctc_zero_infinity": false,
    "do_stable_layer_norm": true,
    "eos_token_id": 2,
    "feat_extract_activation": "gelu",
    "feat_extract_dropout": 0.0,
    "feat_extract_norm": "layer",
    "feat_proj_dropout": 0.1,
    "final_dropout": 0.1,
    "gradient_checkpointing": false,
    "hidden_act": "gelu",
    "hidden_dropout": 0.1,
    "hidden_dropout_prob": 0.1,
    "hidden_size": 1024,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "layer_norm_eps": 1e-05,
    "layerdrop": 0.1,
    "mask_feature_length": 10,
    "mask_feature_prob": 0.0,
    "mask_time_length": 10,
    "mask_time_prob": 0.05,
    "model_type": "wav2vec2",
    "num_attention_heads": 16,
    "num_conv_pos_embedding_groups": 16,
    "num_conv_pos_embeddings": 128,
    "num_feat_extract_layers": 7,
    "num_hidden_layers": 24,
    "pad_token_id": 0,
    "transformers_version": "4.21.1",
    "vocab_size": 32
}