{ "activation_dropout": 0.0, "adapter_act": "relu", "adapter_kernel_size": 3, "adapter_stride": 2, "add_adapter": true, "apply_spec_augment": true, "architectures": [ "Wav2Vec2BertForMultilevelCTC" ], "attention_dropout": 0.0, "bos_token_id": 1, "classifier_proj_size": 768, "conformer_conv_dropout": 0.1, "conv_depthwise_kernel_size": 31, "ctc_loss_reduction": "mean", "ctc_zero_infinity": false, "eos_token_id": 2, "feat_proj_dropout": 0.0, "feature_projection_input_dim": 160, "final_dropout": 0.1, "hidden_act": "swish", "hidden_dropout": 0.0, "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 4096, "layer_norm_eps": 1e-05, "layerdrop": 0.0, "left_max_position_embeddings": 64, "level_to_loss_weight": { "ghonna": 0.06, "hams_or_jahr": 0.06, "istitala": 0.06, "itbaq": 0.06, "phonemes": 0.4, "qalqla": 0.06, "safeer": 0.06, "shidda_or_rakhawa": 0.06, "tafashie": 0.06, "tafkheem_or_taqeeq": 0.06, "tikraar": 0.06 }, "level_to_vocab_size": { "ghonna": 3, "hams_or_jahr": 3, "istitala": 3, "itbaq": 3, "phonemes": 43, "qalqla": 3, "safeer": 3, "shidda_or_rakhawa": 4, "tafashie": 3, "tafkheem_or_taqeeq": 3, "tikraar": 3 }, "mask_feature_length": 10, "mask_feature_min_masks": 0, "mask_feature_prob": 0.0, "mask_time_length": 10, "mask_time_min_masks": 2, "mask_time_prob": 0.0, "max_source_positions": 5000, "model_type": "multi_level_ctc", "num_adapter_layers": 1, "num_attention_heads": 16, "num_hidden_layers": 24, "output_hidden_size": 1024, "pad_token_id": 0, "position_embeddings_type": "relative_key", "right_max_position_embeddings": 8, "rotary_embedding_base": 10000, "tdnn_dilation": [ 1, 2, 3, 1, 1 ], "tdnn_dim": [ 512, 512, 512, 512, 1500 ], "tdnn_kernel": [ 5, 3, 3, 1, 1 ], "torch_dtype": "float32", "transformers_version": "4.55.0", "use_intermediate_ffn_before_adapter": false, "use_weighted_layer_sum": false, "xvector_output_dim": 512 }