{ "_name_or_path": "./Fine_tuned_Wav2Vec2/checkpoint-496", "activation_dropout": 0.0, "adapter_attn_dim": null, "adapter_kernel_size": 3, "adapter_stride": 2, "add_adapter": false, "apply_spec_augment": true, "architectures": [ "Wav2Vec2ForSequenceClassification" ], "attention_dropout": 0.1, "bos_token_id": 1, "classifier_proj_size": 256, "codevector_dim": 256, "contrastive_logits_temperature": 0.1, "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": "sum", "ctc_zero_infinity": false, "diversity_loss_weight": 0.1, "do_stable_layer_norm": false, "eos_token_id": 2, "feat_extract_activation": "gelu", "feat_extract_norm": "group", "feat_proj_dropout": 0.1, "feat_quantizer_dropout": 0.0, "final_dropout": 0.0, "freeze_feat_extract_train": true, "hidden_act": "gelu", "hidden_dropout": 0.1, "hidden_size": 768, "id2label": { "0": "id10270", "1": "id10271", "2": "id10272", "3": "id10273", "4": "id10274", "5": "id10275", "6": "id10276", "7": "id10277", "8": "id10278", "9": "id10279", "10": "id10280", "11": "id10281", "12": "id10282", "13": "id10283", "14": "id10284", "15": "id10285", "16": "id10286", "17": "id10287", "18": "id10288", "19": "id10289", "20": "id10290", "21": "id10291", "22": "id10292", "23": "id10293", "24": "id10294", "25": "id10295", "26": "id10296", "27": "id10297", "28": "id10298", "29": "id10299", "30": "id10300", "31": "id10301", "32": "id10302", "33": "id10303", "34": "id10304", "35": "id10305", "36": "id10306", "37": "id10307", "38": "id10308", "39": "id10309" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "id10270": 0, "id10271": 1, "id10272": 2, "id10273": 3, "id10274": 4, "id10275": 5, "id10276": 6, "id10277": 7, "id10278": 8, "id10279": 9, "id10280": 10, "id10281": 11, "id10282": 12, "id10283": 13, "id10284": 14, "id10285": 15, "id10286": 16, "id10287": 17, "id10288": 18, "id10289": 19, "id10290": 20, "id10291": 21, "id10292": 22, "id10293": 23, "id10294": 24, "id10295": 25, "id10296": 26, "id10297": 27, "id10298": 28, "id10299": 29, "id10300": 30, "id10301": 31, "id10302": 32, "id10303": 33, "id10304": 34, "id10305": 35, "id10306": 36, "id10307": 37, "id10308": 38, "id10309": 39 }, "layer_norm_eps": 1e-05, "layerdrop": 0.0, "mask_channel_length": 10, "mask_channel_min_space": 1, "mask_channel_other": 0.0, "mask_channel_prob": 0.0, "mask_channel_selection": "static", "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_min_space": 1, "mask_time_other": 0.0, "mask_time_prob": 0.05, "mask_time_selection": "static", "model_type": "wav2vec2", "no_mask_channel_overlap": false, "no_mask_time_overlap": false, "num_adapter_layers": 3, "num_attention_heads": 12, "num_codevector_groups": 2, "num_codevectors_per_group": 320, "num_conv_pos_embedding_groups": 16, "num_conv_pos_embeddings": 128, "num_feat_extract_layers": 7, "num_hidden_layers": 12, "num_negatives": 100, "output_hidden_size": 768, "pad_token_id": 0, "proj_codevector_dim": 256, "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": "4.48.3", "use_weighted_layer_sum": false, "vocab_size": 32, "xvector_output_dim": 512 }