{ "_name_or_path": "facebook/wav2vec2-base", "activation_dropout": 0.0, "adapter_kernel_size": 3, "adapter_stride": 2, "add_adapter": false, "apply_spec_augment": true, "architectures": [ "Wav2Vec2ForPooledSequenceClassification" ], "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": "0", "1": "1", "10": "10", "11": "11", "12": "12", "13": "13", "14": "14", "15": "15", "16": "16", "17": "17", "18": "18", "19": "19", "2": "2", "20": "20", "21": "21", "22": "22", "23": "23", "24": "24", "25": "25", "26": "26", "27": "27", "28": "28", "29": "29", "3": "3", "30": "30", "31": "31", "32": "32", "33": "33", "34": "34", "35": "35", "36": "36", "37": "37", "38": "38", "39": "39", "4": "4", "40": "40", "41": "41", "42": "42", "43": "43", "44": "44", "45": "45", "46": "46", "47": "47", "48": "48", "49": "49", "5": "5", "50": "50", "51": "51", "52": "52", "53": "53", "54": "54", "55": "55", "56": "56", "57": "57", "58": "58", "59": "59", "6": "6", "60": "60", "61": "61", "62": "62", "63": "63", "64": "64", "65": "65", "66": "66", "67": "67", "68": "68", "69": "69", "7": "7", "70": "70", "71": "71", "72": "72", "73": "73", "74": "74", "75": "75", "76": "76", "77": "77", "78": "78", "79": "79", "8": "8", "80": "80", "81": "81", "82": "82", "83": "83", "84": "84", "85": "85", "86": "86", "87": "87", "88": "88", "89": "89", "9": "9", "90": "90", "91": "91", "92": "92", "93": "93", "94": "94", "95": "95", "96": "96", "97": "97", "98": "98", "99": "99" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "0": "0", "1": "1", "10": "10", "11": "11", "12": "12", "13": "13", "14": "14", "15": "15", "16": "16", "17": "17", "18": "18", "19": "19", "2": "2", "20": "20", "21": "21", "22": "22", "23": "23", "24": "24", "25": "25", "26": "26", "27": "27", "28": "28", "29": "29", "3": "3", "30": "30", "31": "31", "32": "32", "33": "33", "34": "34", "35": "35", "36": "36", "37": "37", "38": "38", "39": "39", "4": "4", "40": "40", "41": "41", "42": "42", "43": "43", "44": "44", "45": "45", "46": "46", "47": "47", "48": "48", "49": "49", "5": "5", "50": "50", "51": "51", "52": "52", "53": "53", "54": "54", "55": "55", "56": "56", "57": "57", "58": "58", "59": "59", "6": "6", "60": "60", "61": "61", "62": "62", "63": "63", "64": "64", "65": "65", "66": "66", "67": "67", "68": "68", "69": "69", "7": "7", "70": "70", "71": "71", "72": "72", "73": "73", "74": "74", "75": "75", "76": "76", "77": "77", "78": "78", "79": "79", "8": "8", "80": "80", "81": "81", "82": "82", "83": "83", "84": "84", "85": "85", "86": "86", "87": "87", "88": "88", "89": "89", "9": "9", "90": "90", "91": "91", "92": "92", "93": "93", "94": "94", "95": "95", "96": "96", "97": "97", "98": "98", "99": "99" }, "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": "4.25.1", "use_weighted_layer_sum": false, "vocab_size": 32, "xvector_output_dim": 512 }