{ "BertModel": { "_name_or_path": "bert-base-uncased", "add_cross_attention": false, "architectures": [ "BertForMaskedLM" ], "attention_probs_dropout_prob": 0.1, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "classifier_dropout": null, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 3072, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-12, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 512, "min_length": 0, "model_type": "bert", "no_repeat_ngram_size": 0, "num_attention_heads": 12, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 12, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 0, "position_embedding_type": "absolute", "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "transformers_version": "4.28.1", "type_vocab_size": 2, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 30522 }, "Wav2Vec2Model": { "_name_or_path": "jonatasgrosman/wav2vec2-large-xlsr-53-english", "activation_dropout": 0.05, "adapter_kernel_size": 3, "adapter_stride": 2, "add_adapter": false, "add_cross_attention": false, "apply_spec_augment": true, "architectures": [ "Wav2Vec2ForCTC" ], "attention_dropout": 0.1, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 1, "chunk_size_feed_forward": 0, "classifier_proj_size": 256, "codevector_dim": 256, "contrastive_logits_temperature": 0.1, "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 ], "cross_attention_hidden_size": null, "ctc_loss_reduction": "mean", "ctc_zero_infinity": true, "decoder_start_token_id": null, "diversity_loss_weight": 0.1, "diversity_penalty": 0.0, "do_sample": false, "do_stable_layer_norm": true, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 2, "exponential_decay_length_penalty": null, "feat_extract_activation": "gelu", "feat_extract_dropout": 0.0, "feat_extract_norm": "layer", "feat_proj_dropout": 0.05, "feat_quantizer_dropout": 0.0, "final_dropout": 0.0, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "gelu", "hidden_dropout": 0.05, "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-05, "layerdrop": 0.05, "length_penalty": 1.0, "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", "max_length": 20, "min_length": 0, "model_type": "wav2vec2", "no_repeat_ngram_size": 0, "num_adapter_layers": 3, "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "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": 24, "num_negatives": 100, "num_return_sequences": 1, "output_attentions": false, "output_hidden_size": 1024, "output_hidden_states": false, "output_scores": false, "pad_token_id": 0, "prefix": null, "problem_type": null, "proj_codevector_dim": 256, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "tdnn_dilation": [ 1, 2, 3, 1, 1 ], "tdnn_dim": [ 512, 512, 512, 512, 1500 ], "tdnn_kernel": [ 5, 3, 3, 1, 1 ], "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "transformers_version": "4.28.1", "typical_p": 1.0, "use_bfloat16": false, "use_weighted_layer_sum": false, "vocab_size": 33, "xvector_output_dim": 512 }, "architectures": [ "Wav2Vec2BertFusionForSequenceClassification" ], "auto_map": { "AutoConfig": "audio_text_multimodal.Wav2Vec2BertConfig", "AutoModel": "audio_text_multimodal.Wav2Vec2BertFusionForSequenceClassification" }, "gradient_checkpointing": true, "id2label": { "0": "ang", "1": "dis", "2": "exc", "3": "fea", "4": "fru", "5": "hap", "6": "neu", "7": "oth", "8": "sad", "9": "sur" }, "kernel_size": 1, "label2id": { "ang": 0, "dis": 1, "exc": 2, "fea": 3, "fru": 4, "hap": 5, "neu": 6, "oth": 7, "sad": 8, "sur": 9 }, "num_heads": 8, "pooling_mode": "mean", "problem_type": "single_label_classification", "torch_dtype": "float32", "transformers_version": "4.28.1" }