| { | |
| "_name_or_path": "Aniemore/wavlm-emotion-russian-resd", | |
| "activation_dropout": 0.05, | |
| "adapter_kernel_size": 3, | |
| "adapter_stride": 2, | |
| "add_adapter": false, | |
| "apply_spec_augment": true, | |
| "architectures": [ | |
| "WavLMForSequenceClassification" | |
| ], | |
| "attention_dropout": 0.05, | |
| "bos_token_id": 1, | |
| "classifier_proj_size": 1024, | |
| "codevector_dim": 768, | |
| "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": true, | |
| "eos_token_id": 2, | |
| "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": 0.05, | |
| "finetuning_task": [ | |
| "wavlm_classification" | |
| ], | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout": 0.05, | |
| "hidden_size": 1024, | |
| "id2label": { | |
| "0": "anger", | |
| "1": "disgust", | |
| "2": "enthusiasm", | |
| "3": "fear", | |
| "4": "happiness", | |
| "5": "neutral", | |
| "6": "sadness" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "label2id": { | |
| "anger": 0, | |
| "disgust": 1, | |
| "enthusiasm": 2, | |
| "fear": 3, | |
| "happiness": 4, | |
| "neutral": 5, | |
| "sadness": 6 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "layerdrop": 0.05, | |
| "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_bucket_distance": 800, | |
| "model_type": "wavlm", | |
| "num_adapter_layers": 3, | |
| "num_attention_heads": 16, | |
| "num_buckets": 320, | |
| "num_codevector_groups": 2, | |
| "num_codevectors_per_group": 320, | |
| "num_conv_pos_embedding_groups": 16, | |
| "num_conv_pos_embeddings": 128, | |
| "num_ctc_classes": 80, | |
| "num_feat_extract_layers": 7, | |
| "num_hidden_layers": 24, | |
| "num_negatives": 100, | |
| "output_hidden_size": 1024, | |
| "pad_token_id": 0, | |
| "pooling_mode": "mean", | |
| "problem_type": "single_label_classification", | |
| "proj_codevector_dim": 768, | |
| "replace_prob": 0.5, | |
| "tdnn_dilation": [ | |
| 1, | |
| 2, | |
| 3, | |
| 1, | |
| 1 | |
| ], | |
| "tdnn_dim": [ | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 1500 | |
| ], | |
| "tdnn_kernel": [ | |
| 5, | |
| 3, | |
| 3, | |
| 1, | |
| 1 | |
| ], | |
| "tokenizer_class": "Wav2Vec2CTCTokenizer", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.25.1", | |
| "use_weighted_layer_sum": false, | |
| "vocab_size": 40, | |
| "xvector_output_dim": 512 | |
| } | |