config.json
| 1 | { |
| 2 | "_name_or_path": "facebook/hubert-large-ls960-ft", |
| 3 | "activation_dropout": 0.1, |
| 4 | "apply_spec_augment": true, |
| 5 | "architectures": [ |
| 6 | "HubertForSequenceClassification" |
| 7 | ], |
| 8 | "attention_dropout": 0.1, |
| 9 | "bos_token_id": 1, |
| 10 | "classifier_proj_size": 256, |
| 11 | "conv_bias": true, |
| 12 | "conv_dim": [ |
| 13 | 512, |
| 14 | 512, |
| 15 | 512, |
| 16 | 512, |
| 17 | 512, |
| 18 | 512, |
| 19 | 512 |
| 20 | ], |
| 21 | "conv_kernel": [ |
| 22 | 10, |
| 23 | 3, |
| 24 | 3, |
| 25 | 3, |
| 26 | 3, |
| 27 | 2, |
| 28 | 2 |
| 29 | ], |
| 30 | "conv_stride": [ |
| 31 | 5, |
| 32 | 2, |
| 33 | 2, |
| 34 | 2, |
| 35 | 2, |
| 36 | 2, |
| 37 | 2 |
| 38 | ], |
| 39 | "ctc_loss_reduction": "sum", |
| 40 | "ctc_zero_infinity": false, |
| 41 | "diversity_loss_weight": 0.1, |
| 42 | "do_stable_layer_norm": true, |
| 43 | "eos_token_id": 2, |
| 44 | "feat_extract_activation": "gelu", |
| 45 | "feat_extract_dropout": 0.0, |
| 46 | "feat_extract_norm": "layer", |
| 47 | "feat_proj_dropout": 0.1, |
| 48 | "feat_proj_layer_norm": true, |
| 49 | "final_dropout": 0.1, |
| 50 | "gradient_checkpointing": false, |
| 51 | "hidden_act": "gelu", |
| 52 | "hidden_dropout": 0.1, |
| 53 | "hidden_dropout_prob": 0.1, |
| 54 | "hidden_size": 1024, |
| 55 | "id2label": { |
| 56 | "0": "neutral", |
| 57 | "1": "angry", |
| 58 | "2": "positive", |
| 59 | "3": "sad", |
| 60 | "4": "other" |
| 61 | }, |
| 62 | "initializer_range": 0.02, |
| 63 | "intermediate_size": 4096, |
| 64 | "label2id": { |
| 65 | "neutral": 0, |
| 66 | "angry": 1, |
| 67 | "positive": 2, |
| 68 | "sad": 3, |
| 69 | "other": 4 |
| 70 | }, |
| 71 | "layer_norm_eps": 1e-05, |
| 72 | "layerdrop": 0.1, |
| 73 | "mask_feature_length": 10, |
| 74 | "mask_feature_min_masks": 0, |
| 75 | "mask_feature_prob": 0.0, |
| 76 | "mask_time_length": 10, |
| 77 | "mask_time_min_masks": 2, |
| 78 | "mask_time_prob": 0.05, |
| 79 | "model_type": "hubert", |
| 80 | "num_attention_heads": 16, |
| 81 | "num_conv_pos_embedding_groups": 16, |
| 82 | "num_conv_pos_embeddings": 128, |
| 83 | "num_feat_extract_layers": 7, |
| 84 | "num_hidden_layers": 24, |
| 85 | "pad_token_id": 0, |
| 86 | "torch_dtype": "float32", |
| 87 | "transformers_version": "4.30.2", |
| 88 | "use_weighted_layer_sum": false, |
| 89 | "vocab_size": 32 |
| 90 | } |
| 91 | |