| { | |
| "_name_or_path": "facebook/hubert-base-ls960", | |
| "activation_dropout": 0.1, | |
| "apply_spec_augment": true, | |
| "architectures": [ | |
| "HubertForSequenceClassification" | |
| ], | |
| "attention_dropout": 0.1, | |
| "bos_token_id": 1, | |
| "classifier_proj_size": 256, | |
| "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, | |
| "do_stable_layer_norm": false, | |
| "eos_token_id": 2, | |
| "feat_extract_activation": "gelu", | |
| "feat_extract_dropout": 0.0, | |
| "feat_extract_norm": "group", | |
| "feat_proj_dropout": 0.1, | |
| "feat_proj_layer_norm": true, | |
| "final_dropout": 0.1, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout": 0.1, | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "bed", | |
| "1": "bird", | |
| "10": "house", | |
| "11": "left", | |
| "12": "marvin", | |
| "13": "nine", | |
| "14": "no", | |
| "15": "off", | |
| "16": "on", | |
| "17": "one", | |
| "18": "right", | |
| "19": "seven", | |
| "2": "cat", | |
| "20": "sheila", | |
| "21": "silence", | |
| "22": "six", | |
| "23": "stop", | |
| "24": "three", | |
| "25": "tree", | |
| "26": "two", | |
| "27": "up", | |
| "28": "wow", | |
| "29": "yes", | |
| "3": "dog", | |
| "30": "zero", | |
| "4": "down", | |
| "5": "eight", | |
| "6": "five", | |
| "7": "four", | |
| "8": "go", | |
| "9": "happy" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "bed": "0", | |
| "bird": "1", | |
| "cat": "2", | |
| "dog": "3", | |
| "down": "4", | |
| "eight": "5", | |
| "five": "6", | |
| "four": "7", | |
| "go": "8", | |
| "happy": "9", | |
| "house": "10", | |
| "left": "11", | |
| "marvin": "12", | |
| "nine": "13", | |
| "no": "14", | |
| "off": "15", | |
| "on": "16", | |
| "one": "17", | |
| "right": "18", | |
| "seven": "19", | |
| "sheila": "20", | |
| "silence": "21", | |
| "six": "22", | |
| "stop": "23", | |
| "three": "24", | |
| "tree": "25", | |
| "two": "26", | |
| "up": "27", | |
| "wow": "28", | |
| "yes": "29", | |
| "zero": "30" | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "layerdrop": 0.1, | |
| "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_prob": 0.05, | |
| "model_type": "hubert", | |
| "num_attention_heads": 12, | |
| "num_conv_pos_embedding_groups": 16, | |
| "num_conv_pos_embeddings": 128, | |
| "num_feat_extract_layers": 7, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "tokenizer_class": "Wav2Vec2CTCTokenizer", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.40.1", | |
| "use_weighted_layer_sum": false, | |
| "vocab_size": 32 | |
| } | |