| { | |
| "_name_or_path": "openai/whisper-tiny", | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "apply_spec_augment": false, | |
| "architectures": [ | |
| "WhisperForAudioClassification" | |
| ], | |
| "attention_dropout": 0.0, | |
| "begin_suppress_tokens": [ | |
| 220, | |
| 50257 | |
| ], | |
| "bos_token_id": 50257, | |
| "classifier_proj_size": 256, | |
| "d_model": 384, | |
| "decoder_attention_heads": 6, | |
| "decoder_ffn_dim": 1536, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_layers": 4, | |
| "decoder_start_token_id": 50258, | |
| "dropout": 0.0, | |
| "encoder_attention_heads": 6, | |
| "encoder_ffn_dim": 1536, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 4, | |
| "eos_token_id": 50257, | |
| "forced_decoder_ids": [ | |
| [ | |
| 1, | |
| 50259 | |
| ], | |
| [ | |
| 2, | |
| 50359 | |
| ], | |
| [ | |
| 3, | |
| 50363 | |
| ] | |
| ], | |
| "id2label": { | |
| "0": "yes", | |
| "1": "no", | |
| "10": "zero", | |
| "11": "one", | |
| "12": "two", | |
| "13": "three", | |
| "14": "four", | |
| "15": "five", | |
| "16": "six", | |
| "17": "seven", | |
| "18": "eight", | |
| "19": "nine", | |
| "2": "up", | |
| "20": "bed", | |
| "21": "bird", | |
| "22": "cat", | |
| "23": "dog", | |
| "24": "happy", | |
| "25": "house", | |
| "26": "marvin", | |
| "27": "sheila", | |
| "28": "tree", | |
| "29": "wow", | |
| "3": "down", | |
| "30": "backward", | |
| "31": "forward", | |
| "32": "follow", | |
| "33": "learn", | |
| "34": "visual", | |
| "35": "_silence_", | |
| "4": "left", | |
| "5": "right", | |
| "6": "on", | |
| "7": "off", | |
| "8": "stop", | |
| "9": "go" | |
| }, | |
| "init_std": 0.02, | |
| "is_encoder_decoder": true, | |
| "label2id": { | |
| "_silence_": "35", | |
| "backward": "30", | |
| "bed": "20", | |
| "bird": "21", | |
| "cat": "22", | |
| "dog": "23", | |
| "down": "3", | |
| "eight": "18", | |
| "five": "15", | |
| "follow": "32", | |
| "forward": "31", | |
| "four": "14", | |
| "go": "9", | |
| "happy": "24", | |
| "house": "25", | |
| "learn": "33", | |
| "left": "4", | |
| "marvin": "26", | |
| "nine": "19", | |
| "no": "1", | |
| "off": "7", | |
| "on": "6", | |
| "one": "11", | |
| "right": "5", | |
| "seven": "17", | |
| "sheila": "27", | |
| "six": "16", | |
| "stop": "8", | |
| "three": "13", | |
| "tree": "28", | |
| "two": "12", | |
| "up": "2", | |
| "visual": "34", | |
| "wow": "29", | |
| "yes": "0", | |
| "zero": "10" | |
| }, | |
| "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, | |
| "max_length": 448, | |
| "max_source_positions": 1500, | |
| "max_target_positions": 448, | |
| "median_filter_width": 7, | |
| "model_type": "whisper", | |
| "num_hidden_layers": 4, | |
| "num_mel_bins": 80, | |
| "pad_token_id": 50257, | |
| "scale_embedding": false, | |
| "suppress_tokens": [ | |
| 1, | |
| 2, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 14, | |
| 25, | |
| 26, | |
| 27, | |
| 28, | |
| 29, | |
| 31, | |
| 58, | |
| 59, | |
| 60, | |
| 61, | |
| 62, | |
| 63, | |
| 90, | |
| 91, | |
| 92, | |
| 93, | |
| 359, | |
| 503, | |
| 522, | |
| 542, | |
| 873, | |
| 893, | |
| 902, | |
| 918, | |
| 922, | |
| 931, | |
| 1350, | |
| 1853, | |
| 1982, | |
| 2460, | |
| 2627, | |
| 3246, | |
| 3253, | |
| 3268, | |
| 3536, | |
| 3846, | |
| 3961, | |
| 4183, | |
| 4667, | |
| 6585, | |
| 6647, | |
| 7273, | |
| 9061, | |
| 9383, | |
| 10428, | |
| 10929, | |
| 11938, | |
| 12033, | |
| 12331, | |
| 12562, | |
| 13793, | |
| 14157, | |
| 14635, | |
| 15265, | |
| 15618, | |
| 16553, | |
| 16604, | |
| 18362, | |
| 18956, | |
| 20075, | |
| 21675, | |
| 22520, | |
| 26130, | |
| 26161, | |
| 26435, | |
| 28279, | |
| 29464, | |
| 31650, | |
| 32302, | |
| 32470, | |
| 36865, | |
| 42863, | |
| 47425, | |
| 49870, | |
| 50254, | |
| 50258, | |
| 50358, | |
| 50359, | |
| 50360, | |
| 50361, | |
| 50362 | |
| ], | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.36.0.dev0", | |
| "use_cache": true, | |
| "use_weighted_layer_sum": false, | |
| "vocab_size": 51865 | |
| } | |