| { | |
| "_name_or_path": "shhossain/whisper-tiny-bn", | |
| "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": null, | |
| "id2label": { | |
| "0": "ANGRY", | |
| "1": "DISGUST", | |
| "2": "FEAR", | |
| "3": "HAPPY", | |
| "4": "NEUTRAL", | |
| "5": "SAD", | |
| "6": "SURPRISE" | |
| }, | |
| "init_std": 0.02, | |
| "is_encoder_decoder": true, | |
| "label2id": { | |
| "ANGRY": "0", | |
| "DISGUST": "1", | |
| "FEAR": "2", | |
| "HAPPY": "3", | |
| "NEUTRAL": "4", | |
| "SAD": "5", | |
| "SURPRISE": "6" | |
| }, | |
| "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": [], | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.33.2", | |
| "use_cache": true, | |
| "use_weighted_layer_sum": false, | |
| "vocab_size": 51865 | |
| } | |