config.json

{
  "_name_or_path": "waveletdeboshir/whisper-base-ser-ru-dusha",
  "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,
  "num_labels": 5,
  "d_model": 512,
  "dropout": 0.0,
  "encoder_attention_heads": 8,
  "encoder_ffn_dim": 2048,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 6,
  "finetuning_task": "audio-classification",
  "id2label": {
    "0": "angry",
    "1": "sad",
    "2": "neutral",
    "3": "positive",
    "4": "other"
  },
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "label2id": {
    "angry": "0",
    "sad": "1",
    "neutral": "2",
    "positive": "3",
    "other": "4"
  },
  "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": 6,
  "num_mel_bins": 80,
  "scale_embedding": false,
  "torch_dtype": "float32",
  "transformers_version": "4.46.3",
  "use_cache": true,
  "use_weighted_layer_sum": false,
  "vocab_size": 51865
}