Hugging Face's logo

firdhokk
/
speech-emotion-recognition-with-openai-whisper-large-v3

Audio Classification
Transformers
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Community
1
speech-emotion-recognition-with-openai-whisper-large-v3
File size: 1,559 Bytes 
8671a8f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
 
{
  "_name_or_path": "openai/whisper-large-v3",
  "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": 1280,
  "decoder_attention_heads": 20,
  "decoder_ffn_dim": 5120,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 32,
  "decoder_start_token_id": 50258,
  "dropout": 0.0,
  "encoder_attention_heads": 20,
  "encoder_ffn_dim": 5120,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 32,
  "eos_token_id": 50257,
  "id2label": {
    "0": "angry",
    "1": "disgust",
    "2": "fearful",
    "3": "happy",
    "4": "neutral",
    "5": "sad",
    "6": "surprised"
  },
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "label2id": {
    "angry": 0,
    "disgust": 1,
    "fearful": 2,
    "happy": 3,
    "neutral": 4,
    "sad": 5,
    "surprised": 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": 32,
  "num_mel_bins": 128,
  "pad_token_id": 50256,
  "scale_embedding": false,
  "torch_dtype": "float32",
  "transformers_version": "4.44.2",
  "use_cache": true,
  "use_weighted_layer_sum": false,
  "vocab_size": 51866
}