Hugging Face's logo

ylacombe
/
accent-classifier

Audio Classification
Transformers
Safetensors
wav2vec2
Inference Endpoints
Model card Files Community
1
accent-classifier
File size: 3,350 Bytes 
37951de
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
 
{
  "_name_or_path": "/fsx/yoach/accent_classification_final_output/",
  "activation_dropout": 0.0,
  "adapter_attn_dim": 16,
  "adapter_kernel_size": 3,
  "adapter_stride": 2,
  "add_adapter": false,
  "apply_spec_augment": true,
  "architectures": [
    "Wav2Vec2ForSequenceClassification"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "classifier_proj_size": 1024,
  "codevector_dim": 1024,
  "contrastive_logits_temperature": 0.1,
  "conv_bias": true,
  "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": "mean",
  "ctc_zero_infinity": false,
  "diversity_loss_weight": 0.1,
  "do_stable_layer_norm": true,
  "eos_token_id": 2,
  "feat_extract_activation": "gelu",
  "feat_extract_dropout": 0.0,
  "feat_extract_norm": "layer",
  "feat_proj_dropout": 0.0,
  "feat_quantizer_dropout": 0.0,
  "final_dropout": 0.0,
  "finetuning_task": "audio-classification",
  "hidden_act": "gelu",
  "hidden_dropout": 0.0,
  "hidden_size": 1280,
  "id2label": {
    "0": "American",
    "1": "Australian",
    "2": "Canadian",
    "3": "Chinese",
    "4": "Czech",
    "5": "Dutch",
    "6": "Eastern european",
    "7": "English",
    "8": "Finnish",
    "9": "French",
    "10": "German",
    "11": "Hungarian",
    "12": "Indian",
    "13": "Irish",
    "14": "Italian",
    "15": "Jamaican",
    "16": "Latin american",
    "17": "Malaysian",
    "18": "New zealand",
    "19": "Polish",
    "20": "Romanian",
    "21": "Scottish",
    "22": "Singaporean",
    "23": "Slovak",
    "24": "South african",
    "25": "Spanish",
    "26": "Welsh"
  },
  "initializer_range": 0.02,
  "intermediate_size": 5120,
  "label2id": {
    "American": "0",
    "Australian": "1",
    "Canadian": "2",
    "Chinese": "3",
    "Czech": "4",
    "Dutch": "5",
    "Eastern european": "6",
    "English": "7",
    "Finnish": "8",
    "French": "9",
    "German": "10",
    "Hungarian": "11",
    "Indian": "12",
    "Irish": "13",
    "Italian": "14",
    "Jamaican": "15",
    "Latin american": "16",
    "Malaysian": "17",
    "New zealand": "18",
    "Polish": "19",
    "Romanian": "20",
    "Scottish": "21",
    "Singaporean": "22",
    "Slovak": "23",
    "South african": "24",
    "Spanish": "25",
    "Welsh": "26"
  },
  "layer_norm_eps": 1e-05,
  "layerdrop": 0.0,
  "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": "wav2vec2",
  "num_adapter_layers": 3,
  "num_attention_heads": 16,
  "num_codevector_groups": 2,
  "num_codevectors_per_group": 320,
  "num_conv_pos_embedding_groups": 16,
  "num_conv_pos_embeddings": 128,
  "num_feat_extract_layers": 7,
  "num_hidden_layers": 48,
  "num_negatives": 100,
  "output_hidden_size": 1280,
  "pad_token_id": 0,
  "proj_codevector_dim": 1024,
  "tdnn_dilation": [
    1,
    2,
    3,
    1,
    1
  ],
  "tdnn_dim": [
    512,
    512,
    512,
    512,
    1500
  ],
  "tdnn_kernel": [
    5,
    3,
    3,
    1,
    1
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.40.2",
  "use_weighted_layer_sum": false,
  "vocab_size": 154,
  "xvector_output_dim": 512
}