Hugging Face's logo

walston
/
GenAID

Audio Classification
Transformers
Safetensors
Chinese
genaid
feature-extraction
accent-recognition
speaker-disentanglement
wav2vec2
custom_code
Model card Files
xet
 Community
GenAID
File size: 3,385 Bytes
378eaeb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "accent_labels": [
    "north",
    "Sichuan",
    "Guangdong",
    "south",
    "Henan",
    "Shanghai",
    "Wuhan",
    "Tianjin",
    "singapore"
  ],
  "architectures": [
    "GenAIDModel"
  ],
  "auto_map": {
    "AutoConfig": "configuration_genaid.GenAIDConfig",
    "AutoModel": "modeling_genaid.GenAIDModel"
  },
  "bottleneck_dim": 64,
  "encoder_config": {
    "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
    "activation_dropout": 0.0,
    "adapter_attn_dim": null,
    "adapter_kernel_size": 3,
    "adapter_stride": 2,
    "add_adapter": false,
    "apply_spec_augment": true,
    "architectures": [
      "Wav2Vec2ForPreTraining"
    ],
    "attention_dropout": 0.1,
    "bos_token_id": 1,
    "chunk_size_feed_forward": 0,
    "classifier_proj_size": 256,
    "codevector_dim": 768,
    "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": "sum",
    "ctc_zero_infinity": false,
    "diversity_loss_weight": 0.1,
    "do_stable_layer_norm": true,
    "dtype": null,
    "eos_token_id": 2,
    "feat_extract_activation": "gelu",
    "feat_extract_dropout": 0.0,
    "feat_extract_norm": "layer",
    "feat_proj_dropout": 0.1,
    "feat_quantizer_dropout": 0.0,
    "final_dropout": 0.0,
    "gradient_checkpointing": false,
    "hidden_act": "gelu",
    "hidden_dropout": 0.1,
    "hidden_size": 1024,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-05,
    "layerdrop": 0.1,
    "mask_channel_length": 10,
    "mask_channel_min_space": 1,
    "mask_channel_other": 0.0,
    "mask_channel_prob": 0.0,
    "mask_channel_selection": "static",
    "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_min_space": 1,
    "mask_time_other": 0.0,
    "mask_time_prob": 0.075,
    "mask_time_selection": "static",
    "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": 24,
    "num_negatives": 100,
    "output_attentions": false,
    "output_hidden_size": 1024,
    "output_hidden_states": false,
    "pad_token_id": 0,
    "problem_type": null,
    "proj_codevector_dim": 768,
    "return_dict": true,
    "tdnn_dilation": [
      1,
      2,
      3,
      1,
      1
    ],
    "tdnn_dim": [
      512,
      512,
      512,
      512,
      1500
    ],
    "tdnn_kernel": [
      5,
      3,
      3,
      1,
      1
    ],
    "transformers_version": "5.15.0",
    "use_weighted_layer_sum": false,
    "vocab_size": 32,
    "xvector_output_dim": 512
  },
  "model_type": "genaid",
  "num_accents": 9,
  "num_speakers": 336,
  "sampling_rate": 16000,
  "transformers_version": "5.15.0"
}