Ar4ikov commited on
Commit
0a536bf
1 Parent(s): 8c74ef1

Upload Wav2Vec2ForSequenceClassification

Browse files
Files changed (2) hide show
  1. config.json +138 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Aniemore/wav2vec2-emotion-russian-resd",
3
+ "activation_dropout": 0.05,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSequenceClassification"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 1024,
14
+ "codevector_dim": 768,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "mean",
45
+ "ctc_zero_infinity": true,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "layer",
52
+ "feat_proj_dropout": 0.05,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "finetuning_task": [
56
+ "wav2vec2_clf"
57
+ ],
58
+ "hidden_act": "gelu",
59
+ "hidden_dropout": 0.05,
60
+ "hidden_size": 1024,
61
+ "id2label": {
62
+ "0": "anger",
63
+ "1": "disgust",
64
+ "2": "enthusiasm",
65
+ "3": "fear",
66
+ "4": "happiness",
67
+ "5": "neutral",
68
+ "6": "sadness"
69
+ },
70
+ "initializer_range": 0.02,
71
+ "intermediate_size": 4096,
72
+ "label2id": {
73
+ "anger": 0,
74
+ "disgust": 1,
75
+ "enthusiasm": 2,
76
+ "fear": 3,
77
+ "happiness": 4,
78
+ "neutral": 5,
79
+ "sadness": 6
80
+ },
81
+ "layer_norm_eps": 1e-05,
82
+ "layerdrop": 0.05,
83
+ "mask_channel_length": 10,
84
+ "mask_channel_min_space": 1,
85
+ "mask_channel_other": 0.0,
86
+ "mask_channel_prob": 0.0,
87
+ "mask_channel_selection": "static",
88
+ "mask_feature_length": 10,
89
+ "mask_feature_min_masks": 0,
90
+ "mask_feature_prob": 0.0,
91
+ "mask_time_length": 10,
92
+ "mask_time_min_masks": 2,
93
+ "mask_time_min_space": 1,
94
+ "mask_time_other": 0.0,
95
+ "mask_time_prob": 0.05,
96
+ "mask_time_selection": "static",
97
+ "model_type": "wav2vec2",
98
+ "num_adapter_layers": 3,
99
+ "num_attention_heads": 16,
100
+ "num_codevector_groups": 2,
101
+ "num_codevectors_per_group": 320,
102
+ "num_conv_pos_embedding_groups": 16,
103
+ "num_conv_pos_embeddings": 128,
104
+ "num_feat_extract_layers": 7,
105
+ "num_hidden_layers": 24,
106
+ "num_negatives": 100,
107
+ "output_hidden_size": 1024,
108
+ "pad_token_id": 0,
109
+ "pooling_mode": "mean",
110
+ "problem_type": "single_label_classification",
111
+ "proj_codevector_dim": 768,
112
+ "tdnn_dilation": [
113
+ 1,
114
+ 2,
115
+ 3,
116
+ 1,
117
+ 1
118
+ ],
119
+ "tdnn_dim": [
120
+ 512,
121
+ 512,
122
+ 512,
123
+ 512,
124
+ 1500
125
+ ],
126
+ "tdnn_kernel": [
127
+ 5,
128
+ 3,
129
+ 3,
130
+ 1,
131
+ 1
132
+ ],
133
+ "torch_dtype": "float32",
134
+ "transformers_version": "4.25.1",
135
+ "use_weighted_layer_sum": false,
136
+ "vocab_size": 39,
137
+ "xvector_output_dim": 512
138
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6a1da4ef08eb2a8e5c0566c2918ea8b20007445b1a9e3b54f3277e6c4e1431d
3
+ size 1266123637