Hugging Face's logo

mohitsha
/
wav2vec2-base-superb-sd

Transformers
ONNX
wav2vec2
audio-frame-classification
Inference Endpoints
Model card Files Community
mohitsha HF staff commited on
Commit
5a9cd8d
•
1 Parent(s): d27a40a

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +125 -0
config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "anton-l/wav2vec2-base-superb-sd",
3
+ "activation_dropout": 0.0,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForAudioFrameClassification"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
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": "sum",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": false,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.1,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "freeze_feat_extract_train": true,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "id2label": {
59
+ "0": "speaker_0",
60
+ "1": "speaker_1"
61
+ },
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 3072,
64
+ "label2id": {
65
+ "speaker_0": 0,
66
+ "speaker_1": 1
67
+ },
68
+ "layer_norm_eps": 1e-05,
69
+ "layerdrop": 0.05,
70
+ "mask_channel_length": 10,
71
+ "mask_channel_min_space": 1,
72
+ "mask_channel_other": 0.0,
73
+ "mask_channel_prob": 0.0,
74
+ "mask_channel_selection": "static",
75
+ "mask_feature_length": 10,
76
+ "mask_feature_min_masks": 0,
77
+ "mask_feature_prob": 0.0,
78
+ "mask_time_length": 10,
79
+ "mask_time_min_masks": 2,
80
+ "mask_time_min_space": 1,
81
+ "mask_time_other": 0.0,
82
+ "mask_time_prob": 0.05,
83
+ "mask_time_selection": "static",
84
+ "model_type": "wav2vec2",
85
+ "no_mask_channel_overlap": false,
86
+ "no_mask_time_overlap": false,
87
+ "num_adapter_layers": 3,
88
+ "num_attention_heads": 12,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 12,
95
+ "num_negatives": 100,
96
+ "output_hidden_size": 768,
97
+ "pad_token_id": 0,
98
+ "proj_codevector_dim": 256,
99
+ "tdnn_dilation": [
100
+ 1,
101
+ 2,
102
+ 3,
103
+ 1,
104
+ 1
105
+ ],
106
+ "tdnn_dim": [
107
+ 512,
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 1500
112
+ ],
113
+ "tdnn_kernel": [
114
+ 5,
115
+ 3,
116
+ 3,
117
+ 1,
118
+ 1
119
+ ],
120
+ "torch_dtype": "float32",
121
+ "transformers_version": "4.27.0.dev0",
122
+ "use_weighted_layer_sum": true,
123
+ "vocab_size": 32,
124
+ "xvector_output_dim": 512
125
+ }