Hugging Face's logo

chrisjay
/
afrospeech-wav2vec-ibo

Audio Classification
Transformers
PyTorch
wav2vec2
afro-digits-speech
Eval Results
Inference Endpoints
Model card Files Community
chrisjay commited on
Commit
acfeca8
•
1 Parent(s): 8cb23aa

add model

Browse files
Files changed (2) hide show
  1. config.json +141 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
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
+ "Wav2Vec2ForSequenceClassification"
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": "0",
60
+ "1": "1",
61
+ "2": "2",
62
+ "3": "3",
63
+ "4": "4",
64
+ "5": "5",
65
+ "6": "6",
66
+ "7": "7",
67
+ "8": "8",
68
+ "9": "9"
69
+ },
70
+ "initializer_range": 0.02,
71
+ "intermediate_size": 3072,
72
+ "label2id": {
73
+ "0": "0",
74
+ "1": "1",
75
+ "2": "2",
76
+ "3": "3",
77
+ "4": "4",
78
+ "5": "5",
79
+ "6": "6",
80
+ "7": "7",
81
+ "8": "8",
82
+ "9": "9"
83
+ },
84
+ "layer_norm_eps": 1e-05,
85
+ "layerdrop": 0.0,
86
+ "mask_channel_length": 10,
87
+ "mask_channel_min_space": 1,
88
+ "mask_channel_other": 0.0,
89
+ "mask_channel_prob": 0.0,
90
+ "mask_channel_selection": "static",
91
+ "mask_feature_length": 10,
92
+ "mask_feature_min_masks": 0,
93
+ "mask_feature_prob": 0.0,
94
+ "mask_time_length": 10,
95
+ "mask_time_min_masks": 2,
96
+ "mask_time_min_space": 1,
97
+ "mask_time_other": 0.0,
98
+ "mask_time_prob": 0.05,
99
+ "mask_time_selection": "static",
100
+ "model_type": "wav2vec2",
101
+ "no_mask_channel_overlap": false,
102
+ "no_mask_time_overlap": false,
103
+ "num_adapter_layers": 3,
104
+ "num_attention_heads": 12,
105
+ "num_codevector_groups": 2,
106
+ "num_codevectors_per_group": 320,
107
+ "num_conv_pos_embedding_groups": 16,
108
+ "num_conv_pos_embeddings": 128,
109
+ "num_feat_extract_layers": 7,
110
+ "num_hidden_layers": 12,
111
+ "num_negatives": 100,
112
+ "output_hidden_size": 768,
113
+ "pad_token_id": 0,
114
+ "proj_codevector_dim": 256,
115
+ "tdnn_dilation": [
116
+ 1,
117
+ 2,
118
+ 3,
119
+ 1,
120
+ 1
121
+ ],
122
+ "tdnn_dim": [
123
+ 512,
124
+ 512,
125
+ 512,
126
+ 512,
127
+ 1500
128
+ ],
129
+ "tdnn_kernel": [
130
+ 5,
131
+ 3,
132
+ 3,
133
+ 1,
134
+ 1
135
+ ],
136
+ "torch_dtype": "float32",
137
+ "transformers_version": "4.21.3",
138
+ "use_weighted_layer_sum": false,
139
+ "vocab_size": 32,
140
+ "xvector_output_dim": 512
141
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:336b448a306b15e911fc23e8279abb6fab1797b932ee8990d4e4886c95e92c64
3
+ size 378356755