Hugging Face's logo

Roblox
/
voice-safety-classifier

Audio Classification
Transformers
Safetensors
wavlm
Inference Endpoints
Model card Files Community
1
josephliu-roblox commited on
Commit
39d9319
•
1 Parent(s): 1545bad

Upload Voice-Safety-Classifier model

Browse files
Files changed (2) hide show
  1. config.json +138 -0
  2. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "patrickvonplaten/wavlm-libri-clean-100h-base-plus",
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
+ "WavLMForSequenceClassification"
10
+ ],
11
+ "attention_dropout": 0.0,
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": "mean",
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": 0.0,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "freeze_feat_extract_train": true,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.0,
57
+ "hidden_size": 768,
58
+ "id2label": {
59
+ "0": "LABEL_0",
60
+ "1": "LABEL_1",
61
+ "2": "LABEL_2",
62
+ "3": "LABEL_3",
63
+ "4": "LABEL_4",
64
+ "5": "LABEL_5"
65
+ },
66
+ "initializer_range": 0.02,
67
+ "intermediate_size": 3072,
68
+ "label2id": {
69
+ "LABEL_0": 0,
70
+ "LABEL_1": 1,
71
+ "LABEL_2": 2,
72
+ "LABEL_3": 3,
73
+ "LABEL_4": 4,
74
+ "LABEL_5": 5
75
+ },
76
+ "layer_norm_eps": 1e-05,
77
+ "layerdrop": 0.0,
78
+ "mask_channel_length": 10,
79
+ "mask_channel_min_space": 1,
80
+ "mask_channel_other": 0.0,
81
+ "mask_channel_prob": 0.0,
82
+ "mask_channel_selection": "static",
83
+ "mask_feature_length": 10,
84
+ "mask_feature_min_masks": 0,
85
+ "mask_feature_prob": 0.0,
86
+ "mask_time_length": 10,
87
+ "mask_time_min_masks": 2,
88
+ "mask_time_min_space": 1,
89
+ "mask_time_other": 0.0,
90
+ "mask_time_prob": 0.05,
91
+ "mask_time_selection": "static",
92
+ "max_bucket_distance": 800,
93
+ "model_type": "wavlm",
94
+ "no_mask_channel_overlap": false,
95
+ "no_mask_time_overlap": false,
96
+ "num_adapter_layers": 3,
97
+ "num_attention_heads": 12,
98
+ "num_buckets": 320,
99
+ "num_codevector_groups": 2,
100
+ "num_codevectors_per_group": 320,
101
+ "num_conv_pos_embedding_groups": 16,
102
+ "num_conv_pos_embeddings": 128,
103
+ "num_ctc_classes": 80,
104
+ "num_feat_extract_layers": 7,
105
+ "num_hidden_layers": 12,
106
+ "num_negatives": 100,
107
+ "output_hidden_size": 768,
108
+ "pad_token_id": 28,
109
+ "proj_codevector_dim": 256,
110
+ "replace_prob": 0.5,
111
+ "tdnn_dilation": [
112
+ 1,
113
+ 2,
114
+ 3,
115
+ 1,
116
+ 1
117
+ ],
118
+ "tdnn_dim": [
119
+ 512,
120
+ 512,
121
+ 512,
122
+ 512,
123
+ 1500
124
+ ],
125
+ "tdnn_kernel": [
126
+ 5,
127
+ 3,
128
+ 3,
129
+ 1,
130
+ 1
131
+ ],
132
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
133
+ "torch_dtype": "float32",
134
+ "transformers_version": "4.38.2",
135
+ "use_weighted_layer_sum": false,
136
+ "vocab_size": 31,
137
+ "xvector_output_dim": 512
138
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e567d30937841722e766196bc82793b7ee21aa4ad6b7c373a2866ff9691f676f
3
+ size 378351368