Hugging Face's logo

Orange
/
Speaker-wavLM-tbr

Safetensors
English
wavlm
Speaker traits
Voice
Speaker
🇪🇺 Region: EU
Model card Files Community
ggmbr commited on
Commit
d90b63c
·
1 Parent(s): 720ee27

config

Browse files
Files changed (1) hide show
  1. config.json +123 -0
config.json ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "orange/w-pro",
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
+ "EmbeddingsModel"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 768,
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": true,
48
+ "embd_size": 128,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_size": 1024,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 4096,
62
+ "layer_norm_eps": 1e-05,
63
+ "layerdrop": 0.1,
64
+ "mask_channel_length": 10,
65
+ "mask_channel_min_space": 1,
66
+ "mask_channel_other": 0.0,
67
+ "mask_channel_prob": 0.0,
68
+ "mask_channel_selection": "static",
69
+ "mask_feature_length": 10,
70
+ "mask_feature_min_masks": 0,
71
+ "mask_feature_prob": 0.0,
72
+ "mask_time_length": 10,
73
+ "mask_time_min_masks": 2,
74
+ "mask_time_min_space": 1,
75
+ "mask_time_other": 0.0,
76
+ "mask_time_prob": 0.075,
77
+ "mask_time_selection": "static",
78
+ "max_bucket_distance": 800,
79
+ "model_type": "wavlm",
80
+ "num_adapter_layers": 3,
81
+ "num_attention_heads": 16,
82
+ "num_buckets": 320,
83
+ "num_codevector_groups": 2,
84
+ "num_codevectors_per_group": 320,
85
+ "num_conv_pos_embedding_groups": 16,
86
+ "num_conv_pos_embeddings": 128,
87
+ "num_ctc_classes": 80,
88
+ "num_feat_extract_layers": 7,
89
+ "num_hidden_layers": 24,
90
+ "num_negatives": 100,
91
+ "output_hidden_size": 1024,
92
+ "pad_token_id": 0,
93
+ "proj_codevector_dim": 768,
94
+ "replace_prob": 0.5,
95
+ "tdnn_dilation": [
96
+ 1,
97
+ 2,
98
+ 3,
99
+ 1,
100
+ 1
101
+ ],
102
+ "tdnn_dim": [
103
+ 512,
104
+ 512,
105
+ 512,
106
+ 512,
107
+ 1500
108
+ ],
109
+ "tdnn_kernel": [
110
+ 5,
111
+ 3,
112
+ 3,
113
+ 1,
114
+ 1
115
+ ],
116
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
117
+ "top_interm_size": 512,
118
+ "torch_dtype": "float32",
119
+ "transformers_version": "4.48.2",
120
+ "use_weighted_layer_sum": false,
121
+ "vocab_size": 32,
122
+ "xvector_output_dim": 512
123
+ }