Hugging Face's logo

publicstaticvo
/
SPECTRA-base

PyTorch
Model card Files
xet
Community
publicstaticvo commited on
Commit
2d90334
·
1 Parent(s): d751f29

init

Browse files
Files changed (6) hide show
  1. audio_config.json +126 -0
  2. merges.txt +0 -0
  3. pytorch_model.bin +3 -0
  4. text_config.json +28 -0
  5. tokenizer.json +0 -0
  6. vocab.json +0 -0
audio_config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/data/yts/models/wavlmForV1.1.3",
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
+ "WavLMModel"
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
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2,
35
+ 5
36
+ ],
37
+ "conv_stride": [
38
+ 5,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2,
44
+ 2,
45
+ 5
46
+ ],
47
+ "ctc_loss_reduction": "sum",
48
+ "ctc_zero_infinity": false,
49
+ "diversity_loss_weight": 0.1,
50
+ "do_stable_layer_norm": false,
51
+ "eos_token_id": 2,
52
+ "feat_extract_activation": "gelu",
53
+ "feat_extract_norm": "group",
54
+ "feat_proj_dropout": 0.1,
55
+ "feat_quantizer_dropout": 0.0,
56
+ "final_dropout": 0.0,
57
+ "freeze_feat_extract_train": true,
58
+ "hidden_act": "gelu",
59
+ "hidden_dropout": 0.1,
60
+ "hidden_size": 768,
61
+ "initializer_range": 0.02,
62
+ "intermediate_size": 3072,
63
+ "layer_norm_eps": 1e-05,
64
+ "layerdrop": 0.05,
65
+ "mask_channel_length": 10,
66
+ "mask_channel_min_space": 1,
67
+ "mask_channel_other": 0.0,
68
+ "mask_channel_prob": 0.0,
69
+ "mask_channel_selection": "static",
70
+ "mask_feature_length": 10,
71
+ "mask_feature_min_masks": 0,
72
+ "mask_feature_prob": 0.0,
73
+ "mask_time_length": 10,
74
+ "mask_time_min_masks": 2,
75
+ "mask_time_min_space": 1,
76
+ "mask_time_other": 0.0,
77
+ "mask_time_prob": 0.05,
78
+ "mask_time_selection": "static",
79
+ "max_bucket_distance": 800,
80
+ "max_length": 160000,
81
+ "model_type": "wavlm",
82
+ "no_mask_channel_overlap": false,
83
+ "no_mask_time_overlap": false,
84
+ "num_adapter_layers": 3,
85
+ "num_attention_heads": 12,
86
+ "num_buckets": 320,
87
+ "num_codevector_groups": 2,
88
+ "num_codevectors_per_group": 320,
89
+ "num_conv_pos_embedding_groups": 16,
90
+ "num_conv_pos_embeddings": 128,
91
+ "num_ctc_classes": 80,
92
+ "num_feat_extract_layers": 8,
93
+ "num_hidden_layers": 12,
94
+ "num_negatives": 100,
95
+ "output_hidden_size": 768,
96
+ "pad_token_id": 0,
97
+ "proj_codevector_dim": 256,
98
+ "replace_prob": 0.5,
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
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
121
+ "torch_dtype": "float32",
122
+ "transformers_version": "4.18.0",
123
+ "use_weighted_layer_sum": false,
124
+ "vocab_size": 32,
125
+ "xvector_output_dim": 512
126
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d064881a2325a97c304f8457724b4799c913d3b7d7942bd84bdcb575fe206f26
3
+ size 1070838453
text_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/data/yts/models/robertaForV3",
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_length": 512,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_fused_layers": 1,
21
+ "num_hidden_layers": 12,
22
+ "pad_token_id": 1,
23
+ "position_embedding_type": "absolute",
24
+ "transformers_version": "4.18.0",
25
+ "type_vocab_size": 2,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff