mazkooleg commited on
Commit
6c65464
1 Parent(s): cecb6f0

End of training

Browse files
Files changed (5) hide show
  1. .gitignore +1 -0
  2. config.json +150 -0
  3. preprocessor_config.json +9 -0
  4. pytorch_model.bin +3 -0
  5. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/wavlm-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": 0.1,
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": "zero",
60
+ "1": "one",
61
+ "10": "#unk#",
62
+ "11": "#pub#",
63
+ "2": "two",
64
+ "3": "three",
65
+ "4": "four",
66
+ "5": "five",
67
+ "6": "six",
68
+ "7": "seven",
69
+ "8": "eight",
70
+ "9": "nine"
71
+ },
72
+ "initializer_range": 0.02,
73
+ "intermediate_size": 3072,
74
+ "label2id": {
75
+ "#pub#": 11,
76
+ "#unk#": 10,
77
+ "eight": 8,
78
+ "five": 5,
79
+ "four": 4,
80
+ "nine": 9,
81
+ "one": 1,
82
+ "seven": 7,
83
+ "six": 6,
84
+ "three": 3,
85
+ "two": 2,
86
+ "zero": 0
87
+ },
88
+ "layer_norm_eps": 1e-05,
89
+ "layerdrop": 0.05,
90
+ "mask_channel_length": 10,
91
+ "mask_channel_min_space": 1,
92
+ "mask_channel_other": 0.0,
93
+ "mask_channel_prob": 0.0,
94
+ "mask_channel_selection": "static",
95
+ "mask_feature_length": 10,
96
+ "mask_feature_min_masks": 0,
97
+ "mask_feature_prob": 0.0,
98
+ "mask_time_length": 10,
99
+ "mask_time_min_masks": 2,
100
+ "mask_time_min_space": 1,
101
+ "mask_time_other": 0.0,
102
+ "mask_time_prob": 0.05,
103
+ "mask_time_selection": "static",
104
+ "max_bucket_distance": 800,
105
+ "model_type": "wavlm",
106
+ "no_mask_channel_overlap": false,
107
+ "no_mask_time_overlap": false,
108
+ "num_adapter_layers": 3,
109
+ "num_attention_heads": 12,
110
+ "num_buckets": 320,
111
+ "num_codevector_groups": 2,
112
+ "num_codevectors_per_group": 320,
113
+ "num_conv_pos_embedding_groups": 16,
114
+ "num_conv_pos_embeddings": 128,
115
+ "num_ctc_classes": 80,
116
+ "num_feat_extract_layers": 7,
117
+ "num_hidden_layers": 12,
118
+ "num_negatives": 100,
119
+ "output_hidden_size": 768,
120
+ "pad_token_id": 0,
121
+ "proj_codevector_dim": 256,
122
+ "replace_prob": 0.5,
123
+ "tdnn_dilation": [
124
+ 1,
125
+ 2,
126
+ 3,
127
+ 1,
128
+ 1
129
+ ],
130
+ "tdnn_dim": [
131
+ 512,
132
+ 512,
133
+ 512,
134
+ 512,
135
+ 1500
136
+ ],
137
+ "tdnn_kernel": [
138
+ 5,
139
+ 3,
140
+ 3,
141
+ 1,
142
+ 1
143
+ ],
144
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
145
+ "torch_dtype": "float32",
146
+ "transformers_version": "4.27.3",
147
+ "use_weighted_layer_sum": false,
148
+ "vocab_size": 32,
149
+ "xvector_output_dim": 512
150
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": false,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d93b5fb2c95c238853682a17156233e12cb9d4ad9cd89a6bf90c6f0ee45b6600
3
+ size 378411145
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8077b7dfa1e21d3c07b0940f8cf9e7e83485f90c9e378686c84b28440049f40a
3
+ size 3567