jimregan commited on
Commit
e0d54cd
1 Parent(s): b538e1e
config.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.05,
3
+ "adapter_kernel_size": 3,
4
+ "adapter_stride": 2,
5
+ "add_adapter": false,
6
+ "apply_spec_augment": true,
7
+ "architectures": [
8
+ "Wav2Vec2ForCTC"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 1,
12
+ "classifier_proj_size": 256,
13
+ "codevector_dim": 256,
14
+ "contrastive_logits_temperature": 0.1,
15
+ "conv_bias": true,
16
+ "conv_dim": [
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512
24
+ ],
25
+ "conv_kernel": [
26
+ 10,
27
+ 3,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 2,
32
+ 2
33
+ ],
34
+ "conv_stride": [
35
+ 5,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2
42
+ ],
43
+ "ctc_loss_reduction": "mean",
44
+ "ctc_zero_infinity": true,
45
+ "diversity_loss_weight": 0.1,
46
+ "do_stable_layer_norm": true,
47
+ "eos_token_id": 2,
48
+ "feat_extract_activation": "gelu",
49
+ "feat_extract_dropout": 0.0,
50
+ "feat_extract_norm": "layer",
51
+ "feat_proj_dropout": 0.05,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "hidden_act": "gelu",
55
+ "hidden_dropout": 0.05,
56
+ "hidden_size": 1024,
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 4096,
59
+ "layer_norm_eps": 1e-05,
60
+ "layerdrop": 0.05,
61
+ "mask_channel_length": 10,
62
+ "mask_channel_min_space": 1,
63
+ "mask_channel_other": 0.0,
64
+ "mask_channel_prob": 0.0,
65
+ "mask_channel_selection": "static",
66
+ "mask_feature_length": 10,
67
+ "mask_feature_min_masks": 0,
68
+ "mask_feature_prob": 0.0,
69
+ "mask_time_length": 10,
70
+ "mask_time_min_masks": 2,
71
+ "mask_time_min_space": 1,
72
+ "mask_time_other": 0.0,
73
+ "mask_time_prob": 0.05,
74
+ "mask_time_selection": "static",
75
+ "model_type": "wav2vec2",
76
+ "num_adapter_layers": 3,
77
+ "num_attention_heads": 16,
78
+ "num_codevector_groups": 2,
79
+ "num_codevectors_per_group": 320,
80
+ "num_conv_pos_embedding_groups": 16,
81
+ "num_conv_pos_embeddings": 128,
82
+ "num_feat_extract_layers": 7,
83
+ "num_hidden_layers": 24,
84
+ "num_negatives": 100,
85
+ "output_hidden_size": 1024,
86
+ "pad_token_id": 0,
87
+ "proj_codevector_dim": 256,
88
+ "tdnn_dilation": [
89
+ 1,
90
+ 2,
91
+ 3,
92
+ 1,
93
+ 1
94
+ ],
95
+ "tdnn_dim": [
96
+ 512,
97
+ 512,
98
+ 512,
99
+ 512,
100
+ 1500
101
+ ],
102
+ "tdnn_kernel": [
103
+ 5,
104
+ 3,
105
+ 3,
106
+ 1,
107
+ 1
108
+ ],
109
+ "torch_dtype": "float32",
110
+ "transformers_version": "4.26.1",
111
+ "use_weighted_layer_sum": false,
112
+ "vocab_size": 36,
113
+ "xvector_output_dim": 512
114
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51828b94f342526deb19c5d658439dc8d216abe83d7dff595ca86053f873455a
3
+ size 1262043565
runs/train/events.out.tfevents.1677869013.sbtaldeep24 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19f9d2b375f47a7180d39f91ab24ab96f30752f7b1b0ddd7e77ffe91c71492bb
3
- size 99724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c4ac8f5de9d8b02e7f2ce0e8ce235ec41b567341f2a663082c951521fe5267d
3
+ size 189903
runs/train_inner/events.out.tfevents.1677869187.sbtaldeep24 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d0059d7517907dfb79fa31ed19ac959b6f3b2ab3fef1784576e54bd04456fcd
3
- size 44113
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ce7a74bd72e5d1cb62a75c545aeb84d5c7e216b5f3b730db99c84ab780a6c73
3
+ size 83577
runs/valid/events.out.tfevents.1677869002.sbtaldeep24 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5dea25b09db678ee2ae673606dbb4442ad414f0ada9e58212a00844e4f46f7f
3
- size 78386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a8dbcab8a5472e5098f8268137716df274c9c103cbab3334ff752c21f00750
3
+ size 148003
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "pad_token": "<pad>",
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "replace_word_delimiter_char": " ",
9
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
10
+ "unk_token": "<unk>",
11
+ "word_delimiter_token": "|"
12
+ }
vocab.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "-": 4,
3
+ ":": 5,
4
+ "</s>": 2,
5
+ "<pad>": 0,
6
+ "<s>": 1,
7
+ "<unk>": 3,
8
+ "a": 6,
9
+ "b": 7,
10
+ "c": 8,
11
+ "d": 9,
12
+ "e": 10,
13
+ "f": 11,
14
+ "g": 12,
15
+ "h": 13,
16
+ "i": 14,
17
+ "j": 15,
18
+ "k": 16,
19
+ "l": 17,
20
+ "m": 18,
21
+ "n": 19,
22
+ "o": 20,
23
+ "p": 21,
24
+ "r": 22,
25
+ "s": 23,
26
+ "t": 24,
27
+ "u": 25,
28
+ "v": 26,
29
+ "w": 27,
30
+ "x": 28,
31
+ "y": 29,
32
+ "z": 30,
33
+ "|": 31,
34
+ "ä": 32,
35
+ "å": 33,
36
+ "é": 34,
37
+ "ö": 35
38
+ }