Hugging Face's logo

snehatyagi
/
wav2vec2_timit

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Model card Files
xet
Metrics Community
1
snehatyagi commited on
Commit
af034f9
·
1 Parent(s): 1965fad

Training in progress, step 500

Browse files
Files changed (8) hide show
  1. config.json +117 -0
  2. preprocessor_config.json +10 -0
  3. pytorch_model.bin +3 -0
  4. runs/Mar21_05-00-10_DESKTOP-C5B0HSF/1647819310.4838724/events.out.tfevents.1647819310.DESKTOP-C5B0HSF.17432.1 +3 -0
  5. runs/Mar21_05-00-10_DESKTOP-C5B0HSF/events.out.tfevents.1647819310.DESKTOP-C5B0HSF.17432.0 +3 -0
  6. runs/Mar21_05-14-30_DESKTOP-C5B0HSF/1647819988.6945155/events.out.tfevents.1647819988.DESKTOP-C5B0HSF.17432.3 +3 -0
  7. runs/Mar21_05-14-30_DESKTOP-C5B0HSF/events.out.tfevents.1647819988.DESKTOP-C5B0HSF.17432.2 +3 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
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
+ "Wav2Vec2ForCTC"
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": "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": 0.1,
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
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.0,
62
+ "mask_channel_length": 10,
63
+ "mask_channel_min_space": 1,
64
+ "mask_channel_other": 0.0,
65
+ "mask_channel_prob": 0.0,
66
+ "mask_channel_selection": "static",
67
+ "mask_feature_length": 10,
68
+ "mask_feature_min_masks": 0,
69
+ "mask_feature_prob": 0.0,
70
+ "mask_time_length": 10,
71
+ "mask_time_min_masks": 2,
72
+ "mask_time_min_space": 1,
73
+ "mask_time_other": 0.0,
74
+ "mask_time_prob": 0.05,
75
+ "mask_time_selection": "static",
76
+ "model_type": "wav2vec2",
77
+ "no_mask_channel_overlap": false,
78
+ "no_mask_time_overlap": false,
79
+ "num_adapter_layers": 3,
80
+ "num_attention_heads": 12,
81
+ "num_codevector_groups": 2,
82
+ "num_codevectors_per_group": 320,
83
+ "num_conv_pos_embedding_groups": 16,
84
+ "num_conv_pos_embeddings": 128,
85
+ "num_feat_extract_layers": 7,
86
+ "num_hidden_layers": 12,
87
+ "num_negatives": 100,
88
+ "output_hidden_size": 768,
89
+ "pad_token_id": 29,
90
+ "proj_codevector_dim": 256,
91
+ "tdnn_dilation": [
92
+ 1,
93
+ 2,
94
+ 3,
95
+ 1,
96
+ 1
97
+ ],
98
+ "tdnn_dim": [
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 512,
103
+ 1500
104
+ ],
105
+ "tdnn_kernel": [
106
+ 5,
107
+ 3,
108
+ 3,
109
+ 1,
110
+ 1
111
+ ],
112
+ "torch_dtype": "float32",
113
+ "transformers_version": "4.17.0",
114
+ "use_weighted_layer_sum": false,
115
+ "vocab_size": 32,
116
+ "xvector_output_dim": 512
117
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_normlaize": true,
4
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
5
+ "feature_size": 1,
6
+ "padding_side": "right",
7
+ "padding_value": 0.0,
8
+ "return_attention_mask": false,
9
+ "sampling_rate": 16000
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:800e69dd19476a4ce6214175bd743ef38c7078a5e391c0fc8a4c4050ca7de17a
3
+ size 377668631
runs/Mar21_05-00-10_DESKTOP-C5B0HSF/1647819310.4838724/events.out.tfevents.1647819310.DESKTOP-C5B0HSF.17432.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f854bde1073464fdd80dc016c6e95bd527de99c4f41e2b7067459b493e8c987
3
+ size 4760
runs/Mar21_05-00-10_DESKTOP-C5B0HSF/events.out.tfevents.1647819310.DESKTOP-C5B0HSF.17432.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f15c6b03cfec5fce440b84a5bf519fa554336acdf69aca2a28c5c2a60dcf4c04
3
+ size 4973
runs/Mar21_05-14-30_DESKTOP-C5B0HSF/1647819988.6945155/events.out.tfevents.1647819988.DESKTOP-C5B0HSF.17432.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60d10006c6a45c13a741bc6c0a8b393e3d7a227af2bae30a4ee34ea03b22b45
3
+ size 4760
runs/Mar21_05-14-30_DESKTOP-C5B0HSF/events.out.tfevents.1647819988.DESKTOP-C5B0HSF.17432.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a16eb60223e3dba75a57a86982d03b3537ba54266e4ad834a24063ee28371b43
3
+ size 5448
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc377fdaefd4427fdc4586a6f35d3f0b222fb3dd3ded92003aac11aa2318b2a7
3
+ size 2991