Hugging Face's logo

JovialValley
/
model_broadclass_onSet0

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Model card Files
xet
Metrics Community
1
JovialValley commited on
Commit
3359f8a
·
1 Parent(s): d84135d

Training in progress, step 100

Browse files
Files changed (10) hide show
  1. .gitignore +1 -0
  2. config.json +116 -0
  3. preprocessor_config.json +9 -0
  4. pytorch_model.bin +3 -0
  5. runs/Dec20_15-47-50_0bec1ee3876b/1671551594.3055804/events.out.tfevents.1671551594.0bec1ee3876b.16421.5 +3 -0
  6. runs/Dec20_15-47-50_0bec1ee3876b/1671553834.8082376/events.out.tfevents.1671553834.0bec1ee3876b.16421.6 +3 -0
  7. runs/Dec20_15-47-50_0bec1ee3876b/events.out.tfevents.1671551594.0bec1ee3876b.16421.4 +3 -0
  8. runs/Dec20_17-17-29_0bec1ee3876b/1671556672.1912138/events.out.tfevents.1671556672.0bec1ee3876b.61673.1 +3 -0
  9. runs/Dec20_17-17-29_0bec1ee3876b/events.out.tfevents.1671556672.0bec1ee3876b.61673.0 +3 -0
  10. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
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": 768,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
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": true,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "layer",
52
+ "feat_proj_dropout": 0.0,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_size": 1024,
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 4096,
61
+ "layer_norm_eps": 1e-05,
62
+ "layerdrop": 0.1,
63
+ "mask_channel_length": 10,
64
+ "mask_channel_min_space": 1,
65
+ "mask_channel_other": 0.0,
66
+ "mask_channel_prob": 0.0,
67
+ "mask_channel_selection": "static",
68
+ "mask_feature_length": 10,
69
+ "mask_feature_min_masks": 0,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_min_masks": 2,
73
+ "mask_time_min_space": 1,
74
+ "mask_time_other": 0.0,
75
+ "mask_time_prob": 0.01,
76
+ "mask_time_selection": "static",
77
+ "model_type": "wav2vec2",
78
+ "num_adapter_layers": 3,
79
+ "num_attention_heads": 16,
80
+ "num_codevector_groups": 2,
81
+ "num_codevectors_per_group": 320,
82
+ "num_conv_pos_embedding_groups": 16,
83
+ "num_conv_pos_embeddings": 128,
84
+ "num_feat_extract_layers": 7,
85
+ "num_hidden_layers": 24,
86
+ "num_negatives": 100,
87
+ "output_hidden_size": 1024,
88
+ "pad_token_id": 26,
89
+ "proj_codevector_dim": 768,
90
+ "tdnn_dilation": [
91
+ 1,
92
+ 2,
93
+ 3,
94
+ 1,
95
+ 1
96
+ ],
97
+ "tdnn_dim": [
98
+ 512,
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 1500
103
+ ],
104
+ "tdnn_kernel": [
105
+ 5,
106
+ 3,
107
+ 3,
108
+ 1,
109
+ 1
110
+ ],
111
+ "torch_dtype": "float32",
112
+ "transformers_version": "4.25.1",
113
+ "use_weighted_layer_sum": false,
114
+ "vocab_size": 27,
115
+ "xvector_output_dim": 512
116
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
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 sha256:3ad875e923016236c79abc4bd41a8df3d409d41934e938980000181cc02591de
3
+ size 1262012525
runs/Dec20_15-47-50_0bec1ee3876b/1671551594.3055804/events.out.tfevents.1671551594.0bec1ee3876b.16421.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e4fe17165f6caa6440afe6aa6871d02e577d307d4b5c9ddeed45c30facf2d2b
3
+ size 5537
runs/Dec20_15-47-50_0bec1ee3876b/1671553834.8082376/events.out.tfevents.1671553834.0bec1ee3876b.16421.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d077d7fcc8d1aefe5af1bc3eff186eb35921c84b0daceaed7a126513991e97f9
3
+ size 5537
runs/Dec20_15-47-50_0bec1ee3876b/events.out.tfevents.1671551594.0bec1ee3876b.16421.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:121719b856fc9c16a0b307fd6869944fa3270a93c70d56c29db7883b77960963
3
+ size 9487
runs/Dec20_17-17-29_0bec1ee3876b/1671556672.1912138/events.out.tfevents.1671556672.0bec1ee3876b.61673.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14d7fdac740df15cadff7470626fc780d7223c0a215acda5effb2897599f1f07
3
+ size 5537
runs/Dec20_17-17-29_0bec1ee3876b/events.out.tfevents.1671556672.0bec1ee3876b.61673.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29c4c3f69c9760292146b55cc3b5056b61f1a7ccb600241b92cd02d1f46f1043
3
+ size 8630
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b8ed89397a04f13667c32516888ec3acc53a51aa833b3faab1d553ade0d89e0
3
+ size 3451