Hugging Face's logo

JovialValley
/
model_syllable_onSet4

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Model card Files
xet
 Metrics Community
1
JovialValley commited on
Commit
791e1b9
·
1 Parent(s): 56cadf6

Training in progress, step 100

Browse files
Files changed (18) hide show
  1. .gitignore +1 -0
  2. config.json +116 -0
  3. last-checkpoint/config.json +116 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/preprocessor_config.json +9 -0
  6. last-checkpoint/pytorch_model.bin +3 -0
  7. last-checkpoint/rng_state.pth +3 -0
  8. last-checkpoint/scaler.pt +3 -0
  9. last-checkpoint/scheduler.pt +3 -0
  10. last-checkpoint/trainer_state.json +146 -0
  11. last-checkpoint/training_args.bin +3 -0
  12. preprocessor_config.json +9 -0
  13. pytorch_model.bin +3 -0
  14. runs/Dec21_17-30-19_dd30ac9fa6d8/1671643880.3510318/events.out.tfevents.1671643880.dd30ac9fa6d8.22182.1 +3 -0
  15. runs/Dec21_17-30-19_dd30ac9fa6d8/events.out.tfevents.1671643880.dd30ac9fa6d8.22182.0 +3 -0
  16. runs/Dec21_17-34-31_dd30ac9fa6d8/1671644095.0942724/events.out.tfevents.1671644095.dd30ac9fa6d8.22182.3 +3 -0
  17. runs/Dec21_17-34-31_dd30ac9fa6d8/events.out.tfevents.1671644095.dd30ac9fa6d8.22182.2 +3 -0
  18. 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": 6,
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": 7,
115
+ "xvector_output_dim": 512
116
+ }
last-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": 6,
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": 7,
115
+ "xvector_output_dim": 512
116
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa54937ac2b847600a6183d21d2a292575c8168159aba8f1621fd62abc9316d
3
+ size 2490118021
last-checkpoint/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
+ }
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84b08deb21a13f765f43af6cb8da74565d400d52caa70096318271ec00b72eff
3
+ size 1261930541
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:701d1e1bc1f592ffcd3174173f4c78d685dddfe8beb3652c128b4fb3ef518dd2
3
+ size 14639
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c558518f74cde0fe2cd0b38e5cffc7840b3e9359964c34b0672be1a51ed0fb8
3
+ size 557
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa3fc80509a767df0f73f0a03848f1ccf58cae2f296702b1c2c1603cba4770e6
3
+ size 627
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.163265306122449,
5
+ "global_step": 100,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.41,
12
+ "learning_rate": 8.999999999999999e-06,
13
+ "loss": 18.9189,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.82,
18
+ "learning_rate": 2.3999999999999997e-05,
19
+ "loss": 17.9484,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 1.24,
24
+ "learning_rate": 3.9e-05,
25
+ "loss": 17.4952,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 1.65,
30
+ "learning_rate": 5.399999999999999e-05,
31
+ "loss": 16.7614,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 2.08,
36
+ "learning_rate": 6.599999999999999e-05,
37
+ "loss": 14.6991,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 2.49,
42
+ "learning_rate": 8.1e-05,
43
+ "loss": 7.4187,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 2.9,
48
+ "learning_rate": 9.599999999999999e-05,
49
+ "loss": 2.4627,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 3.33,
54
+ "learning_rate": 0.00011099999999999999,
55
+ "loss": 1.7973,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 3.73,
60
+ "learning_rate": 0.00012599999999999997,
61
+ "loss": 1.6154,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 4.16,
66
+ "learning_rate": 0.00014099999999999998,
67
+ "loss": 1.6602,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 4.16,
72
+ "eval_0_f1-score": 0.0,
73
+ "eval_0_precision": 0.0,
74
+ "eval_0_recall": 0.0,
75
+ "eval_0_support": 26,
76
+ "eval_1_f1-score": 0.0,
77
+ "eval_1_precision": 0.0,
78
+ "eval_1_recall": 0.0,
79
+ "eval_1_support": 31,
80
+ "eval_2_f1-score": 0.4,
81
+ "eval_2_precision": 0.25842696629213485,
82
+ "eval_2_recall": 0.8846153846153846,
83
+ "eval_2_support": 26,
84
+ "eval_3_f1-score": 0.0,
85
+ "eval_3_precision": 0.0,
86
+ "eval_3_recall": 0.0,
87
+ "eval_3_support": 14,
88
+ "eval_accuracy": 0.23711340206185566,
89
+ "eval_loss": 1.5639466047286987,
90
+ "eval_macro avg_f1-score": 0.1,
91
+ "eval_macro avg_precision": 0.06460674157303371,
92
+ "eval_macro avg_recall": 0.22115384615384615,
93
+ "eval_macro avg_support": 97,
94
+ "eval_mtrix": [
95
+ [
96
+ 0,
97
+ 1,
98
+ 2,
99
+ 3
100
+ ],
101
+ [
102
+ 0,
103
+ 0,
104
+ 0,
105
+ 26,
106
+ 0
107
+ ],
108
+ [
109
+ 1,
110
+ 0,
111
+ 0,
112
+ 31,
113
+ 0
114
+ ],
115
+ [
116
+ 2,
117
+ 3,
118
+ 0,
119
+ 23,
120
+ 0
121
+ ],
122
+ [
123
+ 3,
124
+ 5,
125
+ 0,
126
+ 9,
127
+ 0
128
+ ]
129
+ ],
130
+ "eval_runtime": 5.9884,
131
+ "eval_samples_per_second": 16.198,
132
+ "eval_steps_per_second": 2.171,
133
+ "eval_weighted avg_f1-score": 0.10721649484536083,
134
+ "eval_weighted avg_precision": 0.06926908374840729,
135
+ "eval_weighted avg_recall": 0.23711340206185566,
136
+ "eval_weighted avg_support": 97,
137
+ "eval_wer": 0.9732246798603027,
138
+ "step": 100
139
+ }
140
+ ],
141
+ "max_steps": 1680,
142
+ "num_train_epochs": 70,
143
+ "total_flos": 2.224051635996902e+17,
144
+ "trial_name": null,
145
+ "trial_params": null
146
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:053f1f44281de78d1929d4f81fd1f2689093847dbaace021817e4b983c98eb4d
3
+ size 3387
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 sha256:84b08deb21a13f765f43af6cb8da74565d400d52caa70096318271ec00b72eff
3
+ size 1261930541
runs/Dec21_17-30-19_dd30ac9fa6d8/1671643880.3510318/events.out.tfevents.1671643880.dd30ac9fa6d8.22182.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26cad945778b9f84b0ac1a9447b4458a405b65956249262617d467faaa47edce
3
+ size 5531
runs/Dec21_17-30-19_dd30ac9fa6d8/events.out.tfevents.1671643880.dd30ac9fa6d8.22182.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8151cc529c4f5f842330efdf24cddf661b9b92ab5fef982645d849df297fb891
3
+ size 5691
runs/Dec21_17-34-31_dd30ac9fa6d8/1671644095.0942724/events.out.tfevents.1671644095.dd30ac9fa6d8.22182.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:188aff44f29d2a28ed3c8b1fa1860ab1401241bdbb64737b840464e5665278ce
3
+ size 5531
runs/Dec21_17-34-31_dd30ac9fa6d8/events.out.tfevents.1671644095.dd30ac9fa6d8.22182.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:117bac0815851fff4df11d0d0e5dd92d7d3a6442337b5a75f3d7c7e597916cc9
3
+ size 8622
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:053f1f44281de78d1929d4f81fd1f2689093847dbaace021817e4b983c98eb4d
3
+ size 3387