Hugging Face's logo

Botnoi
/
wav2vec2-xls-r-300m-th-v7_0

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
newknp commited on
Commit
865eabb
•
1 Parent(s): 5e0f78a

Training in progress, step 3000

Browse files
Files changed (15) hide show
  1. checkpoint-3000/config.json +108 -0
  2. checkpoint-3000/optimizer.pt +3 -0
  3. checkpoint-3000/preprocessor_config.json +9 -0
  4. checkpoint-3000/pytorch_model.bin +3 -0
  5. checkpoint-3000/rng_state.pth +3 -0
  6. checkpoint-3000/scaler.pt +3 -0
  7. checkpoint-3000/scheduler.pt +3 -0
  8. checkpoint-3000/trainer_state.json +130 -0
  9. checkpoint-3000/training_args.bin +3 -0
  10. config.json +108 -0
  11. logs/1675161831.778444/events.out.tfevents.1675161831.31efd5474bec.3677.1 +3 -0
  12. logs/events.out.tfevents.1675161831.31efd5474bec.3677.0 +3 -0
  13. preprocessor_config.json +9 -0
  14. pytorch_model.bin +3 -0
  15. training_args.bin +3 -0
checkpoint-3000/config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-300m",
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": 0.0,
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": 0.0,
58
+ "hidden_size": 1024,
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 4096,
61
+ "layer_norm_eps": 1e-05,
62
+ "layerdrop": 0.0,
63
+ "mask_feature_length": 10,
64
+ "mask_feature_min_masks": 0,
65
+ "mask_feature_prob": 0.0,
66
+ "mask_time_length": 10,
67
+ "mask_time_min_masks": 2,
68
+ "mask_time_prob": 0.05,
69
+ "model_type": "wav2vec2",
70
+ "num_adapter_layers": 3,
71
+ "num_attention_heads": 16,
72
+ "num_codevector_groups": 2,
73
+ "num_codevectors_per_group": 320,
74
+ "num_conv_pos_embedding_groups": 16,
75
+ "num_conv_pos_embeddings": 128,
76
+ "num_feat_extract_layers": 7,
77
+ "num_hidden_layers": 24,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 1024,
80
+ "pad_token_id": 66,
81
+ "proj_codevector_dim": 768,
82
+ "tdnn_dilation": [
83
+ 1,
84
+ 2,
85
+ 3,
86
+ 1,
87
+ 1
88
+ ],
89
+ "tdnn_dim": [
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 1500
95
+ ],
96
+ "tdnn_kernel": [
97
+ 5,
98
+ 3,
99
+ 3,
100
+ 1,
101
+ 1
102
+ ],
103
+ "torch_dtype": "float32",
104
+ "transformers_version": "4.27.0.dev0",
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": 69,
107
+ "xvector_output_dim": 512
108
+ }
checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47931e7d674efa8f03cdef5410f88e89c2d0266c5c5998e3157dc5071867cdf1
3
+ size 2490626757
checkpoint-3000/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
+ }
checkpoint-3000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e009881813edf8a917493333ad86b2849d64f322d5ae02aad4290fa00ba4773c
3
+ size 1262184749
checkpoint-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:341e6596d9b09897e9ed4af2fe41564a0cafd7e5b3f7a3b0e75abee148463401
3
+ size 14575
checkpoint-3000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52d0da51680452d79c60669d4d54e23b299030d7fa206229aaedbb353d845b00
3
+ size 557
checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc0bd1d9d77a480b911190405fceef2d45bd78a636445ffc02575a6053dbaa53
3
+ size 627
checkpoint-3000/trainer_state.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.4096385542168672,
5
+ "global_step": 3000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 0.0,
13
+ "loss": 36.5036,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.4,
18
+ "learning_rate": 4.96e-05,
19
+ "loss": 8.5484,
20
+ "step": 500
21
+ },
22
+ {
23
+ "epoch": 0.4,
24
+ "eval_cer": 1.0,
25
+ "eval_clean_cer": 1.0,
26
+ "eval_loss": 3.6234467029571533,
27
+ "eval_runtime": 384.6662,
28
+ "eval_samples_per_second": 19.9,
29
+ "eval_steps_per_second": 1.245,
30
+ "eval_wer": 1.0,
31
+ "learning_rate": 4.96e-05,
32
+ "step": 500
33
+ },
34
+ {
35
+ "epoch": 0.8,
36
+ "learning_rate": 4.792887029288703e-05,
37
+ "loss": 3.2275,
38
+ "step": 1000
39
+ },
40
+ {
41
+ "epoch": 0.8,
42
+ "eval_cer": 0.7080718890168877,
43
+ "eval_clean_cer": 0.653960461430081,
44
+ "eval_loss": 2.2960469722747803,
45
+ "eval_runtime": 383.0083,
46
+ "eval_samples_per_second": 19.987,
47
+ "eval_steps_per_second": 1.251,
48
+ "eval_wer": 0.9997886281969985,
49
+ "learning_rate": 4.792887029288703e-05,
50
+ "step": 1000
51
+ },
52
+ {
53
+ "epoch": 1.2,
54
+ "learning_rate": 4.5841004184100424e-05,
55
+ "loss": 0.9955,
56
+ "step": 1500
57
+ },
58
+ {
59
+ "epoch": 1.2,
60
+ "eval_cer": 0.43273425819260275,
61
+ "eval_clean_cer": 0.37557605377480335,
62
+ "eval_loss": 1.2224403619766235,
63
+ "eval_runtime": 382.1035,
64
+ "eval_samples_per_second": 20.034,
65
+ "eval_steps_per_second": 1.254,
66
+ "eval_wer": 0.9549127684828382,
67
+ "learning_rate": 4.5841004184100424e-05,
68
+ "step": 1500
69
+ },
70
+ {
71
+ "epoch": 1.61,
72
+ "learning_rate": 4.37489539748954e-05,
73
+ "loss": 0.66,
74
+ "step": 2000
75
+ },
76
+ {
77
+ "epoch": 1.61,
78
+ "eval_cer": 0.36509166891345374,
79
+ "eval_clean_cer": 0.304027973464835,
80
+ "eval_loss": 0.9558963775634766,
81
+ "eval_runtime": 380.573,
82
+ "eval_samples_per_second": 20.114,
83
+ "eval_steps_per_second": 1.259,
84
+ "eval_wer": 0.9231907386631546,
85
+ "learning_rate": 4.37489539748954e-05,
86
+ "step": 2000
87
+ },
88
+ {
89
+ "epoch": 2.01,
90
+ "learning_rate": 4.1665271966527195e-05,
91
+ "loss": 0.546,
92
+ "step": 2500
93
+ },
94
+ {
95
+ "epoch": 2.01,
96
+ "eval_cer": 0.3585320718645065,
97
+ "eval_clean_cer": 0.2825745567688153,
98
+ "eval_loss": 0.920676589012146,
99
+ "eval_runtime": 379.317,
100
+ "eval_samples_per_second": 20.181,
101
+ "eval_steps_per_second": 1.263,
102
+ "eval_wer": 0.948051314570021,
103
+ "learning_rate": 4.1665271966527195e-05,
104
+ "step": 2500
105
+ },
106
+ {
107
+ "epoch": 2.41,
108
+ "learning_rate": 3.957740585774059e-05,
109
+ "loss": 0.4459,
110
+ "step": 3000
111
+ },
112
+ {
113
+ "epoch": 2.41,
114
+ "eval_cer": 0.29398698497512193,
115
+ "eval_clean_cer": 0.23832115181401903,
116
+ "eval_loss": 0.7700594067573547,
117
+ "eval_runtime": 382.0036,
118
+ "eval_samples_per_second": 20.039,
119
+ "eval_steps_per_second": 1.254,
120
+ "eval_wer": 0.869307188267239,
121
+ "learning_rate": 3.957740585774059e-05,
122
+ "step": 3000
123
+ }
124
+ ],
125
+ "max_steps": 12450,
126
+ "num_train_epochs": 10,
127
+ "total_flos": 3.2256636479360102e+19,
128
+ "trial_name": null,
129
+ "trial_params": null
130
+ }
checkpoint-3000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5202a12b1552089ddded38ec8212e923965f6e5e5e1bf9a39ed5b7bedc1d608
3
+ size 3515
config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-300m",
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": 0.0,
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": 0.0,
58
+ "hidden_size": 1024,
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 4096,
61
+ "layer_norm_eps": 1e-05,
62
+ "layerdrop": 0.0,
63
+ "mask_feature_length": 10,
64
+ "mask_feature_min_masks": 0,
65
+ "mask_feature_prob": 0.0,
66
+ "mask_time_length": 10,
67
+ "mask_time_min_masks": 2,
68
+ "mask_time_prob": 0.05,
69
+ "model_type": "wav2vec2",
70
+ "num_adapter_layers": 3,
71
+ "num_attention_heads": 16,
72
+ "num_codevector_groups": 2,
73
+ "num_codevectors_per_group": 320,
74
+ "num_conv_pos_embedding_groups": 16,
75
+ "num_conv_pos_embeddings": 128,
76
+ "num_feat_extract_layers": 7,
77
+ "num_hidden_layers": 24,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 1024,
80
+ "pad_token_id": 66,
81
+ "proj_codevector_dim": 768,
82
+ "tdnn_dilation": [
83
+ 1,
84
+ 2,
85
+ 3,
86
+ 1,
87
+ 1
88
+ ],
89
+ "tdnn_dim": [
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 1500
95
+ ],
96
+ "tdnn_kernel": [
97
+ 5,
98
+ 3,
99
+ 3,
100
+ 1,
101
+ 1
102
+ ],
103
+ "torch_dtype": "float32",
104
+ "transformers_version": "4.27.0.dev0",
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": 69,
107
+ "xvector_output_dim": 512
108
+ }
logs/1675161831.778444/events.out.tfevents.1675161831.31efd5474bec.3677.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf86a4de603261a10a633962dedb406b0cfd25cb5828fa52d377e24e5993c783
3
+ size 5666
logs/events.out.tfevents.1675161831.31efd5474bec.3677.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:403a9baba2d0676983a9c1601de944f429143187f414d73503285e4a555cbaf8
3
+ size 9187
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:e009881813edf8a917493333ad86b2849d64f322d5ae02aad4290fa00ba4773c
3
+ size 1262184749
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5202a12b1552089ddded38ec8212e923965f6e5e5e1bf9a39ed5b7bedc1d608
3
+ size 3515