Hugging Face's logo

dima806
/
speech-accent-classification

Audio Classification
Transformers
PyTorch
Safetensors
English
wav2vec2
Inference Endpoints
Model card Files Community
1
dima806 commited on
Commit
3725c67
•
1 Parent(s): b75bb62

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-1188/config.json +113 -0
  2. checkpoint-1188/optimizer.pt +3 -0
  3. checkpoint-1188/preprocessor_config.json +9 -0
  4. checkpoint-1188/pytorch_model.bin +3 -0
  5. checkpoint-1188/rng_state.pth +3 -0
  6. checkpoint-1188/scheduler.pt +3 -0
  7. checkpoint-1188/trainer_state.json +0 -0
  8. checkpoint-1188/training_args.bin +3 -0
  9. checkpoint-1584/config.json +113 -0
  10. checkpoint-1584/optimizer.pt +3 -0
  11. checkpoint-1584/preprocessor_config.json +9 -0
  12. checkpoint-1584/pytorch_model.bin +3 -0
  13. checkpoint-1584/rng_state.pth +3 -0
  14. checkpoint-1584/scheduler.pt +3 -0
  15. checkpoint-1584/trainer_state.json +0 -0
  16. checkpoint-1584/training_args.bin +3 -0
  17. checkpoint-1980/config.json +113 -0
  18. checkpoint-1980/optimizer.pt +3 -0
  19. checkpoint-1980/preprocessor_config.json +9 -0
  20. checkpoint-1980/pytorch_model.bin +3 -0
  21. checkpoint-1980/rng_state.pth +3 -0
  22. checkpoint-1980/scheduler.pt +3 -0
  23. checkpoint-1980/trainer_state.json +0 -0
  24. checkpoint-1980/training_args.bin +3 -0
  25. checkpoint-2376/config.json +113 -0
  26. checkpoint-2376/optimizer.pt +3 -0
  27. checkpoint-2376/preprocessor_config.json +9 -0
  28. checkpoint-2376/pytorch_model.bin +3 -0
  29. checkpoint-2376/rng_state.pth +3 -0
  30. checkpoint-2376/scheduler.pt +3 -0
  31. checkpoint-2376/trainer_state.json +0 -0
  32. checkpoint-2376/training_args.bin +3 -0
  33. checkpoint-2772/config.json +113 -0
  34. checkpoint-2772/optimizer.pt +3 -0
  35. checkpoint-2772/preprocessor_config.json +9 -0
  36. checkpoint-2772/pytorch_model.bin +3 -0
  37. checkpoint-2772/rng_state.pth +3 -0
  38. checkpoint-2772/scheduler.pt +3 -0
  39. checkpoint-2772/trainer_state.json +0 -0
  40. checkpoint-2772/training_args.bin +3 -0
  41. checkpoint-3168/config.json +113 -0
  42. checkpoint-3168/optimizer.pt +3 -0
  43. checkpoint-3168/preprocessor_config.json +9 -0
  44. checkpoint-3168/pytorch_model.bin +3 -0
  45. checkpoint-3168/rng_state.pth +3 -0
  46. checkpoint-3168/scheduler.pt +3 -0
  47. checkpoint-3168/trainer_state.json +0 -0
  48. checkpoint-3168/training_args.bin +3 -0
  49. checkpoint-3564/config.json +113 -0
  50. checkpoint-3564/optimizer.pt +3 -0
checkpoint-1188/config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-960h",
3
+ "activation_dropout": 0.1,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSequenceClassification"
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": "sum",
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_dropout": 0.0,
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.1,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_dropout_prob": 0.1,
59
+ "hidden_size": 768,
60
+ "id2label": {
61
+ "0": "Foreign",
62
+ "1": "Native"
63
+ },
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 3072,
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.1,
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_prob": 0.05,
74
+ "model_type": "wav2vec2",
75
+ "num_adapter_layers": 3,
76
+ "num_attention_heads": 12,
77
+ "num_codevector_groups": 2,
78
+ "num_codevectors_per_group": 320,
79
+ "num_conv_pos_embedding_groups": 16,
80
+ "num_conv_pos_embeddings": 128,
81
+ "num_feat_extract_layers": 7,
82
+ "num_hidden_layers": 12,
83
+ "num_negatives": 100,
84
+ "output_hidden_size": 768,
85
+ "pad_token_id": 0,
86
+ "proj_codevector_dim": 256,
87
+ "tdnn_dilation": [
88
+ 1,
89
+ 2,
90
+ 3,
91
+ 1,
92
+ 1
93
+ ],
94
+ "tdnn_dim": [
95
+ 512,
96
+ 512,
97
+ 512,
98
+ 512,
99
+ 1500
100
+ ],
101
+ "tdnn_kernel": [
102
+ 5,
103
+ 3,
104
+ 3,
105
+ 1,
106
+ 1
107
+ ],
108
+ "torch_dtype": "float32",
109
+ "transformers_version": "4.28.1",
110
+ "use_weighted_layer_sum": false,
111
+ "vocab_size": 32,
112
+ "xvector_output_dim": 512
113
+ }
checkpoint-1188/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6927087e0b8865c0180e983f5ea462633228691b4ffcad35054391c508557549
3
+ size 756677477
checkpoint-1188/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": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-1188/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd0d811da4fb0cfac1f876ced9df766e19da5c76dfb9b9cd94f0bd7b3fdcce39
3
+ size 378348563
checkpoint-1188/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c762f8bb79cfca006e8b4206ef0e021670190bc0b380b067527cfb02322e2fc3
3
+ size 14631
checkpoint-1188/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a97e6e42c229abac35a91863edb487f02fb88823244bbb46e7338ea079d4fb4
3
+ size 623
checkpoint-1188/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1188/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7db14439c369bfe9c89f64ff38f0b2d3fcc53911fc2c0b12a3a7d04656e7384a
3
+ size 3503
checkpoint-1584/config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-960h",
3
+ "activation_dropout": 0.1,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSequenceClassification"
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": "sum",
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_dropout": 0.0,
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.1,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_dropout_prob": 0.1,
59
+ "hidden_size": 768,
60
+ "id2label": {
61
+ "0": "Foreign",
62
+ "1": "Native"
63
+ },
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 3072,
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.1,
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_prob": 0.05,
74
+ "model_type": "wav2vec2",
75
+ "num_adapter_layers": 3,
76
+ "num_attention_heads": 12,
77
+ "num_codevector_groups": 2,
78
+ "num_codevectors_per_group": 320,
79
+ "num_conv_pos_embedding_groups": 16,
80
+ "num_conv_pos_embeddings": 128,
81
+ "num_feat_extract_layers": 7,
82
+ "num_hidden_layers": 12,
83
+ "num_negatives": 100,
84
+ "output_hidden_size": 768,
85
+ "pad_token_id": 0,
86
+ "proj_codevector_dim": 256,
87
+ "tdnn_dilation": [
88
+ 1,
89
+ 2,
90
+ 3,
91
+ 1,
92
+ 1
93
+ ],
94
+ "tdnn_dim": [
95
+ 512,
96
+ 512,
97
+ 512,
98
+ 512,
99
+ 1500
100
+ ],
101
+ "tdnn_kernel": [
102
+ 5,
103
+ 3,
104
+ 3,
105
+ 1,
106
+ 1
107
+ ],
108
+ "torch_dtype": "float32",
109
+ "transformers_version": "4.28.1",
110
+ "use_weighted_layer_sum": false,
111
+ "vocab_size": 32,
112
+ "xvector_output_dim": 512
113
+ }
checkpoint-1584/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97f0993b621c25d8592902e4e8228f4c10e5d60ccfbbe699e0809df117c76619
3
+ size 756677477
checkpoint-1584/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": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-1584/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d312aab2192f2c6ad837fe9faa7663c78d9b1914e5bb72cd670d6a9d86c877d
3
+ size 378348563
checkpoint-1584/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0789e5162b4faec730579ea3006c9e972645bf6ca3f783cc8f5e254a0f9f3f02
3
+ size 14567
checkpoint-1584/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac439ca05576f5000d0f9bd8a9fbe56cdda19ab74e39b0502bfc5ea1a4f0613d
3
+ size 623
checkpoint-1584/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1584/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7db14439c369bfe9c89f64ff38f0b2d3fcc53911fc2c0b12a3a7d04656e7384a
3
+ size 3503
checkpoint-1980/config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-960h",
3
+ "activation_dropout": 0.1,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSequenceClassification"
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": "sum",
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_dropout": 0.0,
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.1,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_dropout_prob": 0.1,
59
+ "hidden_size": 768,
60
+ "id2label": {
61
+ "0": "Foreign",
62
+ "1": "Native"
63
+ },
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 3072,
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.1,
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_prob": 0.05,
74
+ "model_type": "wav2vec2",
75
+ "num_adapter_layers": 3,
76
+ "num_attention_heads": 12,
77
+ "num_codevector_groups": 2,
78
+ "num_codevectors_per_group": 320,
79
+ "num_conv_pos_embedding_groups": 16,
80
+ "num_conv_pos_embeddings": 128,
81
+ "num_feat_extract_layers": 7,
82
+ "num_hidden_layers": 12,
83
+ "num_negatives": 100,
84
+ "output_hidden_size": 768,
85
+ "pad_token_id": 0,
86
+ "proj_codevector_dim": 256,
87
+ "tdnn_dilation": [
88
+ 1,
89
+ 2,
90
+ 3,
91
+ 1,
92
+ 1
93
+ ],
94
+ "tdnn_dim": [
95
+ 512,
96
+ 512,
97
+ 512,
98
+ 512,
99
+ 1500
100
+ ],
101
+ "tdnn_kernel": [
102
+ 5,
103
+ 3,
104
+ 3,
105
+ 1,
106
+ 1
107
+ ],
108
+ "torch_dtype": "float32",
109
+ "transformers_version": "4.28.1",
110
+ "use_weighted_layer_sum": false,
111
+ "vocab_size": 32,
112
+ "xvector_output_dim": 512
113
+ }
checkpoint-1980/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef2af0605afa1a43a02b20603c395961dc7319d54a4fe06873cb388f2977cdc1
3
+ size 756677477
checkpoint-1980/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": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-1980/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d57280519ffd40f6fca295963a4db126c049cdcac69c222f30bc68398060c5
3
+ size 378348563
checkpoint-1980/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4a0d3f377cf41bc60bb1cbe5a284d4a18c47056f8a2e805f0420bd6bd52fdcd
3
+ size 14631
checkpoint-1980/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3192417d69cb3637bbe702cbf00e51984fbc3d22ce07e248105a71df9a183a81
3
+ size 623
checkpoint-1980/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1980/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7db14439c369bfe9c89f64ff38f0b2d3fcc53911fc2c0b12a3a7d04656e7384a
3
+ size 3503
checkpoint-2376/config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-960h",
3
+ "activation_dropout": 0.1,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSequenceClassification"
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": "sum",
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_dropout": 0.0,
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.1,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_dropout_prob": 0.1,
59
+ "hidden_size": 768,
60
+ "id2label": {
61
+ "0": "Foreign",
62
+ "1": "Native"
63
+ },
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 3072,
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.1,
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_prob": 0.05,
74
+ "model_type": "wav2vec2",
75
+ "num_adapter_layers": 3,
76
+ "num_attention_heads": 12,
77
+ "num_codevector_groups": 2,
78
+ "num_codevectors_per_group": 320,
79
+ "num_conv_pos_embedding_groups": 16,
80
+ "num_conv_pos_embeddings": 128,
81
+ "num_feat_extract_layers": 7,
82
+ "num_hidden_layers": 12,
83
+ "num_negatives": 100,
84
+ "output_hidden_size": 768,
85
+ "pad_token_id": 0,
86
+ "proj_codevector_dim": 256,
87
+ "tdnn_dilation": [
88
+ 1,
89
+ 2,
90
+ 3,
91
+ 1,
92
+ 1
93
+ ],
94
+ "tdnn_dim": [
95
+ 512,
96
+ 512,
97
+ 512,
98
+ 512,
99
+ 1500
100
+ ],
101
+ "tdnn_kernel": [
102
+ 5,
103
+ 3,
104
+ 3,
105
+ 1,
106
+ 1
107
+ ],
108
+ "torch_dtype": "float32",
109
+ "transformers_version": "4.28.1",
110
+ "use_weighted_layer_sum": false,
111
+ "vocab_size": 32,
112
+ "xvector_output_dim": 512
113
+ }
checkpoint-2376/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:364b7ac4a1fc23737a02788a40f1a5c741826bf5b6a9e248d8e3504131444587
3
+ size 756677477
checkpoint-2376/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": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-2376/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:415f32f77f5fa3a5892d605f9d3333aa719e7abc96aeb959f4818f6f245a6837
3
+ size 378348563
checkpoint-2376/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5c9d21d29b879455b34a95f363cc8e14f1416bfc5400268d4f39c9b188a7868
3
+ size 14567
checkpoint-2376/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e2bdd50e7407a607d0e5b5c929ea1ed3e3d72d13d158e9ef94854fe3672d5d9
3
+ size 623
checkpoint-2376/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2376/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7db14439c369bfe9c89f64ff38f0b2d3fcc53911fc2c0b12a3a7d04656e7384a
3
+ size 3503
checkpoint-2772/config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-960h",
3
+ "activation_dropout": 0.1,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSequenceClassification"
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": "sum",
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_dropout": 0.0,
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.1,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_dropout_prob": 0.1,
59
+ "hidden_size": 768,
60
+ "id2label": {
61
+ "0": "Foreign",
62
+ "1": "Native"
63
+ },
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 3072,
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.1,
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_prob": 0.05,
74
+ "model_type": "wav2vec2",
75
+ "num_adapter_layers": 3,
76
+ "num_attention_heads": 12,
77
+ "num_codevector_groups": 2,
78
+ "num_codevectors_per_group": 320,
79
+ "num_conv_pos_embedding_groups": 16,
80
+ "num_conv_pos_embeddings": 128,
81
+ "num_feat_extract_layers": 7,
82
+ "num_hidden_layers": 12,
83
+ "num_negatives": 100,
84
+ "output_hidden_size": 768,
85
+ "pad_token_id": 0,
86
+ "proj_codevector_dim": 256,
87
+ "tdnn_dilation": [
88
+ 1,
89
+ 2,
90
+ 3,
91
+ 1,
92
+ 1
93
+ ],
94
+ "tdnn_dim": [
95
+ 512,
96
+ 512,
97
+ 512,
98
+ 512,
99
+ 1500
100
+ ],
101
+ "tdnn_kernel": [
102
+ 5,
103
+ 3,
104
+ 3,
105
+ 1,
106
+ 1
107
+ ],
108
+ "torch_dtype": "float32",
109
+ "transformers_version": "4.28.1",
110
+ "use_weighted_layer_sum": false,
111
+ "vocab_size": 32,
112
+ "xvector_output_dim": 512
113
+ }
checkpoint-2772/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c264e7bf6fe789709415bc8d52c8cca90c135d95e166e43894a890afceea5740
3
+ size 756677477
checkpoint-2772/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": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-2772/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be25b1cf5abc0d6b168daf371d06f0d6bbfe5b96fd13fa28bbcb6bc9412f5a22
3
+ size 378348563
checkpoint-2772/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:687640bdbf44b06437495d532a6ac86d76b3463b3987b834b64923f55e0620bc
3
+ size 14567
checkpoint-2772/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2de1862758096179f75546f36910749e35629f9cdd45e31ebee79dc077f88ab4
3
+ size 623
checkpoint-2772/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2772/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7db14439c369bfe9c89f64ff38f0b2d3fcc53911fc2c0b12a3a7d04656e7384a
3
+ size 3503
checkpoint-3168/config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-960h",
3
+ "activation_dropout": 0.1,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSequenceClassification"
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": "sum",
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_dropout": 0.0,
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.1,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_dropout_prob": 0.1,
59
+ "hidden_size": 768,
60
+ "id2label": {
61
+ "0": "Foreign",
62
+ "1": "Native"
63
+ },
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 3072,
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.1,
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_prob": 0.05,
74
+ "model_type": "wav2vec2",
75
+ "num_adapter_layers": 3,
76
+ "num_attention_heads": 12,
77
+ "num_codevector_groups": 2,
78
+ "num_codevectors_per_group": 320,
79
+ "num_conv_pos_embedding_groups": 16,
80
+ "num_conv_pos_embeddings": 128,
81
+ "num_feat_extract_layers": 7,
82
+ "num_hidden_layers": 12,
83
+ "num_negatives": 100,
84
+ "output_hidden_size": 768,
85
+ "pad_token_id": 0,
86
+ "proj_codevector_dim": 256,
87
+ "tdnn_dilation": [
88
+ 1,
89
+ 2,
90
+ 3,
91
+ 1,
92
+ 1
93
+ ],
94
+ "tdnn_dim": [
95
+ 512,
96
+ 512,
97
+ 512,
98
+ 512,
99
+ 1500
100
+ ],
101
+ "tdnn_kernel": [
102
+ 5,
103
+ 3,
104
+ 3,
105
+ 1,
106
+ 1
107
+ ],
108
+ "torch_dtype": "float32",
109
+ "transformers_version": "4.28.1",
110
+ "use_weighted_layer_sum": false,
111
+ "vocab_size": 32,
112
+ "xvector_output_dim": 512
113
+ }
checkpoint-3168/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d4c416ca93e1fd87f98bb15c654e7ffe94cff6f9a1e3b956ff5e9466c8f8bf6
3
+ size 756677477
checkpoint-3168/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": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-3168/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c085ef8016a5c49e77e50273e4a0e4c333045fff483f59d6035aa36b20382423
3
+ size 378348563
checkpoint-3168/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9675e845f259340915beb46dbee1633c9941c5cf94e84de3add30732d4a76d6a
3
+ size 14567
checkpoint-3168/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:703a8c430c945a695d14caa02ab8a8b1465c1b636a8f2e8dfd1aa7709108607b
3
+ size 623
checkpoint-3168/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3168/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7db14439c369bfe9c89f64ff38f0b2d3fcc53911fc2c0b12a3a7d04656e7384a
3
+ size 3503
checkpoint-3564/config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-960h",
3
+ "activation_dropout": 0.1,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSequenceClassification"
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": "sum",
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_dropout": 0.0,
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.1,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_dropout_prob": 0.1,
59
+ "hidden_size": 768,
60
+ "id2label": {
61
+ "0": "Foreign",
62
+ "1": "Native"
63
+ },
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 3072,
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.1,
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_prob": 0.05,
74
+ "model_type": "wav2vec2",
75
+ "num_adapter_layers": 3,
76
+ "num_attention_heads": 12,
77
+ "num_codevector_groups": 2,
78
+ "num_codevectors_per_group": 320,
79
+ "num_conv_pos_embedding_groups": 16,
80
+ "num_conv_pos_embeddings": 128,
81
+ "num_feat_extract_layers": 7,
82
+ "num_hidden_layers": 12,
83
+ "num_negatives": 100,
84
+ "output_hidden_size": 768,
85
+ "pad_token_id": 0,
86
+ "proj_codevector_dim": 256,
87
+ "tdnn_dilation": [
88
+ 1,
89
+ 2,
90
+ 3,
91
+ 1,
92
+ 1
93
+ ],
94
+ "tdnn_dim": [
95
+ 512,
96
+ 512,
97
+ 512,
98
+ 512,
99
+ 1500
100
+ ],
101
+ "tdnn_kernel": [
102
+ 5,
103
+ 3,
104
+ 3,
105
+ 1,
106
+ 1
107
+ ],
108
+ "torch_dtype": "float32",
109
+ "transformers_version": "4.28.1",
110
+ "use_weighted_layer_sum": false,
111
+ "vocab_size": 32,
112
+ "xvector_output_dim": 512
113
+ }
checkpoint-3564/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d9bd6b60cd229d78ae29b1f74924d0c6347b2f90c1716edb3614940feee3bc8
3
+ size 756677477