Hugging Face's logo

dima806
/
multiple_accent_classification

Audio Classification
Transformers
PyTorch
Safetensors
wav2vec2
Inference Endpoints
Model card Files Community
1
dima806 commited on
Commit
751b029
•
1 Parent(s): 237e7e8

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-1390/config.json +125 -0
  2. checkpoint-1390/optimizer.pt +3 -0
  3. checkpoint-1390/preprocessor_config.json +9 -0
  4. checkpoint-1390/pytorch_model.bin +3 -0
  5. checkpoint-1390/rng_state.pth +3 -0
  6. checkpoint-1390/scheduler.pt +3 -0
  7. checkpoint-1390/trainer_state.json +0 -0
  8. checkpoint-1390/training_args.bin +3 -0
  9. checkpoint-2085/config.json +125 -0
  10. checkpoint-2085/optimizer.pt +3 -0
  11. checkpoint-2085/preprocessor_config.json +9 -0
  12. checkpoint-2085/pytorch_model.bin +3 -0
  13. checkpoint-2085/rng_state.pth +3 -0
  14. checkpoint-2085/scheduler.pt +3 -0
  15. checkpoint-2085/trainer_state.json +0 -0
  16. checkpoint-2085/training_args.bin +3 -0
  17. checkpoint-2780/config.json +125 -0
  18. checkpoint-2780/optimizer.pt +3 -0
  19. checkpoint-2780/preprocessor_config.json +9 -0
  20. checkpoint-2780/pytorch_model.bin +3 -0
  21. checkpoint-2780/rng_state.pth +3 -0
  22. checkpoint-2780/scheduler.pt +3 -0
  23. checkpoint-2780/trainer_state.json +0 -0
  24. checkpoint-2780/training_args.bin +3 -0
  25. checkpoint-3475/config.json +125 -0
  26. checkpoint-3475/optimizer.pt +3 -0
  27. checkpoint-3475/preprocessor_config.json +9 -0
  28. checkpoint-3475/pytorch_model.bin +3 -0
  29. checkpoint-3475/rng_state.pth +3 -0
  30. checkpoint-3475/scheduler.pt +3 -0
  31. checkpoint-3475/trainer_state.json +0 -0
  32. checkpoint-3475/training_args.bin +3 -0
  33. checkpoint-4170/config.json +125 -0
  34. checkpoint-4170/optimizer.pt +3 -0
  35. checkpoint-4170/preprocessor_config.json +9 -0
  36. checkpoint-4170/pytorch_model.bin +3 -0
  37. checkpoint-4170/rng_state.pth +3 -0
  38. checkpoint-4170/scheduler.pt +3 -0
  39. checkpoint-4170/trainer_state.json +0 -0
  40. checkpoint-4170/training_args.bin +3 -0
  41. checkpoint-4865/config.json +125 -0
  42. checkpoint-4865/optimizer.pt +3 -0
  43. checkpoint-4865/preprocessor_config.json +9 -0
  44. checkpoint-4865/pytorch_model.bin +3 -0
  45. checkpoint-4865/rng_state.pth +3 -0
  46. checkpoint-4865/scheduler.pt +3 -0
  47. checkpoint-4865/trainer_state.json +0 -0
  48. checkpoint-4865/training_args.bin +3 -0
  49. checkpoint-5560/config.json +125 -0
  50. checkpoint-5560/optimizer.pt +3 -0
checkpoint-1390/config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "english",
62
+ "1": "spanish",
63
+ "2": "arabic",
64
+ "3": "french",
65
+ "4": "mandarin",
66
+ "5": "other"
67
+ },
68
+ "initializer_range": 0.02,
69
+ "intermediate_size": 3072,
70
+ "label2id": {
71
+ "LABEL_0": 0,
72
+ "LABEL_1": 1,
73
+ "LABEL_2": 2,
74
+ "LABEL_3": 3,
75
+ "LABEL_4": 4,
76
+ "LABEL_5": 5
77
+ },
78
+ "layer_norm_eps": 1e-05,
79
+ "layerdrop": 0.1,
80
+ "mask_feature_length": 10,
81
+ "mask_feature_min_masks": 0,
82
+ "mask_feature_prob": 0.0,
83
+ "mask_time_length": 10,
84
+ "mask_time_min_masks": 2,
85
+ "mask_time_prob": 0.05,
86
+ "model_type": "wav2vec2",
87
+ "num_adapter_layers": 3,
88
+ "num_attention_heads": 12,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 12,
95
+ "num_negatives": 100,
96
+ "output_hidden_size": 768,
97
+ "pad_token_id": 0,
98
+ "proj_codevector_dim": 256,
99
+ "tdnn_dilation": [
100
+ 1,
101
+ 2,
102
+ 3,
103
+ 1,
104
+ 1
105
+ ],
106
+ "tdnn_dim": [
107
+ 512,
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 1500
112
+ ],
113
+ "tdnn_kernel": [
114
+ 5,
115
+ 3,
116
+ 3,
117
+ 1,
118
+ 1
119
+ ],
120
+ "torch_dtype": "float32",
121
+ "transformers_version": "4.28.1",
122
+ "use_weighted_layer_sum": false,
123
+ "vocab_size": 32,
124
+ "xvector_output_dim": 512
125
+ }
checkpoint-1390/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dba9a3d3689ab22fb66cb27fda7bd6656a3e069ce7512547e79f6521b703cf5
3
+ size 756685669
checkpoint-1390/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-1390/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d870c46842a1cbc97d5bce9d68d29fc86f7f8b01465600ee651d0544c5134e
3
+ size 378352659
checkpoint-1390/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09ab720adb20af6df73c6afad40f8d19762c9f925417561f368ec0b44f220c4f
3
+ size 14567
checkpoint-1390/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15bc70771c8dc62fe6199258c446b2652a15dafb01a698f8ea5f4b69ac58e26e
3
+ size 623
checkpoint-1390/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1390/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e586ffec83af94e0cf9ea31750e6c3ca1bf1ee016bdd398b7fe339f74b71c58
3
+ size 3567
checkpoint-2085/config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "english",
62
+ "1": "spanish",
63
+ "2": "arabic",
64
+ "3": "french",
65
+ "4": "mandarin",
66
+ "5": "other"
67
+ },
68
+ "initializer_range": 0.02,
69
+ "intermediate_size": 3072,
70
+ "label2id": {
71
+ "LABEL_0": 0,
72
+ "LABEL_1": 1,
73
+ "LABEL_2": 2,
74
+ "LABEL_3": 3,
75
+ "LABEL_4": 4,
76
+ "LABEL_5": 5
77
+ },
78
+ "layer_norm_eps": 1e-05,
79
+ "layerdrop": 0.1,
80
+ "mask_feature_length": 10,
81
+ "mask_feature_min_masks": 0,
82
+ "mask_feature_prob": 0.0,
83
+ "mask_time_length": 10,
84
+ "mask_time_min_masks": 2,
85
+ "mask_time_prob": 0.05,
86
+ "model_type": "wav2vec2",
87
+ "num_adapter_layers": 3,
88
+ "num_attention_heads": 12,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 12,
95
+ "num_negatives": 100,
96
+ "output_hidden_size": 768,
97
+ "pad_token_id": 0,
98
+ "proj_codevector_dim": 256,
99
+ "tdnn_dilation": [
100
+ 1,
101
+ 2,
102
+ 3,
103
+ 1,
104
+ 1
105
+ ],
106
+ "tdnn_dim": [
107
+ 512,
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 1500
112
+ ],
113
+ "tdnn_kernel": [
114
+ 5,
115
+ 3,
116
+ 3,
117
+ 1,
118
+ 1
119
+ ],
120
+ "torch_dtype": "float32",
121
+ "transformers_version": "4.28.1",
122
+ "use_weighted_layer_sum": false,
123
+ "vocab_size": 32,
124
+ "xvector_output_dim": 512
125
+ }
checkpoint-2085/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c439813f3f829ce34679e8b80afc75be5fbafacb7619d3e6434edc77b10d880
3
+ size 756685669
checkpoint-2085/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-2085/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:773dfcd5d87c0bb990f9e976e3754e7e15a3fef82d4f8e1a038de1c1154fc26c
3
+ size 378352659
checkpoint-2085/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:701e95ed7267123ba519a0235a69162f64ce36e9a452f51a9e0222bab0ca3a36
3
+ size 14567
checkpoint-2085/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27938b4a7ab63b8a6f6318a2da4f4938012468ddd2c83dbf284d9ff66e9f3656
3
+ size 623
checkpoint-2085/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2085/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e586ffec83af94e0cf9ea31750e6c3ca1bf1ee016bdd398b7fe339f74b71c58
3
+ size 3567
checkpoint-2780/config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "english",
62
+ "1": "spanish",
63
+ "2": "arabic",
64
+ "3": "french",
65
+ "4": "mandarin",
66
+ "5": "other"
67
+ },
68
+ "initializer_range": 0.02,
69
+ "intermediate_size": 3072,
70
+ "label2id": {
71
+ "LABEL_0": 0,
72
+ "LABEL_1": 1,
73
+ "LABEL_2": 2,
74
+ "LABEL_3": 3,
75
+ "LABEL_4": 4,
76
+ "LABEL_5": 5
77
+ },
78
+ "layer_norm_eps": 1e-05,
79
+ "layerdrop": 0.1,
80
+ "mask_feature_length": 10,
81
+ "mask_feature_min_masks": 0,
82
+ "mask_feature_prob": 0.0,
83
+ "mask_time_length": 10,
84
+ "mask_time_min_masks": 2,
85
+ "mask_time_prob": 0.05,
86
+ "model_type": "wav2vec2",
87
+ "num_adapter_layers": 3,
88
+ "num_attention_heads": 12,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 12,
95
+ "num_negatives": 100,
96
+ "output_hidden_size": 768,
97
+ "pad_token_id": 0,
98
+ "proj_codevector_dim": 256,
99
+ "tdnn_dilation": [
100
+ 1,
101
+ 2,
102
+ 3,
103
+ 1,
104
+ 1
105
+ ],
106
+ "tdnn_dim": [
107
+ 512,
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 1500
112
+ ],
113
+ "tdnn_kernel": [
114
+ 5,
115
+ 3,
116
+ 3,
117
+ 1,
118
+ 1
119
+ ],
120
+ "torch_dtype": "float32",
121
+ "transformers_version": "4.28.1",
122
+ "use_weighted_layer_sum": false,
123
+ "vocab_size": 32,
124
+ "xvector_output_dim": 512
125
+ }
checkpoint-2780/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:834d71f1927fa5e3997bea7dd8375f5d90954ef60974e1b71971f0e4de519cba
3
+ size 756685669
checkpoint-2780/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-2780/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42b9e3df5a58141c976f6649a4c0a15f4c67bb014e6a5f9579bd8b60eb595140
3
+ size 378352659
checkpoint-2780/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5ea650b347b3b6ecee258fce29bf4b71f686495c8bbfbe370bff3d34a90df47
3
+ size 14567
checkpoint-2780/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da316c642ce53edc59b929694aa5cda251eee014f335feae6e39c42a93216c61
3
+ size 623
checkpoint-2780/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2780/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e586ffec83af94e0cf9ea31750e6c3ca1bf1ee016bdd398b7fe339f74b71c58
3
+ size 3567
checkpoint-3475/config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "english",
62
+ "1": "spanish",
63
+ "2": "arabic",
64
+ "3": "french",
65
+ "4": "mandarin",
66
+ "5": "other"
67
+ },
68
+ "initializer_range": 0.02,
69
+ "intermediate_size": 3072,
70
+ "label2id": {
71
+ "LABEL_0": 0,
72
+ "LABEL_1": 1,
73
+ "LABEL_2": 2,
74
+ "LABEL_3": 3,
75
+ "LABEL_4": 4,
76
+ "LABEL_5": 5
77
+ },
78
+ "layer_norm_eps": 1e-05,
79
+ "layerdrop": 0.1,
80
+ "mask_feature_length": 10,
81
+ "mask_feature_min_masks": 0,
82
+ "mask_feature_prob": 0.0,
83
+ "mask_time_length": 10,
84
+ "mask_time_min_masks": 2,
85
+ "mask_time_prob": 0.05,
86
+ "model_type": "wav2vec2",
87
+ "num_adapter_layers": 3,
88
+ "num_attention_heads": 12,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 12,
95
+ "num_negatives": 100,
96
+ "output_hidden_size": 768,
97
+ "pad_token_id": 0,
98
+ "proj_codevector_dim": 256,
99
+ "tdnn_dilation": [
100
+ 1,
101
+ 2,
102
+ 3,
103
+ 1,
104
+ 1
105
+ ],
106
+ "tdnn_dim": [
107
+ 512,
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 1500
112
+ ],
113
+ "tdnn_kernel": [
114
+ 5,
115
+ 3,
116
+ 3,
117
+ 1,
118
+ 1
119
+ ],
120
+ "torch_dtype": "float32",
121
+ "transformers_version": "4.28.1",
122
+ "use_weighted_layer_sum": false,
123
+ "vocab_size": 32,
124
+ "xvector_output_dim": 512
125
+ }
checkpoint-3475/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e41dcf11f5839069ac03206b2628aac37c4b5c78dd7bb51c0c340ffa8ae127ed
3
+ size 756685669
checkpoint-3475/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-3475/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2edc7253191c15c6bd80f1bf64ee31f8174bc4d0d1628b2c71a80a8ac40d3274
3
+ size 378352659
checkpoint-3475/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f10ee3c3a9763cedee0844ccf45e7435ab6fc9ed45f9c5ce0200510d7e18dc7a
3
+ size 14567
checkpoint-3475/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c884f70eb9e23c04598e0a4a050d6cd3b01180465a73986f2ce2877a449212a
3
+ size 623
checkpoint-3475/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3475/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e586ffec83af94e0cf9ea31750e6c3ca1bf1ee016bdd398b7fe339f74b71c58
3
+ size 3567
checkpoint-4170/config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "english",
62
+ "1": "spanish",
63
+ "2": "arabic",
64
+ "3": "french",
65
+ "4": "mandarin",
66
+ "5": "other"
67
+ },
68
+ "initializer_range": 0.02,
69
+ "intermediate_size": 3072,
70
+ "label2id": {
71
+ "LABEL_0": 0,
72
+ "LABEL_1": 1,
73
+ "LABEL_2": 2,
74
+ "LABEL_3": 3,
75
+ "LABEL_4": 4,
76
+ "LABEL_5": 5
77
+ },
78
+ "layer_norm_eps": 1e-05,
79
+ "layerdrop": 0.1,
80
+ "mask_feature_length": 10,
81
+ "mask_feature_min_masks": 0,
82
+ "mask_feature_prob": 0.0,
83
+ "mask_time_length": 10,
84
+ "mask_time_min_masks": 2,
85
+ "mask_time_prob": 0.05,
86
+ "model_type": "wav2vec2",
87
+ "num_adapter_layers": 3,
88
+ "num_attention_heads": 12,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 12,
95
+ "num_negatives": 100,
96
+ "output_hidden_size": 768,
97
+ "pad_token_id": 0,
98
+ "proj_codevector_dim": 256,
99
+ "tdnn_dilation": [
100
+ 1,
101
+ 2,
102
+ 3,
103
+ 1,
104
+ 1
105
+ ],
106
+ "tdnn_dim": [
107
+ 512,
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 1500
112
+ ],
113
+ "tdnn_kernel": [
114
+ 5,
115
+ 3,
116
+ 3,
117
+ 1,
118
+ 1
119
+ ],
120
+ "torch_dtype": "float32",
121
+ "transformers_version": "4.28.1",
122
+ "use_weighted_layer_sum": false,
123
+ "vocab_size": 32,
124
+ "xvector_output_dim": 512
125
+ }
checkpoint-4170/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2edba1c1b1c3335f4dde03c2ce92c4d1d15d075e9781d1b77c944bad8fecc6c0
3
+ size 756685669
checkpoint-4170/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-4170/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20fc433821d61127971c2f1328aab466ca0f311d64a4e7a27282d8e16463dad2
3
+ size 378352659
checkpoint-4170/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0effe8e8564422a13334f56cbe51d52ca56faf8eda558d2721321c8e2f634ea6
3
+ size 14567
checkpoint-4170/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6cd0777cccd29bdb2a14a71f47c31dcf996d37a7a92db4021e5b970902e41bd
3
+ size 623
checkpoint-4170/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4170/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e586ffec83af94e0cf9ea31750e6c3ca1bf1ee016bdd398b7fe339f74b71c58
3
+ size 3567
checkpoint-4865/config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "english",
62
+ "1": "spanish",
63
+ "2": "arabic",
64
+ "3": "french",
65
+ "4": "mandarin",
66
+ "5": "other"
67
+ },
68
+ "initializer_range": 0.02,
69
+ "intermediate_size": 3072,
70
+ "label2id": {
71
+ "LABEL_0": 0,
72
+ "LABEL_1": 1,
73
+ "LABEL_2": 2,
74
+ "LABEL_3": 3,
75
+ "LABEL_4": 4,
76
+ "LABEL_5": 5
77
+ },
78
+ "layer_norm_eps": 1e-05,
79
+ "layerdrop": 0.1,
80
+ "mask_feature_length": 10,
81
+ "mask_feature_min_masks": 0,
82
+ "mask_feature_prob": 0.0,
83
+ "mask_time_length": 10,
84
+ "mask_time_min_masks": 2,
85
+ "mask_time_prob": 0.05,
86
+ "model_type": "wav2vec2",
87
+ "num_adapter_layers": 3,
88
+ "num_attention_heads": 12,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 12,
95
+ "num_negatives": 100,
96
+ "output_hidden_size": 768,
97
+ "pad_token_id": 0,
98
+ "proj_codevector_dim": 256,
99
+ "tdnn_dilation": [
100
+ 1,
101
+ 2,
102
+ 3,
103
+ 1,
104
+ 1
105
+ ],
106
+ "tdnn_dim": [
107
+ 512,
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 1500
112
+ ],
113
+ "tdnn_kernel": [
114
+ 5,
115
+ 3,
116
+ 3,
117
+ 1,
118
+ 1
119
+ ],
120
+ "torch_dtype": "float32",
121
+ "transformers_version": "4.28.1",
122
+ "use_weighted_layer_sum": false,
123
+ "vocab_size": 32,
124
+ "xvector_output_dim": 512
125
+ }
checkpoint-4865/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ae7717b96ab29bd0c6e7d2b38e05724da0283a57f33300552cc333c6835b204
3
+ size 756685669
checkpoint-4865/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-4865/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43350457b886fe2db874dce5c0917171291e8df554c188a714b3f83dc2e318f8
3
+ size 378352659
checkpoint-4865/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06ef5d41c6f365ce57119eec5e3e504dc3fe79f635b7fcb8536820ebc83c49bd
3
+ size 14567
checkpoint-4865/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de4f5954137b8473313a1edf672c4c4fcf8b7b0eb50b746d28ad259a1199af3f
3
+ size 623
checkpoint-4865/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4865/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e586ffec83af94e0cf9ea31750e6c3ca1bf1ee016bdd398b7fe339f74b71c58
3
+ size 3567
checkpoint-5560/config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "english",
62
+ "1": "spanish",
63
+ "2": "arabic",
64
+ "3": "french",
65
+ "4": "mandarin",
66
+ "5": "other"
67
+ },
68
+ "initializer_range": 0.02,
69
+ "intermediate_size": 3072,
70
+ "label2id": {
71
+ "LABEL_0": 0,
72
+ "LABEL_1": 1,
73
+ "LABEL_2": 2,
74
+ "LABEL_3": 3,
75
+ "LABEL_4": 4,
76
+ "LABEL_5": 5
77
+ },
78
+ "layer_norm_eps": 1e-05,
79
+ "layerdrop": 0.1,
80
+ "mask_feature_length": 10,
81
+ "mask_feature_min_masks": 0,
82
+ "mask_feature_prob": 0.0,
83
+ "mask_time_length": 10,
84
+ "mask_time_min_masks": 2,
85
+ "mask_time_prob": 0.05,
86
+ "model_type": "wav2vec2",
87
+ "num_adapter_layers": 3,
88
+ "num_attention_heads": 12,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 12,
95
+ "num_negatives": 100,
96
+ "output_hidden_size": 768,
97
+ "pad_token_id": 0,
98
+ "proj_codevector_dim": 256,
99
+ "tdnn_dilation": [
100
+ 1,
101
+ 2,
102
+ 3,
103
+ 1,
104
+ 1
105
+ ],
106
+ "tdnn_dim": [
107
+ 512,
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 1500
112
+ ],
113
+ "tdnn_kernel": [
114
+ 5,
115
+ 3,
116
+ 3,
117
+ 1,
118
+ 1
119
+ ],
120
+ "torch_dtype": "float32",
121
+ "transformers_version": "4.28.1",
122
+ "use_weighted_layer_sum": false,
123
+ "vocab_size": 32,
124
+ "xvector_output_dim": 512
125
+ }
checkpoint-5560/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b92110f9394ded1cc7af578211896efd238d978d687f16d50a1001c026f41e6
3
+ size 756685669