Hugging Face's logo

Rest970828
/
wav2vec2-base-finetuned-ks

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Rest970828 commited on
Commit
3dbb746
•
1 Parent(s): f10e0cd

Training in progress, epoch 0

Browse files
Files changed (8) hide show
  1. config.json +130 -130
  2. model.safetensors +1 -1
  3. preprocessor_config.json +9 -9
  4. runs/Aug06_16-40-21_DESKTOP-M45715D/events.out.tfevents.1722930038.DESKTOP-M45715D.29668.0 +3 -0
  5. runs/Aug06_16-41-55_DESKTOP-M45715D/events.out.tfevents.1722930115.DESKTOP-M45715D.69188.0 +3 -0
  6. runs/Aug06_16-44-54_DESKTOP-M45715D/events.out.tfevents.1722930298.DESKTOP-M45715D.72628.0 +3 -0
  7. runs/Aug06_16-54-22_DESKTOP-M45715D/events.out.tfevents.1722930863.DESKTOP-M45715D.24704.0 +3 -0
  8. training_args.bin +1 -1
config.json CHANGED
@@ -1,130 +1,130 @@
1
- {
2
- "_name_or_path": "facebook/wav2vec2-base",
3
- "activation_dropout": 0.0,
4
- "adapter_attn_dim": null,
5
- "adapter_kernel_size": 3,
6
- "adapter_stride": 2,
7
- "add_adapter": false,
8
- "apply_spec_augment": true,
9
- "architectures": [
10
- "Wav2Vec2ForSequenceClassification"
11
- ],
12
- "attention_dropout": 0.1,
13
- "bos_token_id": 1,
14
- "classifier_proj_size": 256,
15
- "codevector_dim": 256,
16
- "contrastive_logits_temperature": 0.1,
17
- "conv_bias": false,
18
- "conv_dim": [
19
- 512,
20
- 512,
21
- 512,
22
- 512,
23
- 512,
24
- 512,
25
- 512
26
- ],
27
- "conv_kernel": [
28
- 10,
29
- 3,
30
- 3,
31
- 3,
32
- 3,
33
- 2,
34
- 2
35
- ],
36
- "conv_stride": [
37
- 5,
38
- 2,
39
- 2,
40
- 2,
41
- 2,
42
- 2,
43
- 2
44
- ],
45
- "ctc_loss_reduction": "sum",
46
- "ctc_zero_infinity": false,
47
- "diversity_loss_weight": 0.1,
48
- "do_stable_layer_norm": false,
49
- "eos_token_id": 2,
50
- "feat_extract_activation": "gelu",
51
- "feat_extract_norm": "group",
52
- "feat_proj_dropout": 0.1,
53
- "feat_quantizer_dropout": 0.0,
54
- "final_dropout": 0.0,
55
- "freeze_feat_extract_train": true,
56
- "hidden_act": "gelu",
57
- "hidden_dropout": 0.1,
58
- "hidden_size": 768,
59
- "id2label": {
60
- "0": "A",
61
- "1": "B",
62
- "2": "C",
63
- "3": "D"
64
- },
65
- "initializer_range": 0.02,
66
- "intermediate_size": 3072,
67
- "label2id": {
68
- "A": "0",
69
- "B": "1",
70
- "C": "2",
71
- "D": "3"
72
- },
73
- "layer_norm_eps": 1e-05,
74
- "layerdrop": 0.0,
75
- "mask_channel_length": 10,
76
- "mask_channel_min_space": 1,
77
- "mask_channel_other": 0.0,
78
- "mask_channel_prob": 0.0,
79
- "mask_channel_selection": "static",
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_min_space": 1,
86
- "mask_time_other": 0.0,
87
- "mask_time_prob": 0.05,
88
- "mask_time_selection": "static",
89
- "model_type": "wav2vec2",
90
- "no_mask_channel_overlap": false,
91
- "no_mask_time_overlap": false,
92
- "num_adapter_layers": 3,
93
- "num_attention_heads": 12,
94
- "num_codevector_groups": 2,
95
- "num_codevectors_per_group": 320,
96
- "num_conv_pos_embedding_groups": 16,
97
- "num_conv_pos_embeddings": 128,
98
- "num_feat_extract_layers": 7,
99
- "num_hidden_layers": 12,
100
- "num_negatives": 100,
101
- "output_hidden_size": 768,
102
- "pad_token_id": 0,
103
- "proj_codevector_dim": 256,
104
- "tdnn_dilation": [
105
- 1,
106
- 2,
107
- 3,
108
- 1,
109
- 1
110
- ],
111
- "tdnn_dim": [
112
- 512,
113
- 512,
114
- 512,
115
- 512,
116
- 1500
117
- ],
118
- "tdnn_kernel": [
119
- 5,
120
- 3,
121
- 3,
122
- 1,
123
- 1
124
- ],
125
- "torch_dtype": "float32",
126
- "transformers_version": "4.36.2",
127
- "use_weighted_layer_sum": false,
128
- "vocab_size": 32,
129
- "xvector_output_dim": 512
130
- }
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
+ "activation_dropout": 0.0,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForSequenceClassification"
11
+ ],
12
+ "attention_dropout": 0.1,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 256,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": false,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "sum",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": false,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "freeze_feat_extract_train": true,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_size": 768,
59
+ "id2label": {
60
+ "0": "A",
61
+ "1": "B",
62
+ "2": "C",
63
+ "3": "D"
64
+ },
65
+ "initializer_range": 0.02,
66
+ "intermediate_size": 3072,
67
+ "label2id": {
68
+ "A": "0",
69
+ "B": "1",
70
+ "C": "2",
71
+ "D": "3"
72
+ },
73
+ "layer_norm_eps": 1e-05,
74
+ "layerdrop": 0.0,
75
+ "mask_channel_length": 10,
76
+ "mask_channel_min_space": 1,
77
+ "mask_channel_other": 0.0,
78
+ "mask_channel_prob": 0.0,
79
+ "mask_channel_selection": "static",
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_min_space": 1,
86
+ "mask_time_other": 0.0,
87
+ "mask_time_prob": 0.05,
88
+ "mask_time_selection": "static",
89
+ "model_type": "wav2vec2",
90
+ "no_mask_channel_overlap": false,
91
+ "no_mask_time_overlap": false,
92
+ "num_adapter_layers": 3,
93
+ "num_attention_heads": 12,
94
+ "num_codevector_groups": 2,
95
+ "num_codevectors_per_group": 320,
96
+ "num_conv_pos_embedding_groups": 16,
97
+ "num_conv_pos_embeddings": 128,
98
+ "num_feat_extract_layers": 7,
99
+ "num_hidden_layers": 12,
100
+ "num_negatives": 100,
101
+ "output_hidden_size": 768,
102
+ "pad_token_id": 0,
103
+ "proj_codevector_dim": 256,
104
+ "tdnn_dilation": [
105
+ 1,
106
+ 2,
107
+ 3,
108
+ 1,
109
+ 1
110
+ ],
111
+ "tdnn_dim": [
112
+ 512,
113
+ 512,
114
+ 512,
115
+ 512,
116
+ 1500
117
+ ],
118
+ "tdnn_kernel": [
119
+ 5,
120
+ 3,
121
+ 3,
122
+ 1,
123
+ 1
124
+ ],
125
+ "torch_dtype": "float32",
126
+ "transformers_version": "4.36.2",
127
+ "use_weighted_layer_sum": false,
128
+ "vocab_size": 32,
129
+ "xvector_output_dim": 512
130
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a681bfbbaa4bbdfa53d0dfe949b7c651e018ad01c5e8b157e8a9e4f1cd2e8b60
3
  size 378304424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc81f4d251b19f1ef5d97a77fa26227af9ea0c9cfaa49b8ffbd0f8bea9082060
3
  size 378304424
preprocessor_config.json CHANGED
@@ -1,9 +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
- }
 
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
+ }
runs/Aug06_16-40-21_DESKTOP-M45715D/events.out.tfevents.1722930038.DESKTOP-M45715D.29668.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce4448aa159bdd6ead3de9233e4995b73555b402395001d5743b9cf99de0a2dc
3
+ size 6258
runs/Aug06_16-41-55_DESKTOP-M45715D/events.out.tfevents.1722930115.DESKTOP-M45715D.69188.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:645168034abc1b23a93af55005b21c444d1c13ccbadca6fecc6754a8076ab7c0
3
+ size 6258
runs/Aug06_16-44-54_DESKTOP-M45715D/events.out.tfevents.1722930298.DESKTOP-M45715D.72628.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc83616f4e06700002eb09bab3b8fab6afba8138421e15af5823eb3b7094e726
3
+ size 6258
runs/Aug06_16-54-22_DESKTOP-M45715D/events.out.tfevents.1722930863.DESKTOP-M45715D.24704.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24d26c3a0d00224ba4adc34d2b37f230caea25d082cc3dc503623e4707784107
3
+ size 7698
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:710baf5c8525397fd393550bc502527115cd27fa7d4bc137c2fb1eb70393e2b0
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbd63b9eae773a9eedb04c4a0862c39959483a66b06ead3ff8fcb807e04db581
3
  size 4728