Hugging Face's logo

Rest970828
/
wav2vec2-large-xlsr-53-finetuned-ks

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Rest970828 commited on
Commit
d18d784
•
1 Parent(s): 06ac01e

Training in progress, epoch 0

Browse files
Files changed (5) hide show
  1. config.json +129 -129
  2. model.safetensors +1 -1
  3. preprocessor_config.json +9 -9
  4. runs/Aug06_20-05-55_DESKTOP-M45715D/events.out.tfevents.1722942356.DESKTOP-M45715D.59152.0 +3 -0
  5. training_args.bin +2 -2
config.json CHANGED
@@ -1,129 +1,129 @@
1
- {
2
- "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
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": 768,
16
- "contrastive_logits_temperature": 0.1,
17
- "conv_bias": true,
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": true,
49
- "eos_token_id": 2,
50
- "feat_extract_activation": "gelu",
51
- "feat_extract_dropout": 0.0,
52
- "feat_extract_norm": "layer",
53
- "feat_proj_dropout": 0.1,
54
- "feat_quantizer_dropout": 0.0,
55
- "final_dropout": 0.0,
56
- "gradient_checkpointing": false,
57
- "hidden_act": "gelu",
58
- "hidden_dropout": 0.1,
59
- "hidden_size": 1024,
60
- "id2label": {
61
- "0": "A",
62
- "1": "B",
63
- "2": "C",
64
- "3": "D"
65
- },
66
- "initializer_range": 0.02,
67
- "intermediate_size": 4096,
68
- "label2id": {
69
- "A": "0",
70
- "B": "1",
71
- "C": "2",
72
- "D": "3"
73
- },
74
- "layer_norm_eps": 1e-05,
75
- "layerdrop": 0.1,
76
- "mask_channel_length": 10,
77
- "mask_channel_min_space": 1,
78
- "mask_channel_other": 0.0,
79
- "mask_channel_prob": 0.0,
80
- "mask_channel_selection": "static",
81
- "mask_feature_length": 10,
82
- "mask_feature_min_masks": 0,
83
- "mask_feature_prob": 0.0,
84
- "mask_time_length": 10,
85
- "mask_time_min_masks": 2,
86
- "mask_time_min_space": 1,
87
- "mask_time_other": 0.0,
88
- "mask_time_prob": 0.075,
89
- "mask_time_selection": "static",
90
- "model_type": "wav2vec2",
91
- "num_adapter_layers": 3,
92
- "num_attention_heads": 16,
93
- "num_codevector_groups": 2,
94
- "num_codevectors_per_group": 320,
95
- "num_conv_pos_embedding_groups": 16,
96
- "num_conv_pos_embeddings": 128,
97
- "num_feat_extract_layers": 7,
98
- "num_hidden_layers": 24,
99
- "num_negatives": 100,
100
- "output_hidden_size": 1024,
101
- "pad_token_id": 0,
102
- "proj_codevector_dim": 768,
103
- "tdnn_dilation": [
104
- 1,
105
- 2,
106
- 3,
107
- 1,
108
- 1
109
- ],
110
- "tdnn_dim": [
111
- 512,
112
- 512,
113
- 512,
114
- 512,
115
- 1500
116
- ],
117
- "tdnn_kernel": [
118
- 5,
119
- 3,
120
- 3,
121
- 1,
122
- 1
123
- ],
124
- "torch_dtype": "float32",
125
- "transformers_version": "4.36.2",
126
- "use_weighted_layer_sum": false,
127
- "vocab_size": 32,
128
- "xvector_output_dim": 512
129
- }
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
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": 768,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
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": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_size": 1024,
60
+ "id2label": {
61
+ "0": "A",
62
+ "1": "B",
63
+ "2": "C",
64
+ "3": "D"
65
+ },
66
+ "initializer_range": 0.02,
67
+ "intermediate_size": 4096,
68
+ "label2id": {
69
+ "A": "0",
70
+ "B": "1",
71
+ "C": "2",
72
+ "D": "3"
73
+ },
74
+ "layer_norm_eps": 1e-05,
75
+ "layerdrop": 0.1,
76
+ "mask_channel_length": 10,
77
+ "mask_channel_min_space": 1,
78
+ "mask_channel_other": 0.0,
79
+ "mask_channel_prob": 0.0,
80
+ "mask_channel_selection": "static",
81
+ "mask_feature_length": 10,
82
+ "mask_feature_min_masks": 0,
83
+ "mask_feature_prob": 0.0,
84
+ "mask_time_length": 10,
85
+ "mask_time_min_masks": 2,
86
+ "mask_time_min_space": 1,
87
+ "mask_time_other": 0.0,
88
+ "mask_time_prob": 0.075,
89
+ "mask_time_selection": "static",
90
+ "model_type": "wav2vec2",
91
+ "num_adapter_layers": 3,
92
+ "num_attention_heads": 16,
93
+ "num_codevector_groups": 2,
94
+ "num_codevectors_per_group": 320,
95
+ "num_conv_pos_embedding_groups": 16,
96
+ "num_conv_pos_embeddings": 128,
97
+ "num_feat_extract_layers": 7,
98
+ "num_hidden_layers": 24,
99
+ "num_negatives": 100,
100
+ "output_hidden_size": 1024,
101
+ "pad_token_id": 0,
102
+ "proj_codevector_dim": 768,
103
+ "tdnn_dilation": [
104
+ 1,
105
+ 2,
106
+ 3,
107
+ 1,
108
+ 1
109
+ ],
110
+ "tdnn_dim": [
111
+ 512,
112
+ 512,
113
+ 512,
114
+ 512,
115
+ 1500
116
+ ],
117
+ "tdnn_kernel": [
118
+ 5,
119
+ 3,
120
+ 3,
121
+ 1,
122
+ 1
123
+ ],
124
+ "torch_dtype": "float32",
125
+ "transformers_version": "4.36.2",
126
+ "use_weighted_layer_sum": false,
127
+ "vocab_size": 32,
128
+ "xvector_output_dim": 512
129
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c6e8d69991f4ca31e174022d5a1a37da1ee991039a786ac9fc743878eb2ed3f
3
  size 1262861360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cced252d01d9458a4a245a4de7a8536d85e3888616dd786680d3b2cc1a326950
3
  size 1262861360
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,
7
- "return_attention_mask": true,
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,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
runs/Aug06_20-05-55_DESKTOP-M45715D/events.out.tfevents.1722942356.DESKTOP-M45715D.59152.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0d9eb30d41ae2d8982a643ab5c2b7582b3810b4b23faa3b5eb92a522f1c5146
3
+ size 16006
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44c6f0a687fdb2d810e9b168ec4f2d52a4d35fd70c42c8239bfac3ada2affa76
3
- size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51078fedfe8d300741514ac594365d6eeafbb31be002f5c16098052f7441739e
3
+ size 4792