Hugging Face's logo

calicxy
/
wav2vec2-base-finetuned-ks

Audio Classification
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
calicxy commited on
Commit
9f7c9ad
·
1 Parent(s): a8e5358

Training in progress, epoch 0

Browse files
Files changed (7) hide show
  1. .gitignore +1 -0
  2. config.json +147 -0
  3. preprocessor_config.json +9 -0
  4. pytorch_model.bin +3 -0
  5. runs/Nov03_12-30-06_b2de817c8610/1667478623.2554753/events.out.tfevents.1667478623.b2de817c8610.77.1 +3 -0
  6. runs/Nov03_12-30-06_b2de817c8610/events.out.tfevents.1667478623.b2de817c8610.77.0 +3 -0
  7. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
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
+ "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_norm": "group",
51
+ "feat_proj_dropout": 0.1,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "freeze_feat_extract_train": true,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "id2label": {
59
+ "0": "boredom",
60
+ "1": "neutral",
61
+ "10": "pain",
62
+ "11": "disappointment",
63
+ "12": "breath",
64
+ "2": "happy",
65
+ "3": "sad",
66
+ "4": "anger",
67
+ "5": "fear",
68
+ "6": "disgust",
69
+ "7": "surprised",
70
+ "8": "excited",
71
+ "9": "pleasure"
72
+ },
73
+ "initializer_range": 0.02,
74
+ "intermediate_size": 3072,
75
+ "label2id": {
76
+ "anger": "4",
77
+ "boredom": "0",
78
+ "breath": "12",
79
+ "disappointment": "11",
80
+ "disgust": "6",
81
+ "excited": "8",
82
+ "fear": "5",
83
+ "happy": "2",
84
+ "neutral": "1",
85
+ "pain": "10",
86
+ "pleasure": "9",
87
+ "sad": "3",
88
+ "surprised": "7"
89
+ },
90
+ "layer_norm_eps": 1e-05,
91
+ "layerdrop": 0.0,
92
+ "mask_channel_length": 10,
93
+ "mask_channel_min_space": 1,
94
+ "mask_channel_other": 0.0,
95
+ "mask_channel_prob": 0.0,
96
+ "mask_channel_selection": "static",
97
+ "mask_feature_length": 10,
98
+ "mask_feature_min_masks": 0,
99
+ "mask_feature_prob": 0.0,
100
+ "mask_time_length": 10,
101
+ "mask_time_min_masks": 2,
102
+ "mask_time_min_space": 1,
103
+ "mask_time_other": 0.0,
104
+ "mask_time_prob": 0.05,
105
+ "mask_time_selection": "static",
106
+ "model_type": "wav2vec2",
107
+ "no_mask_channel_overlap": false,
108
+ "no_mask_time_overlap": false,
109
+ "num_adapter_layers": 3,
110
+ "num_attention_heads": 12,
111
+ "num_codevector_groups": 2,
112
+ "num_codevectors_per_group": 320,
113
+ "num_conv_pos_embedding_groups": 16,
114
+ "num_conv_pos_embeddings": 128,
115
+ "num_feat_extract_layers": 7,
116
+ "num_hidden_layers": 12,
117
+ "num_negatives": 100,
118
+ "output_hidden_size": 768,
119
+ "pad_token_id": 0,
120
+ "proj_codevector_dim": 256,
121
+ "tdnn_dilation": [
122
+ 1,
123
+ 2,
124
+ 3,
125
+ 1,
126
+ 1
127
+ ],
128
+ "tdnn_dim": [
129
+ 512,
130
+ 512,
131
+ 512,
132
+ 512,
133
+ 1500
134
+ ],
135
+ "tdnn_kernel": [
136
+ 5,
137
+ 3,
138
+ 3,
139
+ 1,
140
+ 1
141
+ ],
142
+ "torch_dtype": "float32",
143
+ "transformers_version": "4.24.0",
144
+ "use_weighted_layer_sum": false,
145
+ "vocab_size": 32,
146
+ "xvector_output_dim": 512
147
+ }
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
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36a296c9beee6514b385072f5987ce0807696902e6230945acdab71fe55512e0
3
+ size 378359827
runs/Nov03_12-30-06_b2de817c8610/1667478623.2554753/events.out.tfevents.1667478623.b2de817c8610.77.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe2da32eca64d668d4f9cac94843e8ff4d592467b02cb9033665c2ca1185a092
3
+ size 5499
runs/Nov03_12-30-06_b2de817c8610/events.out.tfevents.1667478623.b2de817c8610.77.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:926f849c1ed4bd66d4242c543ccdccd196b3eda9a2697988b2549abe74763ae9
3
+ size 6893
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a126bf59f57afa7ab69e656c63dc9ea0033a514cd630a6bbd75d0c4dae05de71
3
+ size 3375