Hugging Face's logo

pykeio
/
lku-base

Audio Classification
Transformers
Safetensors
wav2vec2
Inference Endpoints
Model card Files Community
decahedron commited on
Commit
4d6ae50
•
1 Parent(s): bfab0f6

Updated labels

Browse files
Files changed (2) hide show
  1. config.json +126 -125
  2. preprocessor_config.json +9 -9
config.json CHANGED
@@ -1,125 +1,126 @@
1
- {
2
- "activation_dropout": 0.1,
3
- "adapter_attn_dim": null,
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": "happy",
62
- "1": "fear",
63
- "2": "neutral",
64
- "3": "angry",
65
- "4": "sad",
66
- "5": "disgust"
67
- },
68
- "initializer_range": 0.02,
69
- "intermediate_size": 3072,
70
- "label2id": {
71
- "angry": 3,
72
- "disgust": 5,
73
- "fear": 1,
74
- "happy": 0,
75
- "neutral": 2,
76
- "sad": 4
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": "4.37.2",
122
- "use_weighted_layer_sum": false,
123
- "vocab_size": null,
124
- "xvector_output_dim": 512
125
- }
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-100k-voxpopuli",
3
+ "activation_dropout": 0.1,
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_dropout": 0.0,
52
+ "feat_extract_norm": "group",
53
+ "feat_proj_dropout": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.1,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_dropout_prob": 0.1,
60
+ "hidden_size": 768,
61
+ "id2label": {
62
+ "0": "angry",
63
+ "1": "disgust",
64
+ "2": "sad",
65
+ "3": "neutral",
66
+ "4": "fear",
67
+ "5": "happy"
68
+ },
69
+ "initializer_range": 0.02,
70
+ "intermediate_size": 3072,
71
+ "label2id": {
72
+ "angry": 0,
73
+ "disgust": 1,
74
+ "fear": 4,
75
+ "happy": 5,
76
+ "neutral": 3,
77
+ "sad": 2
78
+ },
79
+ "layer_norm_eps": 1e-05,
80
+ "layerdrop": 0.1,
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_prob": 0.05,
87
+ "model_type": "wav2vec2",
88
+ "num_adapter_layers": 3,
89
+ "num_attention_heads": 12,
90
+ "num_codevector_groups": 2,
91
+ "num_codevectors_per_group": 320,
92
+ "num_conv_pos_embedding_groups": 16,
93
+ "num_conv_pos_embeddings": 128,
94
+ "num_feat_extract_layers": 7,
95
+ "num_hidden_layers": 12,
96
+ "num_negatives": 100,
97
+ "output_hidden_size": 768,
98
+ "pad_token_id": 0,
99
+ "proj_codevector_dim": 256,
100
+ "tdnn_dilation": [
101
+ 1,
102
+ 2,
103
+ 3,
104
+ 1,
105
+ 1
106
+ ],
107
+ "tdnn_dim": [
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 512,
112
+ 1500
113
+ ],
114
+ "tdnn_kernel": [
115
+ 5,
116
+ 3,
117
+ 3,
118
+ 1,
119
+ 1
120
+ ],
121
+ "torch_dtype": "float32",
122
+ "transformers_version": "4.37.2",
123
+ "use_weighted_layer_sum": false,
124
+ "vocab_size": 32,
125
+ "xvector_output_dim": 512
126
+ }
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": 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,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }