Hugging Face's logo

pykeio
/
lku-base-v1.1

Audio Classification
Transformers
Safetensors
wav2vec2
Inference Endpoints
Model card Files Community
decahedron commited on
Commit
f9344cb
•
1 Parent(s): 56bce5a

Upload 3 files

Browse files
Files changed (3) hide show
  1. config.json +128 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +9 -0
config.json ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "neutral",
63
+ "1": "sad",
64
+ "2": "happy",
65
+ "3": "angry",
66
+ "4": "fearful",
67
+ "5": "disgusted",
68
+ "6": "surprised"
69
+ },
70
+ "initializer_range": 0.02,
71
+ "intermediate_size": 3072,
72
+ "label2id": {
73
+ "angry": 3,
74
+ "disgusted": 5,
75
+ "fearful": 4,
76
+ "happy": 2,
77
+ "neutral": 0,
78
+ "sad": 1,
79
+ "surprised": 6
80
+ },
81
+ "layer_norm_eps": 1e-05,
82
+ "layerdrop": 0.1,
83
+ "mask_feature_length": 10,
84
+ "mask_feature_min_masks": 0,
85
+ "mask_feature_prob": 0.0,
86
+ "mask_time_length": 10,
87
+ "mask_time_min_masks": 2,
88
+ "mask_time_prob": 0.05,
89
+ "model_type": "wav2vec2",
90
+ "num_adapter_layers": 3,
91
+ "num_attention_heads": 12,
92
+ "num_codevector_groups": 2,
93
+ "num_codevectors_per_group": 320,
94
+ "num_conv_pos_embedding_groups": 16,
95
+ "num_conv_pos_embeddings": 128,
96
+ "num_feat_extract_layers": 7,
97
+ "num_hidden_layers": 12,
98
+ "num_negatives": 100,
99
+ "output_hidden_size": 768,
100
+ "pad_token_id": 0,
101
+ "proj_codevector_dim": 256,
102
+ "tdnn_dilation": [
103
+ 1,
104
+ 2,
105
+ 3,
106
+ 1,
107
+ 1
108
+ ],
109
+ "tdnn_dim": [
110
+ 512,
111
+ 512,
112
+ 512,
113
+ 512,
114
+ 1500
115
+ ],
116
+ "tdnn_kernel": [
117
+ 5,
118
+ 3,
119
+ 3,
120
+ 1,
121
+ 1
122
+ ],
123
+ "torch_dtype": "float32",
124
+ "transformers_version": "4.37.2",
125
+ "use_weighted_layer_sum": false,
126
+ "vocab_size": 32,
127
+ "xvector_output_dim": 512
128
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b2cb67b20cd71f8e849034e78531ad9d8757b27dd9113895c4072202254f6b0
3
+ size 378307508
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,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }