Hugging Face's logo

xbgoose
/
wavlm-large-speech-emotion-recognition-russian-dusha-finetuned

Audio Classification
Transformers
PyTorch
wavlm
Inference Endpoints
Model card Files Community
1
xbgoose commited on
Commit
7b82483
•
1 Parent(s): 66baf5e

Upload WavLMForSequenceClassification

Browse files
Files changed (2) hide show
  1. config.json +135 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/wavlm-large",
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
+ "WavLMForSequenceClassification"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 768,
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": true,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "layer",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_size": 1024,
59
+ "id2label": {
60
+ "0": "LABEL_0",
61
+ "1": "LABEL_1",
62
+ "2": "LABEL_2",
63
+ "3": "LABEL_3",
64
+ "4": "LABEL_4"
65
+ },
66
+ "initializer_range": 0.02,
67
+ "intermediate_size": 4096,
68
+ "label2id": {
69
+ "LABEL_0": 0,
70
+ "LABEL_1": 1,
71
+ "LABEL_2": 2,
72
+ "LABEL_3": 3,
73
+ "LABEL_4": 4
74
+ },
75
+ "layer_norm_eps": 1e-05,
76
+ "layerdrop": 0.1,
77
+ "mask_channel_length": 10,
78
+ "mask_channel_min_space": 1,
79
+ "mask_channel_other": 0.0,
80
+ "mask_channel_prob": 0.0,
81
+ "mask_channel_selection": "static",
82
+ "mask_feature_length": 10,
83
+ "mask_feature_min_masks": 0,
84
+ "mask_feature_prob": 0.0,
85
+ "mask_time_length": 10,
86
+ "mask_time_min_masks": 2,
87
+ "mask_time_min_space": 1,
88
+ "mask_time_other": 0.0,
89
+ "mask_time_prob": 0.075,
90
+ "mask_time_selection": "static",
91
+ "max_bucket_distance": 800,
92
+ "model_type": "wavlm",
93
+ "num_adapter_layers": 3,
94
+ "num_attention_heads": 16,
95
+ "num_buckets": 320,
96
+ "num_codevector_groups": 2,
97
+ "num_codevectors_per_group": 320,
98
+ "num_conv_pos_embedding_groups": 16,
99
+ "num_conv_pos_embeddings": 128,
100
+ "num_ctc_classes": 80,
101
+ "num_feat_extract_layers": 7,
102
+ "num_hidden_layers": 24,
103
+ "num_negatives": 100,
104
+ "output_hidden_size": 1024,
105
+ "pad_token_id": 0,
106
+ "proj_codevector_dim": 768,
107
+ "replace_prob": 0.5,
108
+ "tdnn_dilation": [
109
+ 1,
110
+ 2,
111
+ 3,
112
+ 1,
113
+ 1
114
+ ],
115
+ "tdnn_dim": [
116
+ 512,
117
+ 512,
118
+ 512,
119
+ 512,
120
+ 1500
121
+ ],
122
+ "tdnn_kernel": [
123
+ 5,
124
+ 3,
125
+ 3,
126
+ 1,
127
+ 1
128
+ ],
129
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
130
+ "torch_dtype": "float32",
131
+ "transformers_version": "4.30.2",
132
+ "use_weighted_layer_sum": false,
133
+ "vocab_size": 32,
134
+ "xvector_output_dim": 512
135
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6324099bcc084ff1a5130bd09d3ce4bd392f6783bcb851a5bb1e6898da5bb31e
3
+ size 1263036221