Xenova HF staff commited on
Commit
0d39621
1 Parent(s): a41a555

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/wavlm-base-plus-sd",
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
+ "WavLMForAudioFrameClassification"
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
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.05,
62
+ "mask_channel_length": 10,
63
+ "mask_channel_min_space": 1,
64
+ "mask_channel_other": 0.0,
65
+ "mask_channel_prob": 0.0,
66
+ "mask_channel_selection": "static",
67
+ "mask_feature_length": 10,
68
+ "mask_feature_min_masks": 0,
69
+ "mask_feature_prob": 0.0,
70
+ "mask_time_length": 10,
71
+ "mask_time_min_masks": 2,
72
+ "mask_time_min_space": 1,
73
+ "mask_time_other": 0.0,
74
+ "mask_time_prob": 0.05,
75
+ "mask_time_selection": "static",
76
+ "max_bucket_distance": 800,
77
+ "model_type": "wavlm",
78
+ "no_mask_channel_overlap": false,
79
+ "no_mask_time_overlap": false,
80
+ "num_adapter_layers": 3,
81
+ "num_attention_heads": 12,
82
+ "num_buckets": 320,
83
+ "num_codevector_groups": 2,
84
+ "num_codevectors_per_group": 320,
85
+ "num_conv_pos_embedding_groups": 16,
86
+ "num_conv_pos_embeddings": 128,
87
+ "num_ctc_classes": 80,
88
+ "num_feat_extract_layers": 7,
89
+ "num_hidden_layers": 12,
90
+ "num_negatives": 100,
91
+ "output_hidden_size": 768,
92
+ "pad_token_id": 0,
93
+ "proj_codevector_dim": 256,
94
+ "replace_prob": 0.5,
95
+ "tdnn_dilation": [
96
+ 1,
97
+ 2,
98
+ 3,
99
+ 1,
100
+ 1
101
+ ],
102
+ "tdnn_dim": [
103
+ 512,
104
+ 512,
105
+ 512,
106
+ 512,
107
+ 1500
108
+ ],
109
+ "tdnn_kernel": [
110
+ 5,
111
+ 3,
112
+ 3,
113
+ 1,
114
+ 1
115
+ ],
116
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
117
+ "transformers_version": "4.33.2",
118
+ "use_weighted_layer_sum": true,
119
+ "vocab_size": 32,
120
+ "xvector_output_dim": 512
121
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a2c86146a20e49fdc5ba23acb6832636b2d9e8b4f79dd20eae148508dd7ad72
3
+ size 377989447
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28ddf26911202979b5092c2b7e821ce65dc45dff9aa4c16ed1e2d156281528da
3
+ size 95495292
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": false,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
quantize_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "model": {
6
+ "op_types": [
7
+ "Softmax",
8
+ "Where",
9
+ "ReduceMean",
10
+ "Conv",
11
+ "Mul",
12
+ "Sub",
13
+ "Concat",
14
+ "Unsqueeze",
15
+ "Div",
16
+ "Transpose",
17
+ "InstanceNormalization",
18
+ "Cast",
19
+ "Less",
20
+ "Tile",
21
+ "Log",
22
+ "Range",
23
+ "ReduceSum",
24
+ "Expand",
25
+ "Reshape",
26
+ "Min",
27
+ "Sigmoid",
28
+ "Slice",
29
+ "Add",
30
+ "Pow",
31
+ "Erf",
32
+ "Greater",
33
+ "Abs",
34
+ "Gather",
35
+ "Shape",
36
+ "Sqrt",
37
+ "Constant",
38
+ "MatMul",
39
+ "ConstantOfShape",
40
+ "Gemm"
41
+ ],
42
+ "weight_type": "QUInt8"
43
+ }
44
+ }
45
+ }