Hugging Face's logo

facebook
/
wav2vec2-base-sv-voxpopuli-v2

Automatic Speech Recognition
Transformers
PyTorch
Swedish
wav2vec2
pretraining
audio
voxpopuli-v2
Model card Files Community
patrickvonplaten commited on
Commit
a93d363
•
1 Parent(s): 5a5f0c1

add model

Browse files
Files changed (4) hide show
  1. README.md +6 -0
  2. config.json +116 -0
  3. preprocessor_config.json +9 -0
  4. pytorch_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - correct
4
+ ---
5
+
6
+ Test
config.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "adapter_kernel_size": 3,
4
+ "adapter_stride": 2,
5
+ "add_adapter": false,
6
+ "apply_spec_augment": true,
7
+ "architectures": [
8
+ "Wav2Vec2ForPreTraining"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 1,
12
+ "classifier_proj_size": 256,
13
+ "codevector_dim": 256,
14
+ "contrastive_logits_temperature": 0.1,
15
+ "conv_bias": false,
16
+ "conv_dim": [
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512
24
+ ],
25
+ "conv_kernel": [
26
+ 10,
27
+ 3,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 2,
32
+ 2
33
+ ],
34
+ "conv_stride": [
35
+ 5,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2
42
+ ],
43
+ "ctc_loss_reduction": "sum",
44
+ "ctc_zero_infinity": false,
45
+ "diversity_loss_weight": 0.1,
46
+ "do_stable_layer_norm": false,
47
+ "eos_token_id": 2,
48
+ "feat_extract_activation": "gelu",
49
+ "feat_extract_norm": "group",
50
+ "feat_proj_dropout": 0.1,
51
+ "feat_quantizer_dropout": 0.0,
52
+ "final_dropout": 0.0,
53
+ "freeze_feat_extract_train": true,
54
+ "hidden_act": "gelu",
55
+ "hidden_dropout": 0.1,
56
+ "hidden_size": 768,
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 3072,
59
+ "layer_norm_eps": 1e-05,
60
+ "layerdrop": 0.0,
61
+ "mask_channel_length": 10,
62
+ "mask_channel_min_space": 1,
63
+ "mask_channel_other": 0.0,
64
+ "mask_channel_prob": 0.0,
65
+ "mask_channel_selection": "static",
66
+ "mask_feature_length": 10,
67
+ "mask_feature_min_masks": 0,
68
+ "mask_feature_prob": 0.0,
69
+ "mask_time_length": 10,
70
+ "mask_time_min_masks": 2,
71
+ "mask_time_min_space": 1,
72
+ "mask_time_other": 0.0,
73
+ "mask_time_prob": 0.05,
74
+ "mask_time_selection": "static",
75
+ "model_type": "wav2vec2",
76
+ "no_mask_channel_overlap": false,
77
+ "no_mask_time_overlap": false,
78
+ "num_adapter_layers": 3,
79
+ "num_attention_heads": 12,
80
+ "num_codevector_groups": 2,
81
+ "num_codevectors_per_group": 320,
82
+ "num_conv_pos_embedding_groups": 16,
83
+ "num_conv_pos_embeddings": 128,
84
+ "num_feat_extract_layers": 7,
85
+ "num_hidden_layers": 12,
86
+ "num_negatives": 100,
87
+ "output_hidden_size": 768,
88
+ "pad_token_id": 0,
89
+ "proj_codevector_dim": 256,
90
+ "tdnn_dilation": [
91
+ 1,
92
+ 2,
93
+ 3,
94
+ 1,
95
+ 1
96
+ ],
97
+ "tdnn_dim": [
98
+ 512,
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 1500
103
+ ],
104
+ "tdnn_kernel": [
105
+ 5,
106
+ 3,
107
+ 3,
108
+ 1,
109
+ 1
110
+ ],
111
+ "torch_dtype": "float32",
112
+ "transformers_version": "4.17.0.dev0",
113
+ "use_weighted_layer_sum": false,
114
+ "vocab_size": 32,
115
+ "xvector_output_dim": 512
116
+ }
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
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f6ff1041411ee336da0a75ffb96b4a1a074f666fb16b6565073ee953274a61f
3
+ size 380263437