Hugging Face's logo

facebook
/
wav2vec2-conformer-rel-pos-large

Transformers
PyTorch
English
wav2vec2-conformer
pretraining
speech
Inference Endpoints
Model card Files Community
2
patrickvonplaten commited on
Commit
ee2ffc4
•
1 Parent(s): 359806d

upload model

Browse files
Files changed (3) hide show
  1. config.json +112 -0
  2. preprocessor_config.json +10 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "adapter_kernel_size": 3,
4
+ "adapter_stride": 2,
5
+ "add_adapter": false,
6
+ "apply_spec_augment": true,
7
+ "architectures": [
8
+ "Wav2Vec2ConformerForPreTraining"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 1,
12
+ "classifier_proj_size": 256,
13
+ "codevector_dim": 768,
14
+ "conformer_conv_dropout": 0.1,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
17
+ "conv_depthwise_kernel_size": 31,
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": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.1,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "swish",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_dropout_prob": 0.1,
60
+ "hidden_size": 1024,
61
+ "initializer_range": 0.02,
62
+ "intermediate_size": 4096,
63
+ "layer_norm_eps": 1e-05,
64
+ "layerdrop": 0.0,
65
+ "mask_feature_length": 10,
66
+ "mask_feature_min_masks": 0,
67
+ "mask_feature_prob": 0.0,
68
+ "mask_time_length": 10,
69
+ "mask_time_min_masks": 2,
70
+ "mask_time_prob": 0.05,
71
+ "max_source_positions": 5000,
72
+ "model_type": "wav2vec2-conformer",
73
+ "num_adapter_layers": 3,
74
+ "num_attention_heads": 16,
75
+ "num_codevector_groups": 2,
76
+ "num_codevectors_per_group": 320,
77
+ "num_conv_pos_embedding_groups": 16,
78
+ "num_conv_pos_embeddings": 128,
79
+ "num_feat_extract_layers": 7,
80
+ "num_hidden_layers": 24,
81
+ "num_negatives": 100,
82
+ "output_hidden_size": 1024,
83
+ "pad_token_id": 0,
84
+ "position_embeddings_type": "relative",
85
+ "proj_codevector_dim": 768,
86
+ "rotary_embedding_base": 10000,
87
+ "tdnn_dilation": [
88
+ 1,
89
+ 2,
90
+ 3,
91
+ 1,
92
+ 1
93
+ ],
94
+ "tdnn_dim": [
95
+ 512,
96
+ 512,
97
+ 512,
98
+ 512,
99
+ 1500
100
+ ],
101
+ "tdnn_kernel": [
102
+ 5,
103
+ 3,
104
+ 3,
105
+ 1,
106
+ 1
107
+ ],
108
+ "torch_dtype": "float32",
109
+ "transformers_version": "4.19.0.dev0",
110
+ "use_weighted_layer_sum": false,
111
+ "xvector_output_dim": 512
112
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:002baf81824168fb46b1027c7d03a40fc94ba20d719740168e01a2d181288c95
3
+ size 2482555895