Hugging Face's logo

wadhwani-ai
/
orf_en_wav2vec2_ft_v1

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Inference Endpoints
Model card Files Community
Jatin-WIAI commited on
Commit
f9b8367
·
verified ·
1 Parent(s): 28af5bd

vakhyansh model copy for english wav2vec2 model

Browse files
Files changed (2) hide show
  1. config.json +121 -0
  2. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/users/jatin/models/asr/gu/en_vakhyansh_ft_indian_cv_lora/checkpoint-35500",
3
+ "activation_dropout": 0.1,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_name": "bottleneck",
7
+ "adapter_stride": 2,
8
+ "add_adapter": false,
9
+ "apply_spec_augment": true,
10
+ "architectures": [
11
+ "Wav2Vec2ForCTC"
12
+ ],
13
+ "attention_dropout": 0.1,
14
+ "bos_token": "<s>",
15
+ "bos_token_id": 0,
16
+ "classifier_proj_size": 256,
17
+ "codevector_dim": 256,
18
+ "contrastive_logits_temperature": 0.1,
19
+ "conv_bias": false,
20
+ "conv_dim": [
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512,
26
+ 512,
27
+ 512
28
+ ],
29
+ "conv_kernel": [
30
+ 10,
31
+ 3,
32
+ 3,
33
+ 3,
34
+ 3,
35
+ 2,
36
+ 2
37
+ ],
38
+ "conv_stride": [
39
+ 5,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2,
44
+ 2,
45
+ 2
46
+ ],
47
+ "ctc_loss_reduction": "mean",
48
+ "ctc_zero_infinity": false,
49
+ "diversity_loss_weight": 0.1,
50
+ "do_lower_case": false,
51
+ "do_stable_layer_norm": false,
52
+ "eos_token": "</s>",
53
+ "eos_token_id": 2,
54
+ "feat_enc_adapter": false,
55
+ "feat_extract_activation": "gelu",
56
+ "feat_extract_norm": "group",
57
+ "feat_proj_dropout": 0.1,
58
+ "feat_quantizer_dropout": 0.0,
59
+ "final_dropout": 0.1,
60
+ "gradient_checkpointing": false,
61
+ "hidden_act": "gelu",
62
+ "hidden_dropout": 0.1,
63
+ "hidden_size": 768,
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 3072,
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.1,
68
+ "lora_adapter": true,
69
+ "lora_r": 8,
70
+ "mask_feature_length": 10,
71
+ "mask_feature_min_masks": 0,
72
+ "mask_feature_prob": 0.0,
73
+ "mask_time_length": 10,
74
+ "mask_time_min_masks": 2,
75
+ "mask_time_prob": 0.05,
76
+ "mh_adapter": false,
77
+ "model_type": "wav2vec2",
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_adapter": false,
88
+ "output_hidden_size": 768,
89
+ "pad_token": "<pad>",
90
+ "pad_token_id": 0,
91
+ "prefix_tuning": false,
92
+ "proj_codevector_dim": 256,
93
+ "tdnn_dilation": [
94
+ 1,
95
+ 2,
96
+ 3,
97
+ 1,
98
+ 1
99
+ ],
100
+ "tdnn_dim": [
101
+ 512,
102
+ 512,
103
+ 512,
104
+ 512,
105
+ 1500
106
+ ],
107
+ "tdnn_kernel": [
108
+ 5,
109
+ 3,
110
+ 3,
111
+ 1,
112
+ 1
113
+ ],
114
+ "torch_dtype": "float32",
115
+ "transformers_version": "4.37.2",
116
+ "unk_token": "<unk>",
117
+ "use_weighted_layer_sum": false,
118
+ "vocab_size": 32,
119
+ "word_delimiter_token": "|",
120
+ "xvector_output_dim": 512
121
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd2fc3badb93a87b592c019d9df952e3fc43084e1b33acaf238169a8277808da
3
+ size 382937472