Hugging Face's logo

a2d8a4v
/
omniASR_CTC_1b_hg

Safetensors
wav2vec2
Model card Files
xet
Community
jtli commited on
Commit
cea44ba
·
1 Parent(s): 1a82ef1

init upload

Browse files
Files changed (6) hide show
  1. config.json +102 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +9 -0
  4. special_tokens_map.json +6 -0
  5. tokenizer_config.json +46 -0
  6. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "adapter_attn_dim": null,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": false,
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": null,
10
+ "classifier_proj_size": 256,
11
+ "codevector_dim": 256,
12
+ "contrastive_logits_temperature": 0.1,
13
+ "conv_bias": true,
14
+ "conv_dim": [
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512
22
+ ],
23
+ "conv_kernel": [
24
+ 10,
25
+ 3,
26
+ 3,
27
+ 3,
28
+ 3,
29
+ 2,
30
+ 2
31
+ ],
32
+ "conv_stride": [
33
+ 5,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2
40
+ ],
41
+ "ctc_loss_reduction": "mean",
42
+ "ctc_zero_infinity": false,
43
+ "diversity_loss_weight": 0.1,
44
+ "do_stable_layer_norm": true,
45
+ "eos_token_id": null,
46
+ "feat_extract_activation": "gelu",
47
+ "feat_extract_norm": "layer",
48
+ "feat_proj_dropout": 0.0,
49
+ "feat_quantizer_dropout": 0.0,
50
+ "final_dropout": 0.1,
51
+ "hidden_act": "gelu",
52
+ "hidden_dropout": 0.0,
53
+ "hidden_size": 1280,
54
+ "initializer_range": 0.02,
55
+ "intermediate_size": 5120,
56
+ "layer_norm_eps": 1e-05,
57
+ "layerdrop": 0.0,
58
+ "mask_feature_length": 0,
59
+ "mask_feature_min_masks": 0,
60
+ "mask_feature_prob": 0.0,
61
+ "mask_time_length": 0,
62
+ "mask_time_min_masks": 2,
63
+ "mask_time_prob": 0.0,
64
+ "model_type": "wav2vec2",
65
+ "num_adapter_layers": 3,
66
+ "num_attention_heads": 20,
67
+ "num_codevector_groups": 2,
68
+ "num_codevectors_per_group": 320,
69
+ "num_conv_pos_embedding_groups": 16,
70
+ "num_conv_pos_embeddings": 128,
71
+ "num_feat_extract_layers": 7,
72
+ "num_hidden_layers": 48,
73
+ "num_negatives": 100,
74
+ "output_hidden_size": 768,
75
+ "pad_token_id": 0,
76
+ "proj_codevector_dim": 9812,
77
+ "tdnn_dilation": [
78
+ 1,
79
+ 2,
80
+ 3,
81
+ 1,
82
+ 1
83
+ ],
84
+ "tdnn_dim": [
85
+ 512,
86
+ 512,
87
+ 512,
88
+ 512,
89
+ 1500
90
+ ],
91
+ "tdnn_kernel": [
92
+ 5,
93
+ 3,
94
+ 3,
95
+ 1,
96
+ 1
97
+ ],
98
+ "transformers_version": "4.57.1",
99
+ "use_weighted_layer_sum": false,
100
+ "vocab_size": 9812,
101
+ "xvector_output_dim": 512
102
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46ecfd018ce2467d51889057c667d41c76530f8ab93fa3dfd4e0773352de1420
3
+ size 3900362512
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": 0.0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "extra_special_tokens": {},
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "<pad>",
43
+ "spm_file": "/home/jtli/AcousticModel/SSL/omnilingual/omniASR_tokenizer.model",
44
+ "tokenizer_class": "Speech2Text2Tokenizer",
45
+ "unk_token": "<unk>"
46
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff