Rafeq commited on
Commit
52f09fc
·
1 Parent(s): 80da66e

Upload 5 files

Browse files
config (1).json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "apply_spec_augment": true,
4
+ "architectures": [
5
+ "Wav2Vec2ForPreTraining"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 1,
9
+ "codevector_dim": 256,
10
+ "contrastive_logits_temperature": 0.1,
11
+ "conv_bias": false,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_stride": [
31
+ 5,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2
38
+ ],
39
+ "ctc_loss_reduction": "sum",
40
+ "ctc_zero_infinity": false,
41
+ "diversity_loss_weight": 0.1,
42
+ "do_stable_layer_norm": false,
43
+ "eos_token_id": 2,
44
+ "feat_extract_activation": "gelu",
45
+ "feat_extract_norm": "group",
46
+ "feat_proj_dropout": 0.1,
47
+ "feat_quantizer_dropout": 0.0,
48
+ "final_dropout": 0.0,
49
+ "freeze_feat_extract_train": true,
50
+ "gradient_checkpointing": true,
51
+ "hidden_act": "gelu",
52
+ "hidden_dropout": 0.1,
53
+ "hidden_size": 768,
54
+ "initializer_range": 0.02,
55
+ "intermediate_size": 3072,
56
+ "layer_norm_eps": 1e-05,
57
+ "layerdrop": 0.0,
58
+ "mask_channel_length": 10,
59
+ "mask_channel_min_space": 1,
60
+ "mask_channel_other": 0.0,
61
+ "mask_channel_prob": 0.0,
62
+ "mask_channel_selection": "static",
63
+ "mask_feature_length": 10,
64
+ "mask_feature_prob": 0.0,
65
+ "mask_time_length": 10,
66
+ "mask_time_min_space": 1,
67
+ "mask_time_other": 0.0,
68
+ "mask_time_prob": 0.05,
69
+ "mask_time_selection": "static",
70
+ "model_type": "wav2vec2",
71
+ "no_mask_channel_overlap": false,
72
+ "no_mask_time_overlap": false,
73
+ "num_attention_heads": 12,
74
+ "num_codevector_groups": 2,
75
+ "num_codevectors_per_group": 320,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 12,
80
+ "num_negatives": 100,
81
+ "pad_token_id": 0,
82
+ "proj_codevector_dim": 256,
83
+ "transformers_version": "4.7.0.dev0",
84
+ "vocab_size": 32
85
+ }
preprocessor_config (1).json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_size": 1,
4
+ "padding_side": "right",
5
+ "padding_value": 0.0,
6
+ "return_attention_mask": false,
7
+ "sampling_rate": 16000
8
+ }
special_tokens_map (1).json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
tokenizer_config (1).json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "return_attention_mask": false, "do_normalize": true}
vocab (1).json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "E": 5, "T": 6, "A": 7, "O": 8, "N": 9, "I": 10, "H": 11, "S": 12, "R": 13, "D": 14, "L": 15, "U": 16, "M": 17, "W": 18, "C": 19, "F": 20, "G": 21, "Y": 22, "P": 23, "B": 24, "V": 25, "K": 26, "'": 27, "X": 28, "J": 29, "Q": 30, "Z": 31}