speech-test commited on
Commit
2a456ee
1 Parent(s): b98503d

Upload model

Browse files
config.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "apply_spec_augment": true,
4
+ "architectures": [
5
+ "SEWDForCTC"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "classifier_proj_size": 256,
10
+ "conv_bias": false,
11
+ "conv_dim": [
12
+ 64,
13
+ 128,
14
+ 128,
15
+ 128,
16
+ 128,
17
+ 256,
18
+ 256,
19
+ 256,
20
+ 256,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 1,
30
+ 3,
31
+ 1,
32
+ 3,
33
+ 1,
34
+ 3,
35
+ 1,
36
+ 2,
37
+ 1,
38
+ 2,
39
+ 1
40
+ ],
41
+ "conv_stride": [
42
+ 5,
43
+ 2,
44
+ 1,
45
+ 2,
46
+ 1,
47
+ 2,
48
+ 1,
49
+ 2,
50
+ 1,
51
+ 2,
52
+ 1,
53
+ 2,
54
+ 1
55
+ ],
56
+ "ctc_loss_reduction": "mean",
57
+ "ctc_zero_infinity": false,
58
+ "eos_token_id": 2,
59
+ "feat_extract_activation": "gelu",
60
+ "feat_extract_norm": "group",
61
+ "feat_proj_dropout": 0.0,
62
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
63
+ "final_dropout": 0.0,
64
+ "hidden_act": "gelu",
65
+ "hidden_dropout": 0.0,
66
+ "hidden_size": 384,
67
+ "initializer_range": 0.02,
68
+ "intermediate_size": 1536,
69
+ "layer_norm_eps": 1e-05,
70
+ "layerdrop": 0.1,
71
+ "mask_feature_length": 64,
72
+ "mask_feature_prob": 0.5,
73
+ "mask_time_length": 10,
74
+ "mask_time_prob": 0.65,
75
+ "max_position_embeddings": 512,
76
+ "model_type": "sew-d",
77
+ "norm_rel_ebd": "layer_norm",
78
+ "num_attention_heads": 6,
79
+ "num_conv_pos_embedding_groups": 16,
80
+ "num_conv_pos_embeddings": 31,
81
+ "num_feat_extract_layers": 13,
82
+ "num_hidden_layers": 12,
83
+ "pad_token_id": 0,
84
+ "pos_att_type": [
85
+ "p2c",
86
+ "c2p"
87
+ ],
88
+ "position_biased_input": false,
89
+ "position_buckets": 256,
90
+ "relative_attention": true,
91
+ "share_att_key": true,
92
+ "squeeze_factor": 2,
93
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
94
+ "torch_dtype": "float32",
95
+ "transformers_version": "4.12.0.dev0",
96
+ "use_weighted_layer_sum": false,
97
+ "vocab_size": 32
98
+ }
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 sha256:8dd5d9f5e6aff70472ddf580d5ce0e387f9edfa46e643dcada39bcc8df053684
3
+ size 96600453
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 1, "<pad>": 0, "</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}