marma commited on
Commit
8f852d1
1 Parent(s): b43cf91
config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.05,
3
+ "apply_spec_augment": true,
4
+ "architectures": [
5
+ "Wav2Vec2ForCTC"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 1,
9
+ "codevector_dim": 256,
10
+ "contrastive_logits_temperature": 0.1,
11
+ "conv_bias": true,
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": "mean",
40
+ "ctc_zero_infinity": true,
41
+ "diversity_loss_weight": 0.1,
42
+ "do_stable_layer_norm": true,
43
+ "eos_token_id": 2,
44
+ "feat_extract_activation": "gelu",
45
+ "feat_extract_dropout": 0.0,
46
+ "feat_extract_norm": "layer",
47
+ "feat_proj_dropout": 0.05,
48
+ "feat_quantizer_dropout": 0.0,
49
+ "final_dropout": 0.0,
50
+ "gradient_checkpointing": true,
51
+ "hidden_act": "gelu",
52
+ "hidden_dropout": 0.05,
53
+ "hidden_size": 1024,
54
+ "initializer_range": 0.02,
55
+ "intermediate_size": 4096,
56
+ "layer_norm_eps": 1e-05,
57
+ "layerdrop": 0.05,
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
+ "num_attention_heads": 16,
72
+ "num_codevector_groups": 2,
73
+ "num_codevectors_per_group": 320,
74
+ "num_conv_pos_embedding_groups": 16,
75
+ "num_conv_pos_embeddings": 128,
76
+ "num_feat_extract_layers": 7,
77
+ "num_hidden_layers": 24,
78
+ "num_negatives": 100,
79
+ "pad_token_id": 0,
80
+ "proj_codevector_dim": 256,
81
+ "transformers_version": "4.8.2",
82
+ "vocab_size": 46
83
+ }
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": true,
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:c0bf616680f0da867367ec41714df299569dc92f4a049b3a0628c2b12415c50f
3
+ size 1262106353
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>": 0, "<pad>": 1, "</s>": 2, "<unk>": 3, "|": 4, "T": 5, "E": 6, "A": 7, "N": 8, "R": 9, "S": 10, "I": 11, "L": 12, "D": 13, "O": 14, "M": 15, "K": 16, "G": 17, "U": 18, "V": 19, "F": 20, "H": 21, "Ä": 22, "Å": 23, "P": 24, "Ö": 25, "B": 26, "J": 27, "C": 28, "Y": 29, "X": 30, "W": 31, "Z": 32, "É": 33, "Q": 34, "8": 35, "2": 36, "5": 37, "9": 38, "1": 39, "6": 40, "7": 41, "3": 42, "4": 43, "0": 44, "'": 45}