thanhduycao commited on
Commit
bb0d81a
1 Parent(s): 276444e

Save step 771

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 110, "</s>": 111}
config.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nguyenvulebinh/wav2vec2-base-vietnamese-250h",
3
+ "activation_dropout": 0.1,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForCTC"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "mean",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": false,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.1,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_dropout_prob": 0.1,
59
+ "hidden_size": 768,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 3072,
62
+ "layer_norm_eps": 1e-05,
63
+ "layerdrop": 0.1,
64
+ "mask_feature_length": 10,
65
+ "mask_feature_min_masks": 0,
66
+ "mask_feature_prob": 0.0,
67
+ "mask_time_length": 10,
68
+ "mask_time_min_masks": 2,
69
+ "mask_time_prob": 0.05,
70
+ "model_type": "wav2vec2",
71
+ "num_adapter_layers": 3,
72
+ "num_attention_heads": 12,
73
+ "num_codevector_groups": 2,
74
+ "num_codevectors_per_group": 320,
75
+ "num_conv_pos_embedding_groups": 16,
76
+ "num_conv_pos_embeddings": 128,
77
+ "num_feat_extract_layers": 7,
78
+ "num_hidden_layers": 12,
79
+ "num_negatives": 100,
80
+ "output_hidden_size": 768,
81
+ "pad_token_id": 109,
82
+ "proj_codevector_dim": 256,
83
+ "tdnn_dilation": [
84
+ 1,
85
+ 2,
86
+ 3,
87
+ 1,
88
+ 1
89
+ ],
90
+ "tdnn_dim": [
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 512,
95
+ 1500
96
+ ],
97
+ "tdnn_kernel": [
98
+ 5,
99
+ 3,
100
+ 3,
101
+ 1,
102
+ 1
103
+ ],
104
+ "torch_dtype": "float32",
105
+ "transformers_version": "4.18.0",
106
+ "use_weighted_layer_sum": false,
107
+ "vocab_size": 110,
108
+ "xvector_output_dim": 512
109
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": false,
9
+ "sampling_rate": 16000
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23059a66883a4629307dd0e14e74da9cf183d28b591f6274d6f7b6b4d58957c0
3
+ size 377898657
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
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": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": "/root/.cache/huggingface/transformers/d60dd610960164f1b79222456db381022e8f93b2f92c21d276f4cd2cb7647737.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd", "name_or_path": "nguyenvulebinh/wav2vec2-base-vietnamese-250h", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2Processor"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"ẻ": 0, "6": 1, "ụ": 2, "í": 3, "3": 4, "ỹ": 5, "ý": 6, "ẩ": 7, "ở": 8, "ề": 9, "õ": 10, "7": 11, "ê": 12, "ứ": 13, "ỏ": 14, "v": 15, "ỷ": 16, "a": 17, "l": 18, "ự": 19, "q": 20, "ờ": 21, "j": 22, "ố": 23, "à": 24, "ỗ": 25, "n": 26, "é": 27, "ủ": 28, "у": 29, "ô": 30, "u": 31, "y": 32, "ằ": 33, "4": 34, "w": 35, "b": 36, "ệ": 37, "ễ": 38, "s": 39, "ì": 40, "ầ": 41, "ỵ": 42, "8": 43, "d": 44, "ể": 45, "r": 47, "ũ": 48, "c": 49, "ạ": 50, "9": 51, "ế": 52, "ù": 53, "ỡ": 54, "2": 55, "t": 56, "i": 57, "g": 58, "́": 59, "ử": 60, "̀": 61, "á": 62, "0": 63, "ậ": 64, "e": 65, "ộ": 66, "m": 67, "ẳ": 68, "ợ": 69, "ĩ": 70, "h": 71, "â": 72, "ú": 73, "ọ": 74, "ồ": 75, "ặ": 76, "f": 77, "ữ": 78, "ắ": 79, "ỳ": 80, "x": 81, "ó": 82, "ã": 83, "ổ": 84, "ị": 85, "̣": 86, "z": 87, "ả": 88, "đ": 89, "è": 90, "ừ": 91, "ò": 92, "ẵ": 93, "1": 94, "ơ": 95, "k": 96, "ẫ": 97, "p": 98, "ấ": 99, "ẽ": 100, "ỉ": 101, "ớ": 102, "ẹ": 103, "ă": 104, "o": 105, "ư": 106, "5": 107, "|": 46, "<unk>": 108, "<pad>": 109}