Hugging Face's logo

HuyenNguyen
/
wav2vec2-large-mms-1b-vi-colab

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
HuyenNguyen commited on
Commit
23784dd
•
1 Parent(s): f386606

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -0
  2. special_tokens_map.json +6 -0
  3. tokenizer_config.json +47 -0
  4. vocab.json +95 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 92,
3
+ "<s>": 91
4
+ }
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 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "89": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "90": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "91": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "92": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "replace_word_delimiter_char": " ",
43
+ "target_lang": "vi",
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vi": {
3
+ "[PAD]": 90,
4
+ "[UNK]": 89,
5
+ "a": 1,
6
+ "b": 2,
7
+ "c": 3,
8
+ "d": 4,
9
+ "e": 5,
10
+ "g": 6,
11
+ "h": 7,
12
+ "i": 8,
13
+ "k": 9,
14
+ "l": 10,
15
+ "m": 11,
16
+ "n": 12,
17
+ "o": 13,
18
+ "p": 14,
19
+ "q": 15,
20
+ "r": 16,
21
+ "s": 17,
22
+ "t": 18,
23
+ "u": 19,
24
+ "v": 20,
25
+ "x": 21,
26
+ "y": 22,
27
+ "|": 0,
28
+ "à": 23,
29
+ "á": 24,
30
+ "â": 25,
31
+ "ã": 26,
32
+ "è": 27,
33
+ "é": 28,
34
+ "ê": 29,
35
+ "ì": 30,
36
+ "í": 31,
37
+ "ò": 32,
38
+ "ó": 33,
39
+ "ô": 34,
40
+ "õ": 35,
41
+ "ù": 36,
42
+ "ú": 37,
43
+ "ý": 38,
44
+ "ă": 39,
45
+ "đ": 40,
46
+ "ĩ": 41,
47
+ "ũ": 42,
48
+ "ơ": 43,
49
+ "ư": 44,
50
+ "ạ": 45,
51
+ "ả": 46,
52
+ "ấ": 47,
53
+ "ầ": 48,
54
+ "ẩ": 49,
55
+ "ẫ": 50,
56
+ "ậ": 51,
57
+ "ắ": 52,
58
+ "ằ": 53,
59
+ "ẳ": 54,
60
+ "ẵ": 55,
61
+ "ặ": 56,
62
+ "ẹ": 57,
63
+ "ẻ": 58,
64
+ "ẽ": 59,
65
+ "ế": 60,
66
+ "ề": 61,
67
+ "ể": 62,
68
+ "ễ": 63,
69
+ "ệ": 64,
70
+ "ỉ": 65,
71
+ "ị": 66,
72
+ "ọ": 67,
73
+ "ỏ": 68,
74
+ "ố": 69,
75
+ "ồ": 70,
76
+ "ổ": 71,
77
+ "ỗ": 72,
78
+ "ộ": 73,
79
+ "ớ": 74,
80
+ "ờ": 75,
81
+ "ở": 76,
82
+ "ỡ": 77,
83
+ "ợ": 78,
84
+ "ụ": 79,
85
+ "ủ": 80,
86
+ "ứ": 81,
87
+ "ừ": 82,
88
+ "ử": 83,
89
+ "ữ": 84,
90
+ "ự": 85,
91
+ "ỳ": 86,
92
+ "ỷ": 87,
93
+ "ỹ": 88
94
+ }
95
+ }