Hugging Face's logo

ctaguchi
/
ssc-aln-mms-model

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
 Community
ctaguchi commited on
Commit
a300a54
·
verified ·
1 Parent(s): 32899d0

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 +120 -0
  4. vocab.json +52 -1
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 49,
3
+ "<s>": 48
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 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "1": {
4
+ "content": "th",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "3": {
12
+ "content": "dh",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "11": {
20
+ "content": "nj",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "22": {
28
+ "content": "gj",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "23": {
36
+ "content": "xh",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "32": {
44
+ "content": "rr",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "36": {
52
+ "content": "sh",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "44": {
60
+ "content": "zh",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "45": {
68
+ "content": "ll",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "46": {
76
+ "content": "[UNK]",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "47": {
84
+ "content": "[PAD]",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "48": {
92
+ "content": "<s>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "49": {
100
+ "content": "</s>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ }
107
+ },
108
+ "bos_token": "<s>",
109
+ "clean_up_tokenization_spaces": false,
110
+ "do_lower_case": false,
111
+ "eos_token": "</s>",
112
+ "extra_special_tokens": {},
113
+ "model_max_length": 1000000000000000019884624838656,
114
+ "pad_token": "[PAD]",
115
+ "replace_word_delimiter_char": " ",
116
+ "target_lang": "aln",
117
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
118
+ "unk_token": "[UNK]",
119
+ "word_delimiter_token": "|"
120
+ }
vocab.json CHANGED
@@ -1 +1,52 @@
1
- {"xh": 0, "\u03b5": 1, "\u03c3": 2, "\u03b1": 3, "u": 4, "x": 5, "q": 6, "\u03ac": 7, "dh": 8, "rr": 9, "k": 10, "ll": 11, "sh": 12, "th": 13, "a": 14, "'": 15, "w": 16, "t": 17, "\u03ad": 18, "p": 19, "\u03bd": 20, "n": 21, "b": 22, "l": 23, "\u03c4": 24, "zh": 25, "gj": 26, "e": 27, "d": 28, "z": 29, "g": 30, "i": 31, "m": 32, "nj": 33, "j": 34, "y": 35, "\u03ba": 36, "s": 37, "\u03c0": 38, "r": 39, "o": 40, "v": 42, "h": 43, "f": 44, "c": 45, "|": 41, "[UNK]": 46, "[PAD]": 47}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "aln": {
3
+ "'": 42,
4
+ "[PAD]": 47,
5
+ "[UNK]": 46,
6
+ "a": 4,
7
+ "b": 2,
8
+ "c": 38,
9
+ "d": 13,
10
+ "dh": 3,
11
+ "e": 28,
12
+ "f": 31,
13
+ "g": 14,
14
+ "gj": 22,
15
+ "h": 40,
16
+ "i": 30,
17
+ "j": 6,
18
+ "k": 8,
19
+ "l": 35,
20
+ "ll": 45,
21
+ "m": 12,
22
+ "n": 26,
23
+ "nj": 11,
24
+ "o": 21,
25
+ "p": 27,
26
+ "q": 20,
27
+ "r": 10,
28
+ "rr": 32,
29
+ "s": 41,
30
+ "sh": 36,
31
+ "t": 19,
32
+ "th": 1,
33
+ "u": 9,
34
+ "v": 17,
35
+ "w": 18,
36
+ "x": 39,
37
+ "xh": 23,
38
+ "y": 25,
39
+ "z": 0,
40
+ "zh": 44,
41
+ "|": 15,
42
+ "ά": 24,
43
+ "έ": 33,
44
+ "α": 7,
45
+ "ε": 29,
46
+ "κ": 37,
47
+ "ν": 16,
48
+ "π": 34,
49
+ "σ": 5,
50
+ "τ": 43
51
+ }
52
+ }