Hugging Face's logo

linlinlin
/
wav2vec2_lj_speech_phonemes_word_level

Model card Files Community
linlinlin commited on
Commit
dd3acf3
·
1 Parent(s): e92df74

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -0
  2. tokenizer_config.json +13 -0
  3. vocab.json +118 -0
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "replace_word_delimiter_char": " ",
9
+ "target_lang": null,
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "aɪ": 98,
3
+ "aɪə": 109,
4
+ "aɪɚ": 23,
5
+ "aʊ": 104,
6
+ "b": 8,
7
+ "d": 93,
8
+ "dʒ": 56,
9
+ "eɪ": 44,
10
+ "f": 58,
11
+ "h": 67,
12
+ "i": 88,
13
+ "iə": 81,
14
+ "iː": 100,
15
+ "j": 115,
16
+ "k": 68,
17
+ "l": 36,
18
+ "m": 51,
19
+ "n": 55,
20
+ "n̩": 7,
21
+ "oʊ": 40,
22
+ "oː": 103,
23
+ "oːɹ": 9,
24
+ "p": 21,
25
+ "r": 72,
26
+ "s": 24,
27
+ "t": 77,
28
+ "tʃ": 114,
29
+ "uː": 57,
30
+ "v": 41,
31
+ "w": 107,
32
+ "x": 73,
33
+ "z": 14,
34
+ "|": 0,
35
+ "æ": 62,
36
+ "ð": 32,
37
+ "ŋ": 89,
38
+ "ɐ": 61,
39
+ "ɑː": 85,
40
+ "ɑːɹ": 84,
41
+ "ɔ": 108,
42
+ "ɔɪ": 97,
43
+ "ɔː": 17,
44
+ "ɔːɹ": 26,
45
+ "ə": 18,
46
+ "əl": 35,
47
+ "ɚ": 10,
48
+ "ɛ": 86,
49
+ "ɛɹ": 78,
50
+ "ɜː": 6,
51
+ "ɡ": 42,
52
+ "ɪ": 87,
53
+ "ɪɹ": 82,
54
+ "ɹ": 20,
55
+ "ɾ": 59,
56
+ "ʃ": 33,
57
+ "ʊ": 54,
58
+ "ʊɹ": 94,
59
+ "ʌ": 74,
60
+ "ʒ": 112,
61
+ "ʔ": 66,
62
+ "ˈaɪ": 52,
63
+ "ˈaɪə": 16,
64
+ "ˈaɪɚ": 101,
65
+ "ˈaʊ": 13,
66
+ "ˈeɪ": 64,
67
+ "ˈiə": 83,
68
+ "ˈiː": 48,
69
+ "ˈoʊ": 49,
70
+ "ˈoː": 34,
71
+ "ˈoːɹ": 90,
72
+ "ˈuː": 69,
73
+ "ˈæ": 19,
74
+ "ˈɑː": 47,
75
+ "ˈɑːɹ": 102,
76
+ "ˈɔ": 50,
77
+ "ˈɔɪ": 43,
78
+ "ˈɔː": 37,
79
+ "ˈɔːɹ": 105,
80
+ "ˈɚ": 5,
81
+ "ˈɛ": 76,
82
+ "ˈɛɹ": 80,
83
+ "ˈɜː": 30,
84
+ "ˈɪ": 31,
85
+ "ˈɪɹ": 39,
86
+ "ˈʊ": 22,
87
+ "ˈʊɹ": 15,
88
+ "ˈʌ": 113,
89
+ "ˌaɪ": 95,
90
+ "ˌaɪɚ": 29,
91
+ "ˌaʊ": 2,
92
+ "ˌeɪ": 79,
93
+ "ˌiə": 11,
94
+ "ˌiː": 25,
95
+ "ˌn̩": 45,
96
+ "ˌoʊ": 70,
97
+ "ˌoː": 28,
98
+ "ˌoːɹ": 110,
99
+ "ˌuː": 75,
100
+ "ˌæ": 106,
101
+ "ˌɐ": 12,
102
+ "ˌɑː": 96,
103
+ "ˌɑːɹ": 111,
104
+ "ˌɔ": 38,
105
+ "ˌɔɪ": 92,
106
+ "ˌɔː": 4,
107
+ "ˌɔːɹ": 46,
108
+ "ˌɛ": 65,
109
+ "ˌɛɹ": 71,
110
+ "ˌɜː": 99,
111
+ "ˌɪ": 91,
112
+ "ˌɪɹ": 27,
113
+ "ˌʊ": 60,
114
+ "ˌʊɹ": 3,
115
+ "ˌʌ": 1,
116
+ "θ": 63,
117
+ "ᵻ": 53
118
+ }