Hugging Face's logo

jz703
/
wav2vec2_lj_speech_phonemes_word_level

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
1
jz703 commited on
Commit
f769ff2
·
1 Parent(s): 6d8c276

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