Feature Extraction
Transformers
PyTorch
Safetensors
Fairseq
French
pantagruel_uni
data2vec2
JEPA
speech
custom_code
flaubert commited on
Commit
ca4a86a
verified
1 Parent(s): 3f0e4de

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. vocab.json +75 -75
vocab.json CHANGED
@@ -4,79 +4,79 @@
4
  "</s>": 2,
5
  "<unk>": 3,
6
  "|": 4,
7
- "E": 4,
8
- "S": 4,
9
- "A": 4,
10
- "T": 4,
11
- "I": 4,
12
- "N": 4,
13
- "R": 4,
14
- "L": 4,
15
- "U": 4,
16
- "O": 4,
17
- "D": 4,
18
- "C": 4,
19
- "M": 4,
20
- "P": 4,
21
- "脡": 4,
22
- "V": 4,
23
- "G": 4,
24
- "'": 4,
25
- "F": 4,
26
- "B": 4,
27
- "H": 4,
28
- "Q": 4,
29
- "脠": 4,
30
- "脌": 4,
31
- "X": 4,
32
- "J": 4,
33
- "Y": 4,
34
- "K": 4,
35
- "Z": 4,
36
- "脢": 4,
37
- "W": 4,
38
- "脟": 4,
39
- "脗": 4,
40
- "脭": 4,
41
- "脦": 4,
42
- "脧": 4,
43
- "脹": 4,
44
- "脵": 4,
45
- "脕": 4,
46
- "脣": 4,
47
- "脥": 4,
48
- "脺": 4,
49
- "脰": 4,
50
- "脫": 4,
51
- "脛": 4,
52
- "脩": 4,
53
- "脷": 4,
54
- "脴": 4,
55
- "脙": 4,
56
- "脝": 4,
57
- "脜": 4,
58
- "脻": 4,
59
- "脪": 4,
60
- "脨": 4,
61
- "脤": 4,
62
- "脮": 4,
63
- "脼": 4,
64
- "袚": 4,
65
- "袗": 4,
66
- "袝": 4,
67
- "袉": 4,
68
- "袌": 4,
69
- "袟": 4,
70
- "袠": 4,
71
- "袣": 4,
72
- "袦": 4,
73
- "袧": 4,
74
- "袩": 4,
75
- "袪": 4,
76
- "协": 4,
77
- "要": 4,
78
- "madeupword0000": 4,
79
- "madeupword0001": 4,
80
- "madeupword0002": 4,
81
- "madeupword0003": 4
82
  }
 
4
  "</s>": 2,
5
  "<unk>": 3,
6
  "|": 4,
7
+ "E": 5,
8
+ "S": 6,
9
+ "A": 7,
10
+ "T": 8,
11
+ "I": 9,
12
+ "N": 10,
13
+ "R": 11,
14
+ "L": 12,
15
+ "U": 13,
16
+ "O": 14,
17
+ "D": 15,
18
+ "C": 16,
19
+ "M": 17,
20
+ "P": 18,
21
+ "脡": 19,
22
+ "V": 20,
23
+ "G": 21,
24
+ "'": 22,
25
+ "F": 23,
26
+ "B": 24,
27
+ "H": 25,
28
+ "Q": 26,
29
+ "脠": 27,
30
+ "脌": 28,
31
+ "X": 29,
32
+ "J": 30,
33
+ "Y": 31,
34
+ "K": 32,
35
+ "Z": 33,
36
+ "脢": 34,
37
+ "W": 35,
38
+ "脟": 36,
39
+ "脗": 37,
40
+ "脭": 38,
41
+ "脦": 39,
42
+ "脧": 40,
43
+ "脹": 41,
44
+ "脵": 42,
45
+ "脕": 43,
46
+ "脣": 44,
47
+ "脥": 45,
48
+ "脺": 46,
49
+ "脰": 47,
50
+ "脫": 48,
51
+ "脛": 49,
52
+ "脩": 50,
53
+ "脷": 51,
54
+ "脴": 52,
55
+ "脙": 53,
56
+ "脝": 54,
57
+ "脜": 55,
58
+ "脻": 56,
59
+ "脪": 57,
60
+ "脨": 58,
61
+ "脤": 59,
62
+ "脮": 60,
63
+ "脼": 61,
64
+ "袚": 62,
65
+ "袗": 63,
66
+ "袝": 64,
67
+ "袉": 65,
68
+ "袌": 66,
69
+ "袟": 67,
70
+ "袠": 68,
71
+ "袣": 69,
72
+ "袦": 70,
73
+ "袧": 71,
74
+ "袩": 72,
75
+ "袪": 73,
76
+ "协": 74,
77
+ "要": 75,
78
+ "madeupword0000": 76,
79
+ "madeupword0001": 77,
80
+ "madeupword0002": 78,
81
+ "madeupword0003": 79
82
  }