asr-wav2vec2-ctc-MEDIA / tokenizer.ckpt
GaelleLaperriere's picture
Create tokenizer.ckpt
36e6811
'l' => 66
'e' => 1
'c' => 2
'i' => 3
'n' => 4
'q' => 5
't' => 6
'_' => 7
'b' => 8
'j' => 9
'a' => 10
'*' => 11
's' => 12
'-' => 13
'o' => 14
'u' => 15
'à' => 16
'h' => 17
'P' => 18
'r' => 19
'x' => 20
'm' => 21
'p' => 22
'd' => 23
"'" => 24
'ô' => 25
'f' => 26
'k' => 27
'è' => 28
'î' => 29
'M' => 30
'v' => 31
'ç' => 32
'D' => 33
'é' => 34
'g' => 35
'z' => 36
'S' => 37
'C' => 38
'L' => 39
'R' => 40
'I' => 41
'N' => 42
'û' => 43
'y' => 44
'J' => 45
'B' => 46
'O' => 47
'A' => 48
'E' => 49
'H' => 50
'F' => 51
'U' => 52
'ê' => 53
'T' => 54
'V' => 55
'G' => 56
'w' => 57
'ï' => 58
'â' => 59
'É' => 60
'ù' => 61
'ë' => 62
'W' => 63
'Y' => 64
'K' => 65
'<blank>' => 0
================
'starting_index' => 0
'blank_label' => '<blank>'