PL-ModernBERT-gl / phoneme_token_maps.json
cmagui's picture
Initial release: weights, model card, and phoneme token maps
6e02c4c verified
Raw
History Blame Contribute Delete
5.13 kB
{
"0": {
"phoneme": "X",
"token": 0,
"grapheme" : " "
},
"1": {
"phoneme": " ",
"token": 1,
"grapheme" : " "
},
"2": {
"phoneme": "$",
"token": 2,
"grapheme" : " "
},
"3": {
"phoneme": "M",
"token": 3,
"grapheme" : " "
},
"4": {
"phoneme": ",",
"token": 4,
"grapheme" :","
},
"5": {
"phoneme": ".",
"token": 5,
"grapheme" :"."
},
"6": {
"phoneme": "a",
"token": 6,
"grapheme" :"a"
},
"7": {
"phoneme": "E",
"token": 7,
"grapheme" : "e"
},
"8": {
"phoneme": "e",
"token": 8,
"grapheme" : "e"
},
"9": {
"phoneme": "i",
"token": 9,
"grapheme" : "i"
},
"10": {
"phoneme": "j",
"token": 10,
"grapheme" : "i"
},
"11": {
"phoneme": "O",
"token": 11,
"grapheme" : "o"
},
"12": {
"phoneme": "o",
"token": 12,
"grapheme" : "o"
},
"13": {
"phoneme": "u",
"token": 13,
"grapheme" : "u"
},
"14": {
"phoneme": "w",
"token": 14,
"grapheme" : "u"
},
"15": {
"phoneme": "p",
"token": 15,
"grapheme" : "p"
},
"16": {
"phoneme": "b",
"token": 16,
"grapheme" : "b"
},
"17": {
"phoneme": "B",
"token": 17,
"grapheme" : "b"
},
"18": {
"phoneme": "t",
"token": 18,
"grapheme" : "t"
},
"19": {
"phoneme": "d",
"token": 19,
"grapheme" : "d"
},
"20": {
"phoneme": "D",
"token": 20,
"grapheme" : "d"
},
"21": {
"phoneme": "k",
"token": 21,
"grapheme" : "c"
},
"22": {
"phoneme": "g",
"token": 22,
"grapheme" : "g"
},
"23": {
"phoneme": "G",
"token": 23,
"grapheme" : "g"
},
"24": {
"phoneme": "f",
"token": 24,
"grapheme" : "f"
},
"25": {
"phoneme": "T",
"token": 25,
"grapheme" : "z"
},
"26": {
"phoneme": "s",
"token": 26,
"grapheme" : "s"
},
"27": {
"phoneme": "S",
"token": 27,
"grapheme" : "x"
},
"28": {
"phoneme": "m",
"token": 28,
"grapheme" : "m"
},
"29": {
"phoneme": "n",
"token": 29,
"grapheme" : "n"
},
"30": {
"phoneme": "J",
"token": 30,
"grapheme" : "ñ"
},
"31": {
"phoneme": "N",
"token": 31,
"grapheme" : "nh"
},
"32": {
"phoneme": "l",
"token": 32,
"grapheme" : "l"
},
"33": {
"phoneme": "Z",
"token": 33,
"grapheme" : "ll"
},
"34": {
"phoneme": "r",
"token": 34,
"grapheme" : "r"
},
"35": {
"phoneme": "R",
"token": 35,
"grapheme" : "rr"
},
"36": {
"phoneme": "x",
"token": 36,
"grapheme" : "j"
},
"37": {
"phoneme": "C",
"token": 37,
"grapheme" : "ch"
},
"38": {
"phoneme": "!",
"token": 38,
"grapheme" : "!"
},
"39": {
"phoneme": "\"",
"token": 39,
"grapheme" : "\""
},
"40": {
"phoneme": "(",
"token": 40,
"grapheme" : "("
},
"41": {
"phoneme": ")",
"token": 41,
"grapheme" : ")"
},
"42": {
"phoneme": "/",
"token": 42,
"grapheme" : "/"
},
"43": {
"phoneme": ":",
"token": 43,
"grapheme" : ":"
},
"44": {
"phoneme": ";",
"token": 44,
"grapheme" : ";"
},
"45": {
"phoneme": "?",
"token": 45,
"grapheme" : "?"
},
"46": {
"phoneme": "[",
"token": 46,
"grapheme" : "["
},
"47": {
"phoneme": "]",
"token": 47,
"grapheme" : "]"
},
"48": {
"phoneme": "{",
"token": 48,
"grapheme" : "{"
},
"49": {
"phoneme": "}",
"token": 49,
"grapheme" : "}"
},
"50": {
"phoneme": "¡",
"token": 50,
"grapheme" : "¡"
},
"51": {
"phoneme": "º",
"token": 51,
"grapheme" : "º"
},
"52": {
"phoneme": "ª",
"token": 52,
"grapheme" : "ª"
},
"53": {
"phoneme": "`",
"token": 53,
"grapheme" : "`"
},
"54": {
"phoneme": "¿",
"token": 54,
"grapheme" : "¿"
},
"55": {
"phoneme": "K",
"token": 55,
"grapheme" : "x"
},
"56": {
"phoneme": "W",
"token": 56,
"grapheme" : "x"
},
"57": {
"phoneme": "O",
"token": 57,
"grapheme" : "ao"
},
"58": {
"phoneme": "W",
"token": 58,
"grapheme" : "tS"
},
"59": {
"phoneme": "á",
"token": 59,
"grapheme" : "á"
},
"60": {
"phoneme": "É",
"token": 60,
"grapheme" : "é"
},
"61": {
"phoneme": "é",
"token": 61,
"grapheme" : "é"
},
"62": {
"phoneme": "í",
"token": 62,
"grapheme" : "í"
},
"63": {
"phoneme": "j́",
"token": 63,
"grapheme" : "í"
},
"64": {
"phoneme": "Ó",
"token": 64,
"grapheme" : "ó"
},
"65": {
"phoneme": "ó",
"token": 65,
"grapheme" : "ó"
},
"66": {
"phoneme": "ú",
"token": 66,
"grapheme" : "ú"
},
"67": {
"phoneme": "ẃ",
"token": 67,
"grapheme" : "ú"
},
"68": {
"phoneme": "s",
"token": 68,
"grapheme" : "ps"
},
"69": {
"phoneme": "n",
"token": 69,
"grapheme" : "pn"
}
}