w2v2-libri-10min / vocab.json
jonik's picture
Upload tokenizer
ec978b8
raw
history blame
331 Bytes
{
"'": 23,
"A": 15,
"B": 16,
"C": 24,
"D": 19,
"E": 25,
"F": 0,
"G": 20,
"H": 14,
"I": 1,
"J": 21,
"K": 3,
"L": 13,
"M": 27,
"N": 17,
"O": 9,
"P": 18,
"Q": 11,
"R": 22,
"S": 10,
"T": 5,
"U": 6,
"V": 2,
"W": 8,
"X": 26,
"Y": 12,
"Z": 4,
"[PAD]": 29,
"[UNK]": 28,
"|": 7
}