Add char vocabulary (128 chars + unk)

vocab.json

@@ -0,0 +1 @@
+{"vocab": {" ": 0, "e": 1, "a": 2, "t": 3, "o": 4, "h": 5, "n": 6, "i": 7, "d": 8, "s": 9, "r": 10, "l": 11, "y": 12, "m": 13, "w": 14, ".": 15, "u": 16, "g": 17, "c": 18, "p": 19, "f": 20, "b": 21, "\n": 22, "k": 23, ",": 24, "T": 25, "v": 26, "\"": 27, "S": 28, "H": 29, "L": 30, "I": 31, "'": 32, "O": 33, "!": 34, "B": 35, "M": 36, "x": 37, "A": 38, "W": 39, "j": 40, "J": 41, "Y": 42, "?": 43, "z": 44, "D": 45, "\u00e2": 46, "\u20ac": 47, "E": 48, "F": 49, "q": 50, "C": 51, "N": 52, "G": 53, "P": 54, "-": 55, "\u0153": 56, "R": 57, "K": 58, "\u2122": 59, ":": 60, "3": 61, "V": 62, "Z": 63, "U": 64, ";": 65, "Q": 66, "\u201c": 67, "1": 68, "0": 69, "\u201d": 70, "\u02dc": 71, "2": 72, "X": 73, "5": 74, "4": 75, "\u00a6": 76, "\u00c3": 77, "\u00a9": 78, "9": 79, "7": 80, "6": 81, "/": 82, "8": 83, "\u00c2": 84, ")": 85, "`": 86, "(": 87, "$": 88, "*": 89, "&": 90, "\u00a0": 91, "\\": 92, "\u00b1": 93, "\u2030": 94, "\u0160": 95, "\u00ab": 96, "\u00bb": 97, "+": 98, "\u00b4": 99, "\u00a1": 100, "\u2039": 101, "#": 102, "\u00ad": 103, "_": 104, "]": 105, "\u2026": 106, "\t": 107, "%": 108, "\u00af": 109, "\u00b3": 110, "\u00b6": 111, "~": 112, "\u2022": 113, "|": 114, "\u201a": 115, "<": 116, ">": 117, "[": 118, "\u00a2": 119, "\u00bf": 120}, "unk": 127, "vocab_size": 128, "n_train_rows": 211971}