{ " ": 0, "'": 1, "-": 2, "H": 3, "[PAD]": 37, "[UNK]": 36, "a": 4, "b": 5, "d": 6, "e": 7, "f": 8, "g": 9, "h": 10, "i": 11, "j": 12, "k": 13, "l": 14, "m": 15, "n": 16, "o": 17, "q": 18, "r": 19, "s": 20, "t": 21, "u": 22, "w": 23, "y": 24, "z": 25, "|": 35, "ā": 26, "ī": 27, "ū": 28, "ʿ": 29, "ḍ": 30, "ḥ": 31, "ṣ": 32, "ṭ": 33, "ẓ": 34 }