Upload tokenizer
e834d47 | { |
| "@_c": 69, |
| "@_j": 141, |
| "@_n": 30, |
| "@_t": 89, |
| "[PAD]": 146, |
| "[UNK]": 145, |
| "a_c": 20, |
| "a_j": 3, |
| "a_n": 67, |
| "a_t": 16, |
| "b_c": 51, |
| "b_j": 134, |
| "b_n": 140, |
| "b_t": 26, |
| "d_c": 58, |
| "d_j": 45, |
| "d_n": 64, |
| "d_t": 9, |
| "e_c": 63, |
| "e_j": 25, |
| "e_n": 13, |
| "e_t": 41, |
| "f_c": 39, |
| "f_j": 128, |
| "f_n": 29, |
| "f_t": 109, |
| "i_c": 112, |
| "i_j": 119, |
| "i_n": 93, |
| "i_t": 139, |
| "j_c": 106, |
| "j_j": 87, |
| "j_n": 122, |
| "j_t": 1, |
| "k_c": 107, |
| "k_j": 15, |
| "k_n": 99, |
| "k_t": 101, |
| "l_c": 129, |
| "l_j": 12, |
| "l_n": 65, |
| "l_t": 60, |
| "m_c": 143, |
| "m_j": 84, |
| "m_n": 102, |
| "m_t": 73, |
| "n_c": 27, |
| "n_j": 22, |
| "n_n": 32, |
| "n_t": 6, |
| "o_c": 108, |
| "o_j": 121, |
| "o_n": 110, |
| "o_t": 33, |
| "p_c": 54, |
| "p_j": 132, |
| "p_n": 117, |
| "p_t": 127, |
| "s_c": 85, |
| "s_j": 74, |
| "s_n": 72, |
| "s_t": 28, |
| "t_c": 42, |
| "t_j": 142, |
| "t_n": 52, |
| "t_t": 62, |
| "u_c": 68, |
| "u_j": 135, |
| "u_n": 83, |
| "u_t": 66, |
| "v_c": 35, |
| "v_j": 86, |
| "v_n": 90, |
| "v_t": 81, |
| "w_c": 136, |
| "w_j": 40, |
| "w_n": 144, |
| "w_t": 38, |
| "y_c": 48, |
| "y_j": 36, |
| "y_n": 0, |
| "y_t": 4, |
| "z_c": 53, |
| "z_j": 114, |
| "z_n": 131, |
| "z_t": 126, |
| "|": 138, |
| "ø_c": 56, |
| "ø_j": 113, |
| "ø_n": 21, |
| "ø_t": 8, |
| "œ_c": 61, |
| "œ_j": 137, |
| "œ_n": 77, |
| "œ_t": 124, |
| "œ̃_c": 97, |
| "œ̃_j": 59, |
| "œ̃_n": 130, |
| "œ̃_t": 10, |
| "ɑ_c": 82, |
| "ɑ_j": 18, |
| "ɑ_n": 103, |
| "ɑ_t": 91, |
| "ɑ̃_c": 123, |
| "ɑ̃_j": 120, |
| "ɑ̃_n": 44, |
| "ɑ̃_t": 43, |
| "ɔ_c": 105, |
| "ɔ_j": 50, |
| "ɔ_n": 76, |
| "ɔ_t": 31, |
| "ɔ̃_c": 14, |
| "ɔ̃_j": 88, |
| "ɔ̃_n": 19, |
| "ɔ̃_t": 5, |
| "ɛ_c": 125, |
| "ɛ_j": 7, |
| "ɛ_n": 95, |
| "ɛ_t": 47, |
| "ɛ̃_c": 96, |
| "ɛ̃_j": 111, |
| "ɛ̃_n": 24, |
| "ɛ̃_t": 116, |
| "ɜ_c": 2, |
| "ɜ_j": 100, |
| "ɜ_n": 92, |
| "ɜ_t": 133, |
| "ɡ_c": 70, |
| "ɡ_j": 49, |
| "ɡ_n": 37, |
| "ɡ_t": 75, |
| "ʁ_c": 71, |
| "ʁ_j": 17, |
| "ʁ_n": 55, |
| "ʁ_t": 57, |
| "ʃ_c": 78, |
| "ʃ_j": 98, |
| "ʃ_n": 94, |
| "ʃ_t": 23, |
| "ʊ_c": 79, |
| "ʊ_j": 11, |
| "ʊ_n": 34, |
| "ʊ_t": 115, |
| "ʒ_c": 118, |
| "ʒ_j": 80, |
| "ʒ_n": 46, |
| "ʒ_t": 104 |
| } |
|
|