Upload tokenizer_results.json with huggingface_hub
Browse files- tokenizer_results.json +674 -0
tokenizer_results.json
ADDED
|
@@ -0,0 +1,674 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"name":"shared_bpe_8000",
|
| 4 |
+
"tokenizer_type":"shared",
|
| 5 |
+
"algorithm":"BPE",
|
| 6 |
+
"vocab_size":8000,
|
| 7 |
+
"fertility_overall":1.7787163674,
|
| 8 |
+
"cpt_overall":3.0049111942,
|
| 9 |
+
"fertility_disparity":0.2198677878,
|
| 10 |
+
"cpt_disparity":0.645823621,
|
| 11 |
+
"oov_disparity":0.0,
|
| 12 |
+
"vocab_gini":0.7709496335,
|
| 13 |
+
"shannon_entropy":10.5561176463,
|
| 14 |
+
"exact_match_rate":0.99,
|
| 15 |
+
"morph_edit_distance_ar":4.1755236174,
|
| 16 |
+
"morph_consistency_precision":0.1706382107,
|
| 17 |
+
"morph_consistency_recall":0.1556559587,
|
| 18 |
+
"morph_consistency_f1":0.161694338,
|
| 19 |
+
"ar_fertility":1.656426646,
|
| 20 |
+
"ar_cpt":3.3838216268,
|
| 21 |
+
"ar_oov_rate":0.0,
|
| 22 |
+
"ar_mean_seq_len":17.6595461798,
|
| 23 |
+
"ar_median_seq_len":17.0,
|
| 24 |
+
"az_fertility":1.8762944338,
|
| 25 |
+
"az_cpt":2.7379980058,
|
| 26 |
+
"az_oov_rate":0.0,
|
| 27 |
+
"az_mean_seq_len":25.9109200496,
|
| 28 |
+
"az_median_seq_len":26.0
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"name":"concat_bpe_8000",
|
| 32 |
+
"tokenizer_type":"concatenated",
|
| 33 |
+
"algorithm":"BPE",
|
| 34 |
+
"vocab_size":8000,
|
| 35 |
+
"fertility_overall":1.6889873506,
|
| 36 |
+
"cpt_overall":3.1645498835,
|
| 37 |
+
"fertility_disparity":0.1648715075,
|
| 38 |
+
"cpt_disparity":0.0316881659,
|
| 39 |
+
"oov_disparity":0.0,
|
| 40 |
+
"vocab_gini":0.6849702921,
|
| 41 |
+
"shannon_entropy":10.9244878509,
|
| 42 |
+
"exact_match_rate":0.99,
|
| 43 |
+
"morph_edit_distance_ar":4.2157843708,
|
| 44 |
+
"morph_consistency_precision":0.1569809449,
|
| 45 |
+
"morph_consistency_recall":0.1856069998,
|
| 46 |
+
"morph_consistency_f1":0.1679847615,
|
| 47 |
+
"ar_fertility":1.7806883265,
|
| 48 |
+
"ar_cpt":3.1476885788,
|
| 49 |
+
"ar_oov_rate":0.0,
|
| 50 |
+
"ar_mean_seq_len":19.1354369793,
|
| 51 |
+
"ar_median_seq_len":19.0,
|
| 52 |
+
"az_fertility":1.615816819,
|
| 53 |
+
"az_cpt":3.1793767446,
|
| 54 |
+
"az_oov_rate":0.0,
|
| 55 |
+
"az_mean_seq_len":22.036429711,
|
| 56 |
+
"az_median_seq_len":22.0
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"name":"shared_unigram_8000",
|
| 60 |
+
"tokenizer_type":"shared",
|
| 61 |
+
"algorithm":"Unigram",
|
| 62 |
+
"vocab_size":8000,
|
| 63 |
+
"fertility_overall":1.7790411363,
|
| 64 |
+
"cpt_overall":3.0043626393,
|
| 65 |
+
"fertility_disparity":0.1474708507,
|
| 66 |
+
"cpt_disparity":0.5176722057,
|
| 67 |
+
"oov_disparity":0.0,
|
| 68 |
+
"vocab_gini":0.8189437499,
|
| 69 |
+
"shannon_entropy":10.165482266,
|
| 70 |
+
"exact_match_rate":0.99,
|
| 71 |
+
"morph_edit_distance_ar":4.1823029664,
|
| 72 |
+
"morph_consistency_precision":0.1498923892,
|
| 73 |
+
"morph_consistency_recall":0.2196576099,
|
| 74 |
+
"morph_consistency_f1":0.1770370715,
|
| 75 |
+
"ar_fertility":1.6970183469,
|
| 76 |
+
"ar_cpt":3.3028825634,
|
| 77 |
+
"ar_oov_rate":0.0,
|
| 78 |
+
"ar_mean_seq_len":18.1438574721,
|
| 79 |
+
"ar_median_seq_len":18.0,
|
| 80 |
+
"az_fertility":1.8444891977,
|
| 81 |
+
"az_cpt":2.7852103577,
|
| 82 |
+
"az_oov_rate":0.0,
|
| 83 |
+
"az_mean_seq_len":25.4391065414,
|
| 84 |
+
"az_median_seq_len":25.0
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"name":"concat_unigram_8000",
|
| 88 |
+
"tokenizer_type":"concatenated",
|
| 89 |
+
"algorithm":"Unigram",
|
| 90 |
+
"vocab_size":8000,
|
| 91 |
+
"fertility_overall":1.6947867958,
|
| 92 |
+
"cpt_overall":3.1537210089,
|
| 93 |
+
"fertility_disparity":0.1669302238,
|
| 94 |
+
"cpt_disparity":0.0343315623,
|
| 95 |
+
"oov_disparity":0.0,
|
| 96 |
+
"vocab_gini":0.7623152124,
|
| 97 |
+
"shannon_entropy":10.4233732784,
|
| 98 |
+
"exact_match_rate":0.99,
|
| 99 |
+
"morph_edit_distance_ar":4.2111496914,
|
| 100 |
+
"morph_consistency_precision":0.1450557842,
|
| 101 |
+
"morph_consistency_recall":0.2404900444,
|
| 102 |
+
"morph_consistency_f1":0.1800784056,
|
| 103 |
+
"ar_fertility":1.7876328228,
|
| 104 |
+
"ar_cpt":3.1354606137,
|
| 105 |
+
"ar_oov_rate":0.0,
|
| 106 |
+
"ar_mean_seq_len":19.2194646339,
|
| 107 |
+
"ar_median_seq_len":19.0,
|
| 108 |
+
"az_fertility":1.620702599,
|
| 109 |
+
"az_cpt":3.169792176,
|
| 110 |
+
"az_oov_rate":0.0,
|
| 111 |
+
"az_mean_seq_len":22.1099982273,
|
| 112 |
+
"az_median_seq_len":22.0
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"name":"shared_wordpiece_8000",
|
| 116 |
+
"tokenizer_type":"shared",
|
| 117 |
+
"algorithm":"WordPiece",
|
| 118 |
+
"vocab_size":8000,
|
| 119 |
+
"fertility_overall":1.7761712394,
|
| 120 |
+
"cpt_overall":3.0092170198,
|
| 121 |
+
"fertility_disparity":0.226757188,
|
| 122 |
+
"cpt_disparity":0.6596486988,
|
| 123 |
+
"oov_disparity":0.0,
|
| 124 |
+
"vocab_gini":0.7564900789,
|
| 125 |
+
"shannon_entropy":10.5708706321,
|
| 126 |
+
"exact_match_rate":0.99,
|
| 127 |
+
"morph_edit_distance_ar":4.1765983213,
|
| 128 |
+
"morph_consistency_precision":0.163672929,
|
| 129 |
+
"morph_consistency_recall":0.1493781435,
|
| 130 |
+
"morph_consistency_f1":0.1551907022,
|
| 131 |
+
"ar_fertility":1.6500496569,
|
| 132 |
+
"ar_cpt":3.3968991687,
|
| 133 |
+
"ar_oov_rate":0.0,
|
| 134 |
+
"ar_mean_seq_len":17.5850912959,
|
| 135 |
+
"ar_median_seq_len":17.0,
|
| 136 |
+
"az_fertility":1.8768068449,
|
| 137 |
+
"az_cpt":2.7372504699,
|
| 138 |
+
"az_oov_rate":0.0,
|
| 139 |
+
"az_mean_seq_len":25.9190746322,
|
| 140 |
+
"az_median_seq_len":25.0
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"name":"concat_wordpiece_8000",
|
| 144 |
+
"tokenizer_type":"concatenated",
|
| 145 |
+
"algorithm":"WordPiece",
|
| 146 |
+
"vocab_size":8000,
|
| 147 |
+
"fertility_overall":1.6962184303,
|
| 148 |
+
"cpt_overall":3.1510592198,
|
| 149 |
+
"fertility_disparity":0.1560458869,
|
| 150 |
+
"cpt_disparity":0.0140028965,
|
| 151 |
+
"oov_disparity":0.0,
|
| 152 |
+
"vocab_gini":0.6600277207,
|
| 153 |
+
"shannon_entropy":10.9155665053,
|
| 154 |
+
"exact_match_rate":0.99,
|
| 155 |
+
"morph_edit_distance_ar":4.219108083,
|
| 156 |
+
"morph_consistency_precision":0.1522420473,
|
| 157 |
+
"morph_consistency_recall":0.175816502,
|
| 158 |
+
"morph_consistency_f1":0.1618608459,
|
| 159 |
+
"ar_fertility":1.7830106258,
|
| 160 |
+
"ar_cpt":3.1435888416,
|
| 161 |
+
"ar_oov_rate":0.0,
|
| 162 |
+
"ar_mean_seq_len":19.163623471,
|
| 163 |
+
"ar_median_seq_len":19.0,
|
| 164 |
+
"az_fertility":1.626964739,
|
| 165 |
+
"az_cpt":3.1575917381,
|
| 166 |
+
"az_oov_rate":0.0,
|
| 167 |
+
"az_mean_seq_len":22.2024463748,
|
| 168 |
+
"az_median_seq_len":22.0
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"name":"shared_bbpe_8000",
|
| 172 |
+
"tokenizer_type":"shared",
|
| 173 |
+
"algorithm":"BBPE",
|
| 174 |
+
"vocab_size":8000,
|
| 175 |
+
"fertility_overall":1.9554271209,
|
| 176 |
+
"cpt_overall":2.7333592066,
|
| 177 |
+
"fertility_disparity":0.4718091571,
|
| 178 |
+
"cpt_disparity":0.9376231111,
|
| 179 |
+
"oov_disparity":0.0,
|
| 180 |
+
"vocab_gini":0.8121558079,
|
| 181 |
+
"shannon_entropy":9.9528287353,
|
| 182 |
+
"exact_match_rate":0.99,
|
| 183 |
+
"morph_edit_distance_ar":4.1921228413,
|
| 184 |
+
"morph_consistency_precision":0.1550132007,
|
| 185 |
+
"morph_consistency_recall":0.2827125976,
|
| 186 |
+
"morph_consistency_f1":0.1995081577,
|
| 187 |
+
"ar_fertility":1.6930084603,
|
| 188 |
+
"ar_cpt":3.310705433,
|
| 189 |
+
"ar_oov_rate":0.0,
|
| 190 |
+
"ar_mean_seq_len":18.0962595285,
|
| 191 |
+
"ar_median_seq_len":18.0,
|
| 192 |
+
"az_fertility":2.1648176174,
|
| 193 |
+
"az_cpt":2.3730823219,
|
| 194 |
+
"az_oov_rate":0.0,
|
| 195 |
+
"az_mean_seq_len":30.2043963836,
|
| 196 |
+
"az_median_seq_len":30.0
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"name":"concat_bbpe_8000",
|
| 200 |
+
"tokenizer_type":"concatenated",
|
| 201 |
+
"algorithm":"BBPE",
|
| 202 |
+
"vocab_size":8000,
|
| 203 |
+
"fertility_overall":1.8827749848,
|
| 204 |
+
"cpt_overall":2.8388335126,
|
| 205 |
+
"fertility_disparity":0.116792759,
|
| 206 |
+
"cpt_disparity":0.4279320309,
|
| 207 |
+
"oov_disparity":0.0,
|
| 208 |
+
"vocab_gini":0.7491107045,
|
| 209 |
+
"shannon_entropy":10.2263454675,
|
| 210 |
+
"exact_match_rate":0.99,
|
| 211 |
+
"morph_edit_distance_ar":4.2316542111,
|
| 212 |
+
"morph_consistency_precision":0.1588581248,
|
| 213 |
+
"morph_consistency_recall":0.3282934754,
|
| 214 |
+
"morph_consistency_f1":0.2135590301,
|
| 215 |
+
"ar_fertility":1.8178152465,
|
| 216 |
+
"ar_cpt":3.0834004272,
|
| 217 |
+
"ar_oov_rate":0.0,
|
| 218 |
+
"ar_mean_seq_len":19.5777344442,
|
| 219 |
+
"ar_median_seq_len":19.0,
|
| 220 |
+
"az_fertility":1.9346080055,
|
| 221 |
+
"az_cpt":2.6554683963,
|
| 222 |
+
"az_oov_rate":0.0,
|
| 223 |
+
"az_mean_seq_len":26.7797376352,
|
| 224 |
+
"az_median_seq_len":26.0
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"name":"shared_bpe_16000",
|
| 228 |
+
"tokenizer_type":"shared",
|
| 229 |
+
"algorithm":"BPE",
|
| 230 |
+
"vocab_size":16000,
|
| 231 |
+
"fertility_overall":1.5971771615,
|
| 232 |
+
"cpt_overall":3.3464570197,
|
| 233 |
+
"fertility_disparity":0.1510951681,
|
| 234 |
+
"cpt_disparity":0.6173754613,
|
| 235 |
+
"oov_disparity":0.0,
|
| 236 |
+
"vocab_gini":0.7920106017,
|
| 237 |
+
"shannon_entropy":11.090783206,
|
| 238 |
+
"exact_match_rate":0.99,
|
| 239 |
+
"morph_edit_distance_ar":4.1164562127,
|
| 240 |
+
"morph_consistency_precision":0.1645828627,
|
| 241 |
+
"morph_consistency_recall":0.111253923,
|
| 242 |
+
"morph_consistency_f1":0.1323611335,
|
| 243 |
+
"ar_fertility":1.513138539,
|
| 244 |
+
"ar_cpt":3.7042558651,
|
| 245 |
+
"ar_oov_rate":0.0,
|
| 246 |
+
"ar_mean_seq_len":15.9586952668,
|
| 247 |
+
"ar_median_seq_len":16.0,
|
| 248 |
+
"az_fertility":1.6642337071,
|
| 249 |
+
"az_cpt":3.0868804038,
|
| 250 |
+
"az_oov_rate":0.0,
|
| 251 |
+
"az_mean_seq_len":22.756248892,
|
| 252 |
+
"az_median_seq_len":22.0
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"name":"concat_bpe_16000",
|
| 256 |
+
"tokenizer_type":"concatenated",
|
| 257 |
+
"algorithm":"BPE",
|
| 258 |
+
"vocab_size":16000,
|
| 259 |
+
"fertility_overall":1.5165781285,
|
| 260 |
+
"cpt_overall":3.5243055556,
|
| 261 |
+
"fertility_disparity":0.1426774709,
|
| 262 |
+
"cpt_disparity":0.0229367001,
|
| 263 |
+
"oov_disparity":0.0,
|
| 264 |
+
"vocab_gini":0.7224875042,
|
| 265 |
+
"shannon_entropy":11.453646644,
|
| 266 |
+
"exact_match_rate":0.99,
|
| 267 |
+
"morph_edit_distance_ar":4.1531217,
|
| 268 |
+
"morph_consistency_precision":0.1543768971,
|
| 269 |
+
"morph_consistency_recall":0.1249030296,
|
| 270 |
+
"morph_consistency_f1":0.1376491323,
|
| 271 |
+
"ar_fertility":1.5959348561,
|
| 272 |
+
"ar_cpt":3.5120808886,
|
| 273 |
+
"ar_oov_rate":0.0,
|
| 274 |
+
"ar_mean_seq_len":16.9423861018,
|
| 275 |
+
"ar_median_seq_len":17.0,
|
| 276 |
+
"az_fertility":1.4532573853,
|
| 277 |
+
"az_cpt":3.5350175887,
|
| 278 |
+
"az_oov_rate":0.0,
|
| 279 |
+
"az_mean_seq_len":19.6181528098,
|
| 280 |
+
"az_median_seq_len":19.0
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"name":"shared_unigram_16000",
|
| 284 |
+
"tokenizer_type":"shared",
|
| 285 |
+
"algorithm":"Unigram",
|
| 286 |
+
"vocab_size":16000,
|
| 287 |
+
"fertility_overall":1.6212862838,
|
| 288 |
+
"cpt_overall":3.296693975,
|
| 289 |
+
"fertility_disparity":0.0885280481,
|
| 290 |
+
"cpt_disparity":0.4717666206,
|
| 291 |
+
"oov_disparity":0.0,
|
| 292 |
+
"vocab_gini":0.8334856469,
|
| 293 |
+
"shannon_entropy":10.5776002094,
|
| 294 |
+
"exact_match_rate":0.99,
|
| 295 |
+
"morph_edit_distance_ar":4.1315210046,
|
| 296 |
+
"morph_consistency_precision":0.1557524276,
|
| 297 |
+
"morph_consistency_recall":0.1706022629,
|
| 298 |
+
"morph_consistency_f1":0.1622742892,
|
| 299 |
+
"ar_fertility":1.5720472823,
|
| 300 |
+
"ar_cpt":3.5654476623,
|
| 301 |
+
"ar_oov_rate":0.0,
|
| 302 |
+
"ar_mean_seq_len":16.6604325474,
|
| 303 |
+
"ar_median_seq_len":16.0,
|
| 304 |
+
"az_fertility":1.6605753304,
|
| 305 |
+
"az_cpt":3.0936810417,
|
| 306 |
+
"az_oov_rate":0.0,
|
| 307 |
+
"az_mean_seq_len":22.7031554689,
|
| 308 |
+
"az_median_seq_len":22.0
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"name":"concat_unigram_16000",
|
| 312 |
+
"tokenizer_type":"concatenated",
|
| 313 |
+
"algorithm":"Unigram",
|
| 314 |
+
"vocab_size":16000,
|
| 315 |
+
"fertility_overall":1.541731151,
|
| 316 |
+
"cpt_overall":3.4668072447,
|
| 317 |
+
"fertility_disparity":0.1464437495,
|
| 318 |
+
"cpt_disparity":0.0256827057,
|
| 319 |
+
"oov_disparity":0.0,
|
| 320 |
+
"vocab_gini":0.7918225207,
|
| 321 |
+
"shannon_entropy":10.8508668291,
|
| 322 |
+
"exact_match_rate":0.99,
|
| 323 |
+
"morph_edit_distance_ar":4.1582156543,
|
| 324 |
+
"morph_consistency_precision":0.1464142753,
|
| 325 |
+
"morph_consistency_recall":0.1741476553,
|
| 326 |
+
"morph_consistency_f1":0.1574918159,
|
| 327 |
+
"ar_fertility":1.6231826701,
|
| 328 |
+
"ar_cpt":3.4531247844,
|
| 329 |
+
"ar_oov_rate":0.0,
|
| 330 |
+
"ar_mean_seq_len":17.2674171246,
|
| 331 |
+
"ar_median_seq_len":17.0,
|
| 332 |
+
"az_fertility":1.4767389206,
|
| 333 |
+
"az_cpt":3.4788074901,
|
| 334 |
+
"az_oov_rate":0.0,
|
| 335 |
+
"az_mean_seq_len":19.9683566743,
|
| 336 |
+
"az_median_seq_len":20.0
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"name":"shared_wordpiece_16000",
|
| 340 |
+
"tokenizer_type":"shared",
|
| 341 |
+
"algorithm":"WordPiece",
|
| 342 |
+
"vocab_size":16000,
|
| 343 |
+
"fertility_overall":1.5914307397,
|
| 344 |
+
"cpt_overall":3.3585405825,
|
| 345 |
+
"fertility_disparity":0.1511682691,
|
| 346 |
+
"cpt_disparity":0.6209619713,
|
| 347 |
+
"oov_disparity":0.0,
|
| 348 |
+
"vocab_gini":0.7797479401,
|
| 349 |
+
"shannon_entropy":11.1061302427,
|
| 350 |
+
"exact_match_rate":0.99,
|
| 351 |
+
"morph_edit_distance_ar":4.1158134243,
|
| 352 |
+
"morph_consistency_precision":0.1653640001,
|
| 353 |
+
"morph_consistency_recall":0.1209851544,
|
| 354 |
+
"morph_consistency_f1":0.1385333865,
|
| 355 |
+
"ar_fertility":1.5073514587,
|
| 356 |
+
"ar_cpt":3.7184773832,
|
| 357 |
+
"ar_oov_rate":0.0,
|
| 358 |
+
"ar_mean_seq_len":15.8912426875,
|
| 359 |
+
"ar_median_seq_len":16.0,
|
| 360 |
+
"az_fertility":1.6585197278,
|
| 361 |
+
"az_cpt":3.0975154119,
|
| 362 |
+
"az_oov_rate":0.0,
|
| 363 |
+
"az_mean_seq_len":22.6717780535,
|
| 364 |
+
"az_median_seq_len":22.0
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"name":"concat_wordpiece_16000",
|
| 368 |
+
"tokenizer_type":"concatenated",
|
| 369 |
+
"algorithm":"WordPiece",
|
| 370 |
+
"vocab_size":16000,
|
| 371 |
+
"fertility_overall":1.5161705103,
|
| 372 |
+
"cpt_overall":3.5252530551,
|
| 373 |
+
"fertility_disparity":0.1360666065,
|
| 374 |
+
"cpt_disparity":0.0077904651,
|
| 375 |
+
"oov_disparity":0.0,
|
| 376 |
+
"vocab_gini":0.7024364505,
|
| 377 |
+
"shannon_entropy":11.4443519139,
|
| 378 |
+
"exact_match_rate":0.99,
|
| 379 |
+
"morph_edit_distance_ar":4.1506488459,
|
| 380 |
+
"morph_consistency_precision":0.1740477945,
|
| 381 |
+
"morph_consistency_recall":0.1384490501,
|
| 382 |
+
"morph_consistency_f1":0.1533202072,
|
| 383 |
+
"ar_fertility":1.5918502976,
|
| 384 |
+
"ar_cpt":3.5210926029,
|
| 385 |
+
"ar_oov_rate":0.0,
|
| 386 |
+
"ar_mean_seq_len":16.8945222478,
|
| 387 |
+
"ar_median_seq_len":17.0,
|
| 388 |
+
"az_fertility":1.455783691,
|
| 389 |
+
"az_cpt":3.528883068,
|
| 390 |
+
"az_oov_rate":0.0,
|
| 391 |
+
"az_mean_seq_len":19.6559120723,
|
| 392 |
+
"az_median_seq_len":19.0
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"name":"shared_bbpe_16000",
|
| 396 |
+
"tokenizer_type":"shared",
|
| 397 |
+
"algorithm":"BBPE",
|
| 398 |
+
"vocab_size":16000,
|
| 399 |
+
"fertility_overall":1.7936656802,
|
| 400 |
+
"cpt_overall":2.9798667514,
|
| 401 |
+
"fertility_disparity":0.4264991353,
|
| 402 |
+
"cpt_disparity":1.0104466245,
|
| 403 |
+
"oov_disparity":0.0,
|
| 404 |
+
"vocab_gini":0.8352512331,
|
| 405 |
+
"shannon_entropy":10.2895041219,
|
| 406 |
+
"exact_match_rate":0.99,
|
| 407 |
+
"morph_edit_distance_ar":4.1365421097,
|
| 408 |
+
"morph_consistency_precision":0.154622604,
|
| 409 |
+
"morph_consistency_recall":0.2260888365,
|
| 410 |
+
"morph_consistency_f1":0.1823875169,
|
| 411 |
+
"ar_fertility":1.5564483008,
|
| 412 |
+
"ar_cpt":3.6011811666,
|
| 413 |
+
"ar_oov_rate":0.0,
|
| 414 |
+
"ar_mean_seq_len":16.4752703421,
|
| 415 |
+
"ar_median_seq_len":16.0,
|
| 416 |
+
"az_fertility":1.9829474362,
|
| 417 |
+
"az_cpt":2.590734542,
|
| 418 |
+
"az_oov_rate":0.0,
|
| 419 |
+
"az_mean_seq_len":27.498847722,
|
| 420 |
+
"az_median_seq_len":27.0
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"name":"concat_bbpe_16000",
|
| 424 |
+
"tokenizer_type":"concatenated",
|
| 425 |
+
"algorithm":"BBPE",
|
| 426 |
+
"vocab_size":16000,
|
| 427 |
+
"fertility_overall":1.7340440692,
|
| 428 |
+
"cpt_overall":3.0823234649,
|
| 429 |
+
"fertility_disparity":0.1722144964,
|
| 430 |
+
"cpt_disparity":0.5838072031,
|
| 431 |
+
"oov_disparity":0.0,
|
| 432 |
+
"vocab_gini":0.7908187337,
|
| 433 |
+
"shannon_entropy":10.5217570863,
|
| 434 |
+
"exact_match_rate":0.99,
|
| 435 |
+
"morph_edit_distance_ar":4.1719709073,
|
| 436 |
+
"morph_consistency_precision":0.1620182352,
|
| 437 |
+
"morph_consistency_recall":0.2599866609,
|
| 438 |
+
"morph_consistency_f1":0.1986209129,
|
| 439 |
+
"ar_fertility":1.6382589476,
|
| 440 |
+
"ar_cpt":3.4213469831,
|
| 441 |
+
"ar_oov_rate":0.0,
|
| 442 |
+
"ar_mean_seq_len":17.4463747562,
|
| 443 |
+
"ar_median_seq_len":17.0,
|
| 444 |
+
"az_fertility":1.810473444,
|
| 445 |
+
"az_cpt":2.83753978,
|
| 446 |
+
"az_oov_rate":0.0,
|
| 447 |
+
"az_mean_seq_len":24.9330792413,
|
| 448 |
+
"az_median_seq_len":24.0
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"name":"shared_bpe_32000",
|
| 452 |
+
"tokenizer_type":"shared",
|
| 453 |
+
"algorithm":"BPE",
|
| 454 |
+
"vocab_size":32000,
|
| 455 |
+
"fertility_overall":1.4562440141,
|
| 456 |
+
"cpt_overall":3.670322193,
|
| 457 |
+
"fertility_disparity":0.0726954505,
|
| 458 |
+
"cpt_disparity":0.507593217,
|
| 459 |
+
"oov_disparity":0.0,
|
| 460 |
+
"vocab_gini":0.7969114377,
|
| 461 |
+
"shannon_entropy":11.521256996,
|
| 462 |
+
"exact_match_rate":0.99,
|
| 463 |
+
"morph_edit_distance_ar":4.0705763007,
|
| 464 |
+
"morph_consistency_precision":0.1610095066,
|
| 465 |
+
"morph_consistency_recall":0.0899012584,
|
| 466 |
+
"morph_consistency_f1":0.1149172148,
|
| 467 |
+
"ar_fertility":1.41581105,
|
| 468 |
+
"ar_cpt":3.9588985464,
|
| 469 |
+
"ar_oov_rate":0.0,
|
| 470 |
+
"ar_mean_seq_len":14.8034036518,
|
| 471 |
+
"ar_median_seq_len":14.0,
|
| 472 |
+
"az_fertility":1.4885065005,
|
| 473 |
+
"az_cpt":3.4513053294,
|
| 474 |
+
"az_oov_rate":0.0,
|
| 475 |
+
"az_mean_seq_len":20.1420847367,
|
| 476 |
+
"az_median_seq_len":20.0
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"name":"concat_bpe_32000",
|
| 480 |
+
"tokenizer_type":"concatenated",
|
| 481 |
+
"algorithm":"BPE",
|
| 482 |
+
"vocab_size":32000,
|
| 483 |
+
"fertility_overall":1.3911576687,
|
| 484 |
+
"cpt_overall":3.8420409447,
|
| 485 |
+
"fertility_disparity":0.134007069,
|
| 486 |
+
"cpt_disparity":0.0335692487,
|
| 487 |
+
"oov_disparity":0.0,
|
| 488 |
+
"vocab_gini":0.7567616479,
|
| 489 |
+
"shannon_entropy":11.8182442917,
|
| 490 |
+
"exact_match_rate":0.99,
|
| 491 |
+
"morph_edit_distance_ar":4.0970004442,
|
| 492 |
+
"morph_consistency_precision":0.148728366,
|
| 493 |
+
"morph_consistency_recall":0.0942436549,
|
| 494 |
+
"morph_consistency_f1":0.1146174635,
|
| 495 |
+
"ar_fertility":1.4656919481,
|
| 496 |
+
"ar_cpt":3.8241680422,
|
| 497 |
+
"ar_oov_rate":0.0,
|
| 498 |
+
"ar_mean_seq_len":15.3963836199,
|
| 499 |
+
"ar_median_seq_len":15.0,
|
| 500 |
+
"az_fertility":1.3316848791,
|
| 501 |
+
"az_cpt":3.8577372909,
|
| 502 |
+
"az_oov_rate":0.0,
|
| 503 |
+
"az_mean_seq_len":17.8096082255,
|
| 504 |
+
"az_median_seq_len":17.0
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"name":"shared_unigram_32000",
|
| 508 |
+
"tokenizer_type":"shared",
|
| 509 |
+
"algorithm":"Unigram",
|
| 510 |
+
"vocab_size":32000,
|
| 511 |
+
"fertility_overall":1.5033984749,
|
| 512 |
+
"cpt_overall":3.55520164,
|
| 513 |
+
"fertility_disparity":0.019300727,
|
| 514 |
+
"cpt_disparity":0.3573083439,
|
| 515 |
+
"oov_disparity":0.0,
|
| 516 |
+
"vocab_gini":0.8324888295,
|
| 517 |
+
"shannon_entropy":10.9257151273,
|
| 518 |
+
"exact_match_rate":0.99,
|
| 519 |
+
"morph_edit_distance_ar":4.0979264521,
|
| 520 |
+
"morph_consistency_precision":0.1631020109,
|
| 521 |
+
"morph_consistency_recall":0.1383463815,
|
| 522 |
+
"morph_consistency_f1":0.1482409685,
|
| 523 |
+
"ar_fertility":1.4926634757,
|
| 524 |
+
"ar_cpt":3.7550676352,
|
| 525 |
+
"ar_oov_rate":0.0,
|
| 526 |
+
"ar_mean_seq_len":15.7181350824,
|
| 527 |
+
"ar_median_seq_len":15.0,
|
| 528 |
+
"az_fertility":1.5119642027,
|
| 529 |
+
"az_cpt":3.3977592913,
|
| 530 |
+
"az_oov_rate":0.0,
|
| 531 |
+
"az_mean_seq_len":20.4923772381,
|
| 532 |
+
"az_median_seq_len":20.0
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"name":"concat_unigram_32000",
|
| 536 |
+
"tokenizer_type":"concatenated",
|
| 537 |
+
"algorithm":"Unigram",
|
| 538 |
+
"vocab_size":32000,
|
| 539 |
+
"fertility_overall":1.4304050001,
|
| 540 |
+
"cpt_overall":3.7366233501,
|
| 541 |
+
"fertility_disparity":0.1449358921,
|
| 542 |
+
"cpt_disparity":0.0511471793,
|
| 543 |
+
"oov_disparity":0.0,
|
| 544 |
+
"vocab_gini":0.8069023024,
|
| 545 |
+
"shannon_entropy":11.1617375452,
|
| 546 |
+
"exact_match_rate":0.99,
|
| 547 |
+
"morph_edit_distance_ar":4.1111640248,
|
| 548 |
+
"morph_consistency_precision":0.1486025565,
|
| 549 |
+
"morph_consistency_recall":0.1393090166,
|
| 550 |
+
"morph_consistency_f1":0.1420302247,
|
| 551 |
+
"ar_fertility":1.5110178541,
|
| 552 |
+
"ar_cpt":3.709454718,
|
| 553 |
+
"ar_oov_rate":0.0,
|
| 554 |
+
"ar_mean_seq_len":15.9360042546,
|
| 555 |
+
"ar_median_seq_len":16.0,
|
| 556 |
+
"az_fertility":1.3660819619,
|
| 557 |
+
"az_cpt":3.7606018973,
|
| 558 |
+
"az_oov_rate":0.0,
|
| 559 |
+
"az_mean_seq_len":18.3221946463,
|
| 560 |
+
"az_median_seq_len":18.0
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"name":"shared_wordpiece_32000",
|
| 564 |
+
"tokenizer_type":"shared",
|
| 565 |
+
"algorithm":"WordPiece",
|
| 566 |
+
"vocab_size":32000,
|
| 567 |
+
"fertility_overall":1.4501065441,
|
| 568 |
+
"cpt_overall":3.6858565637,
|
| 569 |
+
"fertility_disparity":0.0723742616,
|
| 570 |
+
"cpt_disparity":0.5097029774,
|
| 571 |
+
"oov_disparity":0.0,
|
| 572 |
+
"vocab_gini":0.7885550388,
|
| 573 |
+
"shannon_entropy":11.5290013722,
|
| 574 |
+
"exact_match_rate":0.99,
|
| 575 |
+
"morph_edit_distance_ar":4.0695593122,
|
| 576 |
+
"morph_consistency_precision":0.1813894046,
|
| 577 |
+
"morph_consistency_recall":0.0999073414,
|
| 578 |
+
"morph_consistency_f1":0.1273030756,
|
| 579 |
+
"ar_fertility":1.4098522241,
|
| 580 |
+
"ar_cpt":3.975631071,
|
| 581 |
+
"ar_oov_rate":0.0,
|
| 582 |
+
"ar_mean_seq_len":14.7339124269,
|
| 583 |
+
"ar_median_seq_len":14.0,
|
| 584 |
+
"az_fertility":1.4822264857,
|
| 585 |
+
"az_cpt":3.4659280936,
|
| 586 |
+
"az_oov_rate":0.0,
|
| 587 |
+
"az_mean_seq_len":20.0491934054,
|
| 588 |
+
"az_median_seq_len":20.0
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"name":"concat_wordpiece_32000",
|
| 592 |
+
"tokenizer_type":"concatenated",
|
| 593 |
+
"algorithm":"WordPiece",
|
| 594 |
+
"vocab_size":32000,
|
| 595 |
+
"fertility_overall":1.3885462613,
|
| 596 |
+
"cpt_overall":3.8492665836,
|
| 597 |
+
"fertility_disparity":0.1308885617,
|
| 598 |
+
"cpt_disparity":0.0257554455,
|
| 599 |
+
"oov_disparity":0.0,
|
| 600 |
+
"vocab_gini":0.7418783914,
|
| 601 |
+
"shannon_entropy":11.7951971085,
|
| 602 |
+
"exact_match_rate":0.99,
|
| 603 |
+
"morph_edit_distance_ar":4.097541522,
|
| 604 |
+
"morph_consistency_precision":0.1635636627,
|
| 605 |
+
"morph_consistency_recall":0.112578089,
|
| 606 |
+
"morph_consistency_f1":0.1328802305,
|
| 607 |
+
"ar_fertility":1.4613460375,
|
| 608 |
+
"ar_cpt":3.8355407712,
|
| 609 |
+
"ar_oov_rate":0.0,
|
| 610 |
+
"ar_mean_seq_len":15.3454174792,
|
| 611 |
+
"ar_median_seq_len":15.0,
|
| 612 |
+
"az_fertility":1.3304574758,
|
| 613 |
+
"az_cpt":3.8612962167,
|
| 614 |
+
"az_oov_rate":0.0,
|
| 615 |
+
"az_mean_seq_len":17.7915263251,
|
| 616 |
+
"az_median_seq_len":17.0
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"name":"shared_bbpe_32000",
|
| 620 |
+
"tokenizer_type":"shared",
|
| 621 |
+
"algorithm":"BBPE",
|
| 622 |
+
"vocab_size":32000,
|
| 623 |
+
"fertility_overall":1.673696699,
|
| 624 |
+
"cpt_overall":3.1934607548,
|
| 625 |
+
"fertility_disparity":0.3736950757,
|
| 626 |
+
"cpt_disparity":1.0310609307,
|
| 627 |
+
"oov_disparity":0.0,
|
| 628 |
+
"vocab_gini":0.843090999,
|
| 629 |
+
"shannon_entropy":10.5235434613,
|
| 630 |
+
"exact_match_rate":0.99,
|
| 631 |
+
"morph_edit_distance_ar":4.0973786272,
|
| 632 |
+
"morph_consistency_precision":0.157092523,
|
| 633 |
+
"morph_consistency_recall":0.1976111484,
|
| 634 |
+
"morph_consistency_f1":0.1737146088,
|
| 635 |
+
"ar_fertility":1.4658487593,
|
| 636 |
+
"ar_cpt":3.8237589465,
|
| 637 |
+
"ar_oov_rate":0.0,
|
| 638 |
+
"ar_mean_seq_len":15.3998404538,
|
| 639 |
+
"ar_median_seq_len":15.0,
|
| 640 |
+
"az_fertility":1.839543835,
|
| 641 |
+
"az_cpt":2.7926980158,
|
| 642 |
+
"az_oov_rate":0.0,
|
| 643 |
+
"az_mean_seq_len":25.3655380252,
|
| 644 |
+
"az_median_seq_len":25.0
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"name":"concat_bbpe_32000",
|
| 648 |
+
"tokenizer_type":"concatenated",
|
| 649 |
+
"algorithm":"BBPE",
|
| 650 |
+
"vocab_size":32000,
|
| 651 |
+
"fertility_overall":1.6299390561,
|
| 652 |
+
"cpt_overall":3.2791929879,
|
| 653 |
+
"fertility_disparity":0.2066556668,
|
| 654 |
+
"cpt_disparity":0.7157815641,
|
| 655 |
+
"oov_disparity":0.0,
|
| 656 |
+
"vocab_gini":0.8217315637,
|
| 657 |
+
"shannon_entropy":10.6841474757,
|
| 658 |
+
"exact_match_rate":0.99,
|
| 659 |
+
"morph_edit_distance_ar":4.1215903942,
|
| 660 |
+
"morph_consistency_precision":0.1574322292,
|
| 661 |
+
"morph_consistency_recall":0.2143887572,
|
| 662 |
+
"morph_consistency_f1":0.1797621337,
|
| 663 |
+
"ar_fertility":1.5149978718,
|
| 664 |
+
"ar_cpt":3.6997096906,
|
| 665 |
+
"ar_oov_rate":0.0,
|
| 666 |
+
"ar_mean_seq_len":15.9832476511,
|
| 667 |
+
"ar_median_seq_len":16.0,
|
| 668 |
+
"az_fertility":1.7216535386,
|
| 669 |
+
"az_cpt":2.9839281265,
|
| 670 |
+
"az_oov_rate":0.0,
|
| 671 |
+
"az_mean_seq_len":23.6117709626,
|
| 672 |
+
"az_median_seq_len":23.0
|
| 673 |
+
}
|
| 674 |
+
]
|