Skip to content

Commit 9416ad5

Browse files
committed
Update Tatoeba Dataset and generate new profiles
1 parent 5db2aed commit 9416ad5

17 files changed

+71490
-70108
lines changed

‎data/bench/cld.json

+16-16
Original file line numberDiff line numberDiff line change
@@ -2,72 +2,72 @@
22
"size": {
33
"10": {
44
"success_rate": 26.5,
5-
"error_rate": 2.4063,
6-
"unindentified_rate": 71.0938,
7-
"execution_time": 0.0937
5+
"error_rate": 2.4375,
6+
"unindentified_rate": 71.0625,
7+
"execution_time": 0.1076
88
},
99
"16": {
1010
"success_rate": 57.5625,
1111
"error_rate": 4.0625,
1212
"unindentified_rate": 38.375,
13-
"execution_time": 0.0677
13+
"execution_time": 0.0891
1414
},
1515
"24": {
1616
"success_rate": 81.6563,
1717
"error_rate": 3.1563,
1818
"unindentified_rate": 15.1875,
19-
"execution_time": 0.0607
19+
"execution_time": 0.0754
2020
},
2121
"36": {
2222
"success_rate": 92.8125,
2323
"error_rate": 1.75,
2424
"unindentified_rate": 5.4375,
25-
"execution_time": 0.0604
25+
"execution_time": 0.0758
2626
},
2727
"48": {
2828
"success_rate": 96.75,
2929
"error_rate": 1.0938,
3030
"unindentified_rate": 2.1563,
31-
"execution_time": 0.0614
31+
"execution_time": 0.0778
3232
},
3333
"64": {
3434
"success_rate": 98.3125,
3535
"error_rate": 0.5,
3636
"unindentified_rate": 1.1875,
37-
"execution_time": 0.0623
37+
"execution_time": 0.0747
3838
},
3939
"128": {
4040
"success_rate": 99.5625,
4141
"error_rate": 0.0938,
4242
"unindentified_rate": 0.3438,
43-
"execution_time": 0.0662
43+
"execution_time": 0.08
4444
},
4545
"256": {
4646
"success_rate": 99.9375,
4747
"error_rate": 0.0313,
4848
"unindentified_rate": 0.0313,
49-
"execution_time": 0.0721
49+
"execution_time": 0.086
5050
},
5151
"512": {
5252
"success_rate": 99.9688,
5353
"error_rate": 0,
5454
"unindentified_rate": 0.0313,
55-
"execution_time": 0.0855
55+
"execution_time": 0.1195
5656
},
5757
"1024": {
5858
"success_rate": 100,
5959
"error_rate": 0,
6060
"unindentified_rate": 0,
61-
"execution_time": 0.1123
61+
"execution_time": 0.1449
6262
}
6363
},
6464
"stats": {
6565
"min": 78.4,
6666
"max": 100,
67-
"success_rate": 92.3628,
68-
"error_rate": 1.6212,
69-
"unindentified_rate": 6.016,
70-
"execution_time": 0.0608
67+
"success_rate": 92.3654,
68+
"error_rate": 1.6213,
69+
"unindentified_rate": 6.0133,
70+
"execution_time": 0.0711
7171
},
7272
"languages": {
7373
"jpn": 100,

‎data/bench/franc-all.json

+20-20
Original file line numberDiff line numberDiff line change
@@ -10,78 +10,78 @@
1010
"success_rate": 41.0938,
1111
"error_rate": 58.9063,
1212
"unindentified_rate": 0,
13-
"execution_time": 0.2296
13+
"execution_time": 0.264
1414
},
1515
"24": {
1616
"success_rate": 50,
1717
"error_rate": 50,
1818
"unindentified_rate": 0,
19-
"execution_time": 0.3066
19+
"execution_time": 0.3342
2020
},
2121
"36": {
2222
"success_rate": 60.5938,
2323
"error_rate": 39.4063,
2424
"unindentified_rate": 0,
25-
"execution_time": 0.3881
25+
"execution_time": 0.3994
2626
},
2727
"48": {
2828
"success_rate": 69.5625,
2929
"error_rate": 30.4375,
3030
"unindentified_rate": 0,
31-
"execution_time": 0.476
31+
"execution_time": 0.509
3232
},
3333
"64": {
3434
"success_rate": 73.5938,
3535
"error_rate": 26.4062,
3636
"unindentified_rate": 0,
37-
"execution_time": 0.5802
37+
"execution_time": 0.6104
3838
},
3939
"128": {
4040
"success_rate": 86.1563,
4141
"error_rate": 13.8438,
4242
"unindentified_rate": 0,
43-
"execution_time": 0.8952
43+
"execution_time": 0.925
4444
},
4545
"256": {
4646
"success_rate": 93.6875,
4747
"error_rate": 6.3125,
4848
"unindentified_rate": 0,
49-
"execution_time": 1.5613
49+
"execution_time": 1.6346
5050
},
5151
"512": {
5252
"success_rate": 96.25,
5353
"error_rate": 3.75,
5454
"unindentified_rate": 0,
55-
"execution_time": 2.7102
55+
"execution_time": 2.8385
5656
},
5757
"1024": {
58-
"success_rate": 98.4306,
59-
"error_rate": 1.5694,
58+
"success_rate": 98.4331,
59+
"error_rate": 1.5669,
6060
"unindentified_rate": 0,
61-
"execution_time": 4.5519
61+
"execution_time": 4.78
6262
}
6363
},
6464
"stats": {
6565
"min": 29.47,
6666
"max": 99.93,
67-
"success_rate": 66.6957,
68-
"error_rate": 33.3043,
67+
"success_rate": 66.7081,
68+
"error_rate": 33.2919,
6969
"unindentified_rate": 0,
70-
"execution_time": 0.4345
70+
"execution_time": 0.4763
7171
},
7272
"languages": {
7373
"jpn": 99.93,
74-
"kor": 99.8619,
74+
"kor": 99.8633,
7575
"cmn": 99.35,
7676
"heb": 98.18,
77-
"ara": 91.73,
77+
"ara": 91.72,
7878
"deu": 80.77,
79-
"fin": 70.8,
79+
"fin": 70.79,
8080
"fra": 67.27,
8181
"hin": 60.42,
82-
"nld": 59.64,
83-
"rus": 51.94,
84-
"eng": 49.91,
82+
"nld": 59.65,
83+
"rus": 51.96,
84+
"eng": 49.92,
8585
"por": 49.39,
8686
"ita": 42.55,
8787
"tur": 32.27,

‎data/bench/franc-min.json

+22-22
Original file line numberDiff line numberDiff line change
@@ -4,86 +4,86 @@
44
"success_rate": 0.125,
55
"error_rate": 0.0625,
66
"unindentified_rate": 99.8125,
7-
"execution_time": 0.0018
7+
"execution_time": 0.0019
88
},
99
"16": {
1010
"success_rate": 45.3438,
1111
"error_rate": 48.4063,
1212
"unindentified_rate": 6.25,
13-
"execution_time": 0.0443
13+
"execution_time": 0.0428
1414
},
1515
"24": {
1616
"success_rate": 55.375,
1717
"error_rate": 38.375,
1818
"unindentified_rate": 6.25,
19-
"execution_time": 0.0549
19+
"execution_time": 0.052
2020
},
2121
"36": {
2222
"success_rate": 66.9375,
2323
"error_rate": 26.8125,
2424
"unindentified_rate": 6.25,
25-
"execution_time": 0.0726
25+
"execution_time": 0.0688
2626
},
2727
"48": {
2828
"success_rate": 73.375,
2929
"error_rate": 20.375,
3030
"unindentified_rate": 6.25,
31-
"execution_time": 0.0911
31+
"execution_time": 0.0835
3232
},
3333
"64": {
3434
"success_rate": 75.9063,
3535
"error_rate": 17.875,
3636
"unindentified_rate": 6.2188,
37-
"execution_time": 0.1087
37+
"execution_time": 0.1015
3838
},
3939
"128": {
4040
"success_rate": 82.5625,
4141
"error_rate": 11.25,
4242
"unindentified_rate": 6.1875,
43-
"execution_time": 0.1725
43+
"execution_time": 0.1628
4444
},
4545
"256": {
4646
"success_rate": 85.1563,
4747
"error_rate": 8.6875,
4848
"unindentified_rate": 6.1563,
49-
"execution_time": 0.3244
49+
"execution_time": 0.3008
5050
},
5151
"512": {
5252
"success_rate": 86.5313,
5353
"error_rate": 7.4375,
5454
"unindentified_rate": 6.0313,
55-
"execution_time": 0.5754
55+
"execution_time": 0.5538
5656
},
5757
"1024": {
58-
"success_rate": 87.1312,
59-
"error_rate": 6.9366,
60-
"unindentified_rate": 5.9322,
61-
"execution_time": 0.9954
58+
"success_rate": 87.1514,
59+
"error_rate": 6.9257,
60+
"unindentified_rate": 5.9229,
61+
"execution_time": 0.9752
6262
}
6363
},
6464
"stats": {
6565
"min": 0.01,
6666
"max": 99.93,
67-
"success_rate": 70.3772,
68-
"error_rate": 23.1986,
69-
"unindentified_rate": 6.4242,
70-
"execution_time": 0.0865
67+
"success_rate": 70.3891,
68+
"error_rate": 23.1888,
69+
"unindentified_rate": 6.422,
70+
"execution_time": 0.084
7171
},
7272
"languages": {
7373
"jpn": 99.93,
74-
"kor": 99.8619,
74+
"kor": 99.8633,
7575
"cmn": 99.35,
7676
"deu": 94.18,
77-
"ara": 91.89,
77+
"ara": 91.88,
7878
"fra": 87.32,
7979
"nld": 87.21,
80-
"eng": 81.41,
80+
"eng": 81.42,
8181
"por": 76.8,
8282
"ita": 74.31,
8383
"hin": 68.25,
84-
"spa": 67.37,
84+
"spa": 67.38,
8585
"tur": 58.11,
86-
"rus": 54.58,
86+
"rus": 54.6,
8787
"fin": 0.01,
8888
"heb": 0.01
8989
}

0 commit comments

Comments
 (0)