Skip to content

Commit c378f9b

Browse files
committed
Update Tatoeba Dataset and generate new profiles
1 parent 268be43 commit c378f9b

16 files changed

+13657
-13780
lines changed

‎data/bench/cld.json

+15-15
Original file line numberDiff line numberDiff line change
@@ -4,64 +4,64 @@
44
"success_rate": 36.375,
55
"error_rate": 3.25,
66
"unindentified_rate": 60.375,
7-
"execution_time": 0.0794
7+
"execution_time": 0.0773
88
},
99
"24": {
1010
"success_rate": 77.7188,
1111
"error_rate": 3.0313,
1212
"unindentified_rate": 19.25,
13-
"execution_time": 0.0572
13+
"execution_time": 0.0587
1414
},
1515
"36": {
1616
"success_rate": 92.8125,
1717
"error_rate": 1.75,
1818
"unindentified_rate": 5.4375,
19-
"execution_time": 0.0577
19+
"execution_time": 0.0581
2020
},
2121
"48": {
2222
"success_rate": 96.75,
2323
"error_rate": 1.0938,
2424
"unindentified_rate": 2.1563,
25-
"execution_time": 0.0579
25+
"execution_time": 0.0585
2626
},
2727
"64": {
2828
"success_rate": 98.3125,
2929
"error_rate": 0.5,
3030
"unindentified_rate": 1.1875,
31-
"execution_time": 0.0586
31+
"execution_time": 0.0595
3232
},
3333
"128": {
3434
"success_rate": 99.5625,
3535
"error_rate": 0.0938,
3636
"unindentified_rate": 0.3438,
37-
"execution_time": 0.0629
37+
"execution_time": 0.063
3838
},
3939
"256": {
4040
"success_rate": 99.9375,
4141
"error_rate": 0.0313,
4242
"unindentified_rate": 0.0313,
43-
"execution_time": 0.0688
43+
"execution_time": 0.07
4444
},
4545
"512": {
4646
"success_rate": 99.9688,
4747
"error_rate": 0,
4848
"unindentified_rate": 0.0313,
49-
"execution_time": 0.0827
49+
"execution_time": 0.084
5050
},
5151
"1024": {
5252
"success_rate": 100,
5353
"error_rate": 0,
5454
"unindentified_rate": 0,
55-
"execution_time": 0.1096
55+
"execution_time": 0.1119
5656
}
5757
},
5858
"stats": {
59-
"min": 78.39,
59+
"min": 78.4,
6060
"max": 100,
61-
"success_rate": 92.315,
62-
"error_rate": 1.6319,
63-
"unindentified_rate": 6.0532,
64-
"execution_time": 0.0565
61+
"success_rate": 92.3628,
62+
"error_rate": 1.6212,
63+
"unindentified_rate": 6.016,
64+
"execution_time": 0.0588
6565
},
6666
"languages": {
6767
"jpn": 100,
@@ -79,6 +79,6 @@
7979
"spa": 87.79,
8080
"ita": 85.9,
8181
"heb": 84.06,
82-
"ara": 78.39
82+
"ara": 78.4
8383
}
8484
}

‎data/bench/franc-all.json

+16-16
Original file line numberDiff line numberDiff line change
@@ -4,68 +4,68 @@
44
"success_rate": 18.5313,
55
"error_rate": 35,
66
"unindentified_rate": 46.4688,
7-
"execution_time": 0.088
7+
"execution_time": 0.1188
88
},
99
"24": {
1010
"success_rate": 48.4375,
1111
"error_rate": 51.5625,
1212
"unindentified_rate": 0,
13-
"execution_time": 0.215
13+
"execution_time": 0.2901
1414
},
1515
"36": {
1616
"success_rate": 60.5938,
1717
"error_rate": 39.4063,
1818
"unindentified_rate": 0,
19-
"execution_time": 0.2977
19+
"execution_time": 0.3766
2020
},
2121
"48": {
2222
"success_rate": 69.5625,
2323
"error_rate": 30.4375,
2424
"unindentified_rate": 0,
25-
"execution_time": 0.3563
25+
"execution_time": 0.4567
2626
},
2727
"64": {
2828
"success_rate": 73.5938,
2929
"error_rate": 26.4062,
3030
"unindentified_rate": 0,
31-
"execution_time": 0.4264
31+
"execution_time": 0.5443
3232
},
3333
"128": {
3434
"success_rate": 86.1563,
3535
"error_rate": 13.8438,
3636
"unindentified_rate": 0,
37-
"execution_time": 0.6821
37+
"execution_time": 0.8152
3838
},
3939
"256": {
4040
"success_rate": 93.6875,
4141
"error_rate": 6.3125,
4242
"unindentified_rate": 0,
43-
"execution_time": 1.1989
43+
"execution_time": 1.4124
4444
},
4545
"512": {
4646
"success_rate": 96.25,
4747
"error_rate": 3.75,
4848
"unindentified_rate": 0,
49-
"execution_time": 2.0734
49+
"execution_time": 2.3568
5050
},
5151
"1024": {
52-
"success_rate": 98.4147,
53-
"error_rate": 1.5853,
52+
"success_rate": 98.4306,
53+
"error_rate": 1.5694,
5454
"unindentified_rate": 0,
55-
"execution_time": 3.5626
55+
"execution_time": 3.9251
5656
}
5757
},
5858
"stats": {
5959
"min": 29.47,
6060
"max": 99.93,
61-
"success_rate": 66.4893,
62-
"error_rate": 33.5107,
61+
"success_rate": 66.6957,
62+
"error_rate": 33.3043,
6363
"unindentified_rate": 0,
64-
"execution_time": 0.3376
64+
"execution_time": 0.4123
6565
},
6666
"languages": {
6767
"jpn": 99.93,
68-
"kor": 99.83,
68+
"kor": 99.8619,
6969
"cmn": 99.35,
7070
"heb": 98.18,
7171
"ara": 91.73,
@@ -75,7 +75,7 @@
7575
"hin": 60.42,
7676
"nld": 59.64,
7777
"rus": 51.94,
78-
"eng": 49.9,
78+
"eng": 49.91,
7979
"por": 49.39,
8080
"ita": 42.55,
8181
"tur": 32.27,

‎data/bench/franc-min.json

+18-18
Original file line numberDiff line numberDiff line change
@@ -4,74 +4,74 @@
44
"success_rate": 21.4375,
55
"error_rate": 29.375,
66
"unindentified_rate": 49.1875,
7-
"execution_time": 0.0171
7+
"execution_time": 0.0188
88
},
99
"24": {
1010
"success_rate": 53.2188,
1111
"error_rate": 40.5313,
1212
"unindentified_rate": 6.25,
13-
"execution_time": 0.0387
13+
"execution_time": 0.0397
1414
},
1515
"36": {
1616
"success_rate": 66.9375,
1717
"error_rate": 26.8125,
1818
"unindentified_rate": 6.25,
19-
"execution_time": 0.0525
19+
"execution_time": 0.0542
2020
},
2121
"48": {
2222
"success_rate": 73.375,
2323
"error_rate": 20.375,
2424
"unindentified_rate": 6.25,
25-
"execution_time": 0.0644
25+
"execution_time": 0.0671
2626
},
2727
"64": {
2828
"success_rate": 75.9063,
2929
"error_rate": 17.875,
3030
"unindentified_rate": 6.2188,
31-
"execution_time": 0.078
31+
"execution_time": 0.08
3232
},
3333
"128": {
3434
"success_rate": 82.5625,
3535
"error_rate": 11.25,
3636
"unindentified_rate": 6.1875,
37-
"execution_time": 0.1275
37+
"execution_time": 0.1292
3838
},
3939
"256": {
4040
"success_rate": 85.1563,
4141
"error_rate": 8.6875,
4242
"unindentified_rate": 6.1563,
43-
"execution_time": 0.2363
43+
"execution_time": 0.2396
4444
},
4545
"512": {
4646
"success_rate": 86.5313,
4747
"error_rate": 7.4375,
4848
"unindentified_rate": 6.0313,
49-
"execution_time": 0.4234
49+
"execution_time": 0.4312
5050
},
5151
"1024": {
52-
"success_rate": 87.0006,
53-
"error_rate": 7.007,
54-
"unindentified_rate": 5.9924,
55-
"execution_time": 0.7489
52+
"success_rate": 87.1312,
53+
"error_rate": 6.9366,
54+
"unindentified_rate": 5.9322,
55+
"execution_time": 0.7717
5656
}
5757
},
5858
"stats": {
5959
"min": 0.01,
6060
"max": 99.93,
61-
"success_rate": 70.193,
62-
"error_rate": 23.3432,
63-
"unindentified_rate": 6.4639,
64-
"execution_time": 0.0668
61+
"success_rate": 70.3772,
62+
"error_rate": 23.1986,
63+
"unindentified_rate": 6.4242,
64+
"execution_time": 0.0711
6565
},
6666
"languages": {
6767
"jpn": 99.93,
68-
"kor": 99.83,
68+
"kor": 99.8619,
6969
"cmn": 99.35,
7070
"deu": 94.18,
7171
"ara": 91.89,
7272
"fra": 87.32,
7373
"nld": 87.21,
74-
"eng": 81.39,
74+
"eng": 81.41,
7575
"por": 76.8,
7676
"ita": 74.31,
7777
"hin": 68.25,

‎data/bench/franc.json

+16-16
Original file line numberDiff line numberDiff line change
@@ -4,68 +4,68 @@
44
"success_rate": 20.6875,
55
"error_rate": 32.8438,
66
"unindentified_rate": 46.4688,
7-
"execution_time": 0.0406
7+
"execution_time": 0.0465
88
},
99
"24": {
1010
"success_rate": 54.6562,
1111
"error_rate": 45.3438,
1212
"unindentified_rate": 0,
13-
"execution_time": 0.0895
13+
"execution_time": 0.0975
1414
},
1515
"36": {
1616
"success_rate": 69.0938,
1717
"error_rate": 30.9063,
1818
"unindentified_rate": 0,
19-
"execution_time": 0.1221
19+
"execution_time": 0.13
2020
},
2121
"48": {
2222
"success_rate": 77.0625,
2323
"error_rate": 22.9375,
2424
"unindentified_rate": 0,
25-
"execution_time": 0.1512
25+
"execution_time": 0.1599
2626
},
2727
"64": {
2828
"success_rate": 80.9688,
2929
"error_rate": 19.0313,
3030
"unindentified_rate": 0,
31-
"execution_time": 0.1813
31+
"execution_time": 0.1949
3232
},
3333
"128": {
3434
"success_rate": 91.2813,
3535
"error_rate": 8.7188,
3636
"unindentified_rate": 0,
37-
"execution_time": 0.2923
37+
"execution_time": 0.3045
3838
},
3939
"256": {
4040
"success_rate": 96.7188,
4141
"error_rate": 3.2813,
4242
"unindentified_rate": 0,
43-
"execution_time": 0.533
43+
"execution_time": 0.5557
4444
},
4545
"512": {
4646
"success_rate": 98.9063,
4747
"error_rate": 1.0938,
4848
"unindentified_rate": 0,
49-
"execution_time": 0.9421
49+
"execution_time": 0.9774
5050
},
5151
"1024": {
52-
"success_rate": 99.6829,
53-
"error_rate": 0.3171,
52+
"success_rate": 99.6861,
53+
"error_rate": 0.3139,
5454
"unindentified_rate": 0,
55-
"execution_time": 1.6453
55+
"execution_time": 1.7506
5656
}
5757
},
5858
"stats": {
5959
"min": 48.96,
6060
"max": 99.93,
61-
"success_rate": 74.088,
62-
"error_rate": 25.912,
61+
"success_rate": 74.2478,
62+
"error_rate": 25.7522,
6363
"unindentified_rate": 0,
64-
"execution_time": 0.1488
64+
"execution_time": 0.1567
6565
},
6666
"languages": {
6767
"jpn": 99.93,
68-
"kor": 99.83,
68+
"kor": 99.8619,
6969
"cmn": 99.35,
7070
"heb": 98.23,
7171
"ara": 91.85,
@@ -76,7 +76,7 @@
7676
"ita": 64.19,
7777
"por": 62.29,
7878
"nld": 62,
79-
"eng": 60.37,
79+
"eng": 60.38,
8080
"rus": 52.3,
8181
"spa": 51.24,
8282
"tur": 48.96

0 commit comments

Comments
 (0)