mirror of https://github.com/davisking/dlib.git
78 lines
2.5 KiB
Plaintext
78 lines
2.5 KiB
Plaintext
<text>
|
|
|
|
|
|
The Canterbury Corpus
|
|
|
|
file size packed size bpb corruption
|
|
|
|
text: 152089 86995 4.576 no
|
|
play: 125179 75430 4.82062 no
|
|
html: 24603 16209 5.27058 no
|
|
Csrc: 11150 7084 5.08269 no
|
|
list: 3721 2224 4.78151 no
|
|
Excl: 1029744 440758 3.42421 no
|
|
tech: 426754 248345 4.65552 no
|
|
poem: 481861 273394 4.53897 no
|
|
fax: 513216 75036 1.16966 no
|
|
SPRC: 38240 25660 5.3682 no
|
|
man: 4227 2663 5.03998 no
|
|
|
|
average: 4.42981
|
|
|
|
time: 875ms
|
|
|
|
|
|
|
|
The Calgary Corpus
|
|
|
|
file size packed size bpb corruption
|
|
|
|
bib: 111261 72533 5.21534 no
|
|
book1: 768771 435527 4.53219 no
|
|
book2: 610856 364597 4.7749 no
|
|
geo: 102400 72600 5.67188 no
|
|
news: 377109 244377 5.18422 no
|
|
obj1: 21504 16183 6.02046 no
|
|
obj2: 246814 189902 6.15531 no
|
|
paper1: 53161 33144 4.98772 no
|
|
paper2: 82199 47398 4.613 no
|
|
pic: 513216 75036 1.16966 no
|
|
progc: 39611 25885 5.22784 no
|
|
progl: 71646 42688 4.76655 no
|
|
progp: 49379 30180 4.88953 no
|
|
trans: 93695 64603 5.51603 no
|
|
|
|
average: 4.9089
|
|
|
|
time: 1.11sec
|
|
|
|
|
|
|
|
The Artificial Corpus
|
|
|
|
file size packed size bpb corruption
|
|
|
|
a: 1 7 56 no
|
|
aaa: 100000 20 0.0016 no
|
|
alphabet: 100000 58912 4.71296 no
|
|
random: 100000 75202 6.01616 no
|
|
|
|
average: 16.6827
|
|
|
|
time: 93ms
|
|
|
|
|
|
|
|
The Large Corpus
|
|
|
|
file size packed size bpb corruption
|
|
|
|
E.coli: 4638690 1162352 2.00462 no
|
|
bible: 4047392 2194059 4.33674 no
|
|
word: 2473400 1542086 4.98774 no
|
|
|
|
average: 3.77637
|
|
|
|
time: 3.766sec
|
|
|
|
</text> |