This commit is contained in:
s432211 2020-05-05 05:43:52 +02:00
parent 69c6410af8
commit 6d9403bbbb
3 changed files with 35 additions and 225 deletions

4
.gitignore vendored Normal file
View File

@ -0,0 +1,4 @@
*.tsv
*.txt
*.trn
results

56
count_lines.sh Normal file → Executable file
View File

@ -3,28 +3,34 @@
#zad 1
wc -l wikiniews_results.tsv > counted_lines_result.txt
#zad 3
cut --fields=2 wikiniews_results.tsv > hypothesis.txt
cut --fields=3 wikiniews_results.tsv > reference.txt
awk 'BEGIN{FS=OFS="\t"}{print $0,"(sp1_"NR")"}' < hypothesis.txt > hypothesis.trn
awk 'BEGIN{FS=OFS="\t"}{print $0,"(sp1_"NR")"}' < reference.txt > reference.trn
sclite -f 0 -r reference.trn trn -h hypothesis.trn trn -e utf-8 -i rm -o all stdout | grep Score > results
# #C #S #D #I do obliczen WER
awk 'BEGIN{OFS="\t"}{print $6, $7, $8, $9}' < results | awk '{ print ($2 + $3 + $4)/($2 + $3 + $1) }' > wer.tsv
paste wikiniews_results.tsv wer.tsv > wikiniews_results.tsv
awk 'BEGIN{FS=OFS="\t"}{ bad = bad + $1; all++ }END{ print bad/all }' < wer.tsv >> wer.txt
awk 'BEGIN{FS=OFS="\t"}{ if ( $1 == 0 ) good++; all++ }END{ print good/all }' < wer.tsv >> srr.txt
tail -n 50 wer.txt > wer1.txt
tail -n 50 srr.txt > srr1.txt
rm wer.txt
rm srr.txt
mv wer1.txt wer.txt
mv srr1.txt srr.txt
##zad 3
## dzielenie linii
#cut --fields=2 wikiniews_results.tsv > hypothesis.txt
#cut --fields=3 wikiniews_results.tsv > reference.txt
#
## tworzenie plikow trn
#awk 'BEGIN{FS=OFS="\t"}{print $0,"(sp1_"NR")"}' < hypothesis.txt > hypothesis.trn
#awk 'BEGIN{FS=OFS="\t"}{print $0,"(sp1_"NR")"}' < reference.txt > reference.trn
#
#sclite -f 0 -r reference.trn trn -h hypothesis.trn trn -e utf-8 -i rm -o all stdout | grep Score > results
#
## #correct words #substitutions #deletions #insertions do obliczen WER
#awk 'BEGIN{OFS="\t"}{print $6, $7, $8, $9}' < results | awk '{ print ($2 + $3 + $4)/($2 + $3 + $1) }' > wer.tsv
#
#paste wikiniews_results.tsv wer.tsv > wikiniews_results.tsv
#
## procent niepoprawnie rozpoznanych wyrazów
#awk 'BEGIN{FS=OFS="\t"}{ bad = bad + $1; all++ }END{ print bad/all }' < wer.tsv >> wer.txt
#
## procent całkowicie poprawnie rozpoznanych zdań
#awk 'BEGIN{FS=OFS="\t"}{ if ( $1 == 0 ) good++; all++ }END{ print good/all }' < wer.tsv >> srr.txt
#
## zamiana treści
#tail -n 50 wer.txt > wer1.txt
#tail -n 50 srr.txt > srr1.txt
#
#rm wer.txt
#rm srr.txt
#
#mv wer1.txt wer.txt
#mv srr1.txt srr.txt

View File

@ -1,200 +0,0 @@
0
0
0
0.133333
0
0.363636
0
0
0
0
0
0
0
0
0
0
0
0
0
0.0588235
0
0
0.375
0
0
0
0.105263
0
0.24
0
0
0.2
0.333333
0
0
0
0
0
0
0
0
0
0
0
0
0.142857
0.173913
0
0
0
0
0
0.0645161
0.470588
0
0
0
0
0
0
0
0
0.84
0
0.0625
0
0
0
0
0
0
0
0.0454545
0
0
0
0
0.117647
0
0.137931
0
0
0
0
0
0
0
0
0
0.703704
0
0.0357143
0
0
0.0714286
0
0.15
0.136364
0
0
0.0588235
0
0
0.333333
0
0
0
0.15
0
0
0.153846
0.0714286
0
0
0
0
0.0909091
0
0
0
0
0
0
0.0666667
0
0.645161
0
0
0.0625
0
0
0
0
0
0
0
0
0.5
0
0
0
0
0
0
0
0
0
0
0.133333
0.105263
0.692308
0
0
0
0
0
0
0.0625
0
0
0.25
0.214286
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0.03125
0
0
0
0
0
0
0
0.047619
0.8
0
0
0
0
0
0
0
0
0
0.0588235
0
0
0.2
1 0
0
0
0
0.133333
0
0.363636
0
0
0
0
0
0
0
0
0
0
0
0
0
0.0588235
0
0
0.375
0
0
0
0.105263
0
0.24
0
0
0.2
0.333333
0
0
0
0
0
0
0
0
0
0
0
0
0.142857
0.173913
0
0
0
0
0
0.0645161
0.470588
0
0
0
0
0
0
0
0
0.84
0
0.0625
0
0
0
0
0
0
0
0.0454545
0
0
0
0
0.117647
0
0.137931
0
0
0
0
0
0
0
0
0
0.703704
0
0.0357143
0
0
0.0714286
0
0.15
0.136364
0
0
0.0588235
0
0
0.333333
0
0
0
0.15
0
0
0.153846
0.0714286
0
0
0
0
0.0909091
0
0
0
0
0
0
0.0666667
0
0.645161
0
0
0.0625
0
0
0
0
0
0
0
0
0.5
0
0
0
0
0
0
0
0
0
0
0.133333
0.105263
0.692308
0
0
0
0
0
0
0.0625
0
0
0.25
0.214286
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0.03125
0
0
0
0
0
0
0
0.047619
0.8
0
0
0
0
0
0
0
0
0
0.0588235
0
0
0.2