commit 8a8aba9c712b7a0a8be5b9f2df004a69db1c4508 Author: koguzhan Date: Thu Jun 27 16:58:31 2019 +0200 wer results diff --git a/dev/oguz_2019_tatar_1_eval.txt b/dev/oguz_2019_tatar_1_eval.txt new file mode 100644 index 0000000..0c45bb7 --- /dev/null +++ b/dev/oguz_2019_tatar_1_eval.txt @@ -0,0 +1,28 @@ +Test file: 'kazantr.txt' +Reference file 'kazantur.txt' + +Statistics about input files +------------------------------------------------------- +Number of words in reference: 195 +Number of words in test: 210 +Number of unknown words (marked with a star) in test: 36 +Percentage of unknown words: 17.14 % + +Results when removing unknown-word marks (stars) +------------------------------------------------------- +Edit distance: 103 +Word error rate (WER): 52.82 % +Number of position-independent correct words: 112 +Position-independent word error rate (PER): 50.26 % + +Results when unknown-word marks (stars) are not removed +------------------------------------------------------- +Edit distance: 102 +Word Error Rate (WER): 52.31 % +Number of position-independent correct words: 113 +Position-independent word error rate (PER): 49.74 % + +Statistics about the translation of unknown words +------------------------------------------------------- +Number of unknown words which were free rides: -1 +Percentage of unknown words that were free rides: -2.78 %