DETAILED OVERALL REPORT FOR THE SYSTEM: /scratch/project_465000836/ipoloka/huggingface_asr/experiments/decred/commonvoice/DeCRED_small_cv/predictions_common_voice_13_en_common_voice_13_en_test_wer108.70_hyp.trn

SENTENCE RECOGNITION PERFORMANCE

 sentences                                           4
 with errors                            100.0%   (   4)

   with substitutions                   100.0%   (   4)
   with deletions                        50.0%   (   2)
   with insertions                       25.0%   (   1)


WORD RECOGNITION PERFORMANCE

Percent Total Error       =  108.7%   (  25)

Percent Correct           =    0.0%   (   0)

Percent Substitution      =   73.9%   (  17)
Percent Deletions         =   26.1%   (   6)
Percent Insertions        =    8.7%   (   2)
Percent Word Accuracy     =   -8.7%


Ref. words                =           (  23)
Hyp. words                =           (  19)
Aligned words             =           (  25)

CONFUSION PAIRS                  Total                 (17)
                                 With >=  1 occurrences (17)

   1:    1  ->  about ==> theas
   2:    1  ->  alls ==> a
   3:    1  ->  also ==> moas
   4:    1  ->  and ==> available
   5:    1  ->  buster ==> moa
   6:    1  ->  ends ==> alsasls
   7:    1  ->  films ==> was
   8:    1  ->  had ==> thea
   9:    1  ->  medium ==> thes
  10:    1  ->  of ==> a
  11:    1  ->  reservations ==> ends
  12:    1  ->  right ==> hus
  13:    1  ->  six ==> thes
  14:    1  ->  that ==> californias
  15:    1  ->  the ==> thels
  16:    1  ->  well ==> alsas
  17:    1  ->  well ==> wasasasasasaslasasasas
     -------
        17



INSERTIONS                       Total                 (2)
                                 With >=  1 occurrences (2)

   1:    1  ->  asasas
   2:    1  ->  theaslsas
     -------
         2



DELETIONS                        Total                 (6)
                                 With >=  1 occurrences (6)

   1:    1  ->  all
   2:    1  ->  be
   3:    1  ->  disapproved
   4:    1  ->  joe
   5:    1  ->  keaton
   6:    1  ->  shell
     -------
         6



SUBSTITUTIONS                    Total                 (16)
                                 With >=  1 occurrences (16)

   1:    2  ->  well
   2:    1  ->  about
   3:    1  ->  alls
   4:    1  ->  also
   5:    1  ->  and
   6:    1  ->  buster
   7:    1  ->  ends
   8:    1  ->  films
   9:    1  ->  had
  10:    1  ->  medium
  11:    1  ->  of
  12:    1  ->  reservations
  13:    1  ->  right
  14:    1  ->  six
  15:    1  ->  that
  16:    1  ->  the
     -------
        17


* NOTE: The 'Substitution' words are those reference words
        for which the recognizer supplied an incorrect word.


FALSELY RECOGNIZED               Total                 (15)
                                 With >=  1 occurrences (15)

   1:    2  ->  a
   2:    2  ->  thes
   3:    1  ->  alsas
   4:    1  ->  alsasls
   5:    1  ->  available
   6:    1  ->  californias
   7:    1  ->  ends
   8:    1  ->  hus
   9:    1  ->  moa
  10:    1  ->  moas
  11:    1  ->  thea
  12:    1  ->  theas
  13:    1  ->  thels
  14:    1  ->  was
  15:    1  ->  wasasasasasaslasasasas
     -------
        17


* NOTE: The 'Falsely Recognized' words are those hypothesis words
        which the recognizer incorrectly substituted for a reference word.