Speech-Lab-IITM/Hindi-ASR-Challenge

data/train/wav.scp is not in sorted order or has duplicates

Opened this issue · 0 comments

I got this error when building the model with the supplied data: utils/validate_data_dir.sh: file data/train/wav.scp is not in sorted order or has duplicates

Anyone else dealing with this or found a solution to this?

+ echo ============================================================================
============================================================================
+ echo '         MFCC Feature Extration & CMVN for Training and test set           '
         MFCC Feature Extration & CMVN for Training and test set           
+ echo ============================================================================
============================================================================
+ mfccdir=dump/mfcc_data
+ for x in $train_set $recog_sets
+ steps/make_mfcc.sh --cmd run.pl --nj 10 data/train exp_hindi_model/make_mfcc/train dump/mfcc_data/train
steps/make_mfcc.sh --cmd run.pl --nj 10 data/train exp_hindi_model/make_mfcc/train dump/mfcc_data/train
utils/validate_data_dir.sh: file data/train/wav.scp is not in sorted order or has duplicates
+ exit 1