Iam

egs/iam/v2/local/chain/compare_wer.sh

@@ -50,32 +50,32 @@ for x in $*; do
 done
 echo
 
-echo -n "# WER val  "
+echo -n "# WER val "
 for x in $*; do
  wer=$(cat $x/decode_val/scoring_kaldi/best_wer | awk '{print $2}')
  printf "% 10s" $wer
 done
 echo
 
-echo -n "# WER (rescored) val  "
+echo -n "# WER (rescored) val "
 for x in $*; do
  wer="--"
- [ -d $x/decode_val_rescored ] && wer=$(cat $x/decode_test_rescored/scoring_kaldi/best_wer | awk '{print $2}')
+ [ -d $x/decode_val_rescored ] && wer=$(cat $x/decode_val_rescored/scoring_kaldi/best_wer | awk '{print $2}')
  printf "% 10s" $wer
 done
 echo
 
-echo -n "# CER val  "
+echo -n "# CER val "
 for x in $*; do
  cer=$(cat $x/decode_val/scoring_kaldi/best_cer | awk '{print $2}')
  printf "% 10s" $cer
 done
 echo
 
-echo -n "# CER (rescored) val  "
+echo -n "# CER (rescored) val "
 for x in $*; do
  cer="--"
- [ -d $x/decode_val_rescored ] && cer=$(cat $x/decode_test_rescored/scoring_kaldi/best_cer | awk '{print $2}')
+ [ -d $x/decode_val_rescored ] && cer=$(cat $x/decode_val_rescored/scoring_kaldi/best_cer | awk '{print $2}')
  printf "% 10s" $cer
 done
 echo

egs/iam/v2/local/chain/tuning/run_cnn_e2eali_1a.sh

@@ -43,7 +43,9 @@ tdnn_dim=450
 # training options
 srand=0
 remove_egs=true
-lang_test=lang_unk
+lang_decode=data/lang
+lang_rescore=data/lang_rescore_6g
+if $decode_val; then maybe_val=val; else maybe_val= ; fi
 # End configuration section.
 echo "$0 $@" # Print the command line for logging
 
@@ -229,35 +231,25 @@ if [ $stage -le 6 ]; then
  # as long as phones.txt was compatible.
 
  utils/mkgraph.sh \
- --self-loop-scale 1.0 data/$lang_test \
+ --self-loop-scale 1.0 $lang_decode \
  $dir $dir/graph || exit 1;
 fi
 
 if [ $stage -le 7 ]; then
  frames_per_chunk=$(echo $chunk_width | cut -d, -f1)
- steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
- --extra-left-context $chunk_left_context \
- --extra-right-context $chunk_right_context \
- --extra-left-context-initial 0 \
- --extra-right-context-final 0 \
- --frames-per-chunk $frames_per_chunk \
- --nj $nj --cmd "$cmd" \
- $dir/graph data/test $dir/decode_test || exit 1;
-fi
-
-if [ $stage -le 8 ] && $decode_val; then
- frames_per_chunk=$(echo $chunk_width | cut -d, -f1)
- steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
- --extra-left-context $chunk_left_context \
- --extra-right-context $chunk_right_context \
- --extra-left-context-initial 0 \
- --extra-right-context-final 0 \
- --frames-per-chunk $frames_per_chunk \
- --nj $nj --cmd "$cmd" \
- $dir/graph data/val $dir/decode_val || exit 1;
-
- steps/lmrescore_const_arpa.sh --cmd "$cmd" $lang_decode $lang_rescore \
- data/val $dir/decode_val{,_rescored} || exit 1
+ for decode_set in test $maybe_val; do
+ steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
+ --extra-left-context $chunk_left_context \
+ --extra-right-context $chunk_right_context \
+ --extra-left-context-initial 0 \
+ --extra-right-context-final 0 \
+ --frames-per-chunk $frames_per_chunk \
+ --nj $nj --cmd "$cmd" \
+ $dir/graph data/$decode_set $dir/decode_$decode_set || exit 1;
+
+ steps/lmrescore_const_arpa.sh --cmd "$cmd" $lang_decode $lang_rescore \
+ data/$decode_set $dir/decode_$decode_set{,_rescored} || exit 1
+ done
 fi
 
 echo "Done. Date: $(date). Results:"

egs/iam/v2/local/chain/tuning/run_cnn_e2eali_1b.sh

@@ -46,6 +46,7 @@ srand=0
 remove_egs=true
 lang_decode=data/lang
 lang_rescore=data/lang_rescore_6g
+if $decode_val; then maybe_val=val; else maybe_val= ; fi
 
 # End configuration section.
 echo "$0 $@" # Print the command line for logging
@@ -238,32 +239,19 @@ fi
 
 if [ $stage -le 7 ]; then
  frames_per_chunk=$(echo $chunk_width | cut -d, -f1)
- steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
- --extra-left-context $chunk_left_context \
- --extra-right-context $chunk_right_context \
- --extra-left-context-initial 0 \
- --extra-right-context-final 0 \
- --frames-per-chunk $frames_per_chunk \
- --nj $nj --cmd "$cmd" \
- $dir/graph data/test $dir/decode_test || exit 1;
-
- steps/lmrescore_const_arpa.sh --cmd "$cmd" $lang_decode $lang_rescore \
- data/test $dir/decode_test{,_rescored} || exit 1
-fi
-
-if [ $stage -le 8 ] && $decode_val; then
- frames_per_chunk=$(echo $chunk_width | cut -d, -f1)
- steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
- --extra-left-context $chunk_left_context \
- --extra-right-context $chunk_right_context \
- --extra-left-context-initial 0 \
- --extra-right-context-final 0 \
- --frames-per-chunk $frames_per_chunk \
- --nj $nj --cmd "$cmd" \
- $dir/graph data/val $dir/decode_val || exit 1;
-
- steps/lmrescore_const_arpa.sh --cmd "$cmd" $lang_decode $lang_rescore \
- data/val $dir/decode_val{,_rescored} || exit 1
+ for decode_set in test $maybe_val; do
+ steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
+ --extra-left-context $chunk_left_context \
+ --extra-right-context $chunk_right_context \
+ --extra-left-context-initial 0 \
+ --extra-right-context-final 0 \
+ --frames-per-chunk $frames_per_chunk \
+ --nj $nj --cmd "$cmd" \
+ $dir/graph data/$decode_set $dir/decode_$decode_set || exit 1;
+
+ steps/lmrescore_const_arpa.sh --cmd "$cmd" $lang_decode $lang_rescore \
+ data/$decode_set $dir/decode_$decode_set{,_rescored} || exit 1
+ done
 fi
 
 echo "Done. Date: $(date). Results:"

egs/iam/v2/local/chain/tuning/run_cnn_e2eali_1c.sh

@@ -48,7 +48,7 @@ srand=0
 remove_egs=true
 lang_decode=data/lang
 lang_rescore=data/lang_rescore_6g
-
+if $decode_val; then maybe_val=val; else maybe_val= ; fi
 dropout_schedule='0,[email protected],[email protected],0'
 # End configuration section.
 echo "$0 $@" # Print the command line for logging
@@ -240,32 +240,19 @@ fi
 
 if [ $stage -le 7 ]; then
  frames_per_chunk=$(echo $chunk_width | cut -d, -f1)
- steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
- --extra-left-context $chunk_left_context \
- --extra-right-context $chunk_right_context \
- --extra-left-context-initial 0 \
- --extra-right-context-final 0 \
- --frames-per-chunk $frames_per_chunk \
- --nj $nj --cmd "$cmd" \
- $dir/graph data/test $dir/decode_test || exit 1;
-
- steps/lmrescore_const_arpa.sh --cmd "$cmd" $lang_decode $lang_rescore \
- data/test $dir/decode_test{,_rescored} || exit 1
-fi
-
-if [ $stage -le 8 ] && $decode_val; then
- frames_per_chunk=$(echo $chunk_width | cut -d, -f1)
- steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
- --extra-left-context $chunk_left_context \
- --extra-right-context $chunk_right_context \
- --extra-left-context-initial 0 \
- --extra-right-context-final 0 \
- --frames-per-chunk $frames_per_chunk \
- --nj $nj --cmd "$cmd" \
- $dir/graph data/val $dir/decode_val || exit 1;
-
- steps/lmrescore_const_arpa.sh --cmd "$cmd" $lang_decode $lang_rescore \
- data/val $dir/decode_val{,_rescored} || exit 1
+ for decode_set in test $maybe_val; do
+ steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
+ --extra-left-context $chunk_left_context \
+ --extra-right-context $chunk_right_context \
+ --extra-left-context-initial 0 \
+ --extra-right-context-final 0 \
+ --frames-per-chunk $frames_per_chunk \
+ --nj $nj --cmd "$cmd" \
+ $dir/graph data/$decode_set $dir/decode_$decode_set || exit 1;
+
+ steps/lmrescore_const_arpa.sh --cmd "$cmd" $lang_decode $lang_rescore \
+ data/$decode_set $dir/decode_$decode_set{,_rescored} || exit 1
+ done
 fi
 
 echo "Done. Date: $(date). Results:"

egs/iam/v2/local/chain/tuning/run_cnn_e2eali_1d.sh

@@ -1,5 +1,8 @@
 #!/bin/bash
 
+# e2eali_1c is the same as e2eali_1c but has more CNN layers, different filter size
+# smaller lm-opts, less epochs, more initial/finaljobs, less minibatch, frams-per-iter.
+
 # This script does end2end chain training (i.e. from scratch)
 # local/chain/compare_wer.sh exp/chain/e2e_cnn_1b/ exp/chain/cnn_e2eali_1d
 # System e2e_cnn_1b cnn_e2eali_1d
@@ -44,7 +47,7 @@ srand=0
 remove_egs=true
 lang_decode=data/lang
 lang_rescore=data/lang_rescore_6g
-
+if $decode_val; then maybe_val=val; else maybe_val= ; fi
 dropout_schedule='0,[email protected],[email protected],0'
 # End configuration section.
 echo "$0 $@" # Print the command line for logging
@@ -237,33 +240,21 @@ fi
 
 if [ $stage -le 7 ]; then
  frames_per_chunk=$(echo $chunk_width | cut -d, -f1)
- steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
- --extra-left-context $chunk_left_context \
- --extra-right-context $chunk_right_context \
- --extra-left-context-initial 0 \
- --extra-right-context-final 0 \
- --frames-per-chunk $frames_per_chunk \
- --nj $nj --cmd "$cmd" \
- $dir/graph data/test $dir/decode_test || exit 1;
-
- steps/lmrescore_const_arpa.sh --cmd "$cmd" $lang_decode $lang_rescore \
- data/test $dir/decode_test{,_rescored} || exit 1
+ for decode_set in test $maybe_val; do
+ steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
+ --extra-left-context $chunk_left_context \
+ --extra-right-context $chunk_right_context \
+ --extra-left-context-initial 0 \
+ --extra-right-context-final 0 \
+ --frames-per-chunk $frames_per_chunk \
+ --nj $nj --cmd "$cmd" \
+ $dir/graph data/$decode_set $dir/decode_$decode_set || exit 1;
+
+ steps/lmrescore_const_arpa.sh --cmd "$cmd" $lang_decode $lang_rescore \
+ data/$decode_set $dir/decode_$decode_set{,_rescored} || exit 1
+ done
 fi
 
-if [ $stage -le 8 ] && $decode_val; then
- frames_per_chunk=$(echo $chunk_width | cut -d, -f1)
- steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
- --extra-left-context $chunk_left_context \
- --extra-right-context $chunk_right_context \
- --extra-left-context-initial 0 \
- --extra-right-context-final 0 \
- --frames-per-chunk $frames_per_chunk \
- --nj $nj --cmd "$cmd" \
- $dir/graph data/val $dir/decode_val || exit 1;
-
- steps/lmrescore_const_arpa.sh --cmd "$cmd" $lang_decode $lang_rescore \
- data/val $dir/decode_val{,_rescored} || exit 1
-fi
 
 echo "Done. Date: $(date). Results:"
 local/chain/compare_wer.sh $dir

egs/iam/v2/local/chain/tuning/run_e2e_cnn_1a.sh

@@ -163,23 +163,14 @@ if [ $stage -le 4 ]; then
 fi
 
 if [ $stage -le 5 ]; then
- frames_per_chunk=$(echo $chunk_width | cut -d, -f1)
- steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
- --nj $nj --cmd "$cmd" \
- $dir/graph data/test $dir/decode_test || exit 1;
-
- steps/lmrescore_const_arpa.sh --cmd "$cmd" $lang_decode $lang_rescore \
- data/test $dir/decode_test{,_rescored} || exit 1
-fi
-
-if [ $stage -le 6 ] && $decode_val; then
- frames_per_chunk=$(echo $chunk_width | cut -d, -f1)
- steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
- --nj $nj --cmd "$cmd" \
- $dir/graph data/val $dir/decode_val || exit 1;
-
- steps/lmrescore_const_arpa.sh --cmd "$cmd" $lang_decode $lang_rescore \
- data/val $dir/decode_val{,_rescored} || exit 1
+ for decode_set in test $maybe_val; do
+ steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
+ --nj $nj --cmd "$cmd" \
+ $dir/graph data/$decode_set $dir/decode_$decode_set || exit 1;
+
+ steps/lmrescore_const_arpa.sh --cmd "$cmd" $lang_decode $lang_rescore \
+ data/$decode_set $dir/decode_$decode_set{,_rescored} || exit 1
+ done
 fi
 
 echo "Done. Date: $(date). Results:"

egs/iam/v2/local/chain/tuning/run_e2e_cnn_1b.sh

@@ -33,7 +33,7 @@ train_set=train
 decode_val=true
 lang_decode=data/lang
 lang_rescore=data/lang_rescore_6g
-
+if $decode_val; then maybe_val=val; else maybe_val= ; fi
 # End configuration section.
 echo "$0 $@" # Print the command line for logging
 
@@ -149,23 +149,14 @@ if [ $stage -le 4 ]; then
 fi
 
 if [ $stage -le 5 ]; then
- frames_per_chunk=$(echo $chunk_width | cut -d, -f1)
- steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
- --nj $nj --cmd "$cmd" \
- $dir/graph data/test $dir/decode_test || exit 1;
-
- steps/lmrescore_const_arpa.sh --cmd "$cmd" $lang_decode $lang_rescore \
- data/test $dir/decode_test{,_rescored} || exit 1
-fi
-
-if [ $stage -le 6 ] && $decode_val; then
- frames_per_chunk=$(echo $chunk_width | cut -d, -f1)
- steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
- --nj $nj --cmd "$cmd" \
- $dir/graph data/val $dir/decode_val || exit 1;
-
- steps/lmrescore_const_arpa.sh --cmd "$cmd" $lang_decode $lang_rescore \
- data/val $dir/decode_val{,_rescored} || exit 1
+ for decode_set in test $maybe_val; do
+ steps/nnet3/decode.sh --acwt 1.0 --post-decode-acwt 10.0 \
+ --nj $nj --cmd "$cmd" \
+ $dir/graph data/$decode_set $dir/decode_$decode_set || exit 1;
+
+ steps/lmrescore_const_arpa.sh --cmd "$cmd" $lang_decode $lang_rescore \
+ data/$decode_set $dir/decode_$decode_set{,_rescored} || exit 1
+ done
 fi
 
 echo "Done. Date: $(date). Results:"