Merge master into kaldi10 (#3105)

* [src] Change warp-synchronous to cub::BlockReduce (safer but slower) (#3080)

* [src] Fix && and || uses where & and | intended, and other weird errors (#3087)

* [build] Some fixes to Makefiles (#3088)

clang is unhappy with '-rdynamic' in compile-only step, and the
switch is really unnecessary.

Also, the default location for MKL 64-bit libraries is intel64/.
The em64t/ was explained already obsolete by an Intel rep in 2010:
https://software.intel.com/en-us/forums/intel-math-kernel-library/topic/285973

* [src] Fixed -Wreordered warnings in feat (#3090)

* [egs] Replace bc with perl -e (#3093)

* [scripts] Fix python3 compatibility issue in data-perturbing script (#3084)

* [doc] fix some typos in doc. (#3097)

* [build] Make sure expf() speed probe times sensibly (#3089)

* [scripts] Make sure merge_targets.py works in python3 (#3094)

* [src] ifdef to fix compilation failure on CUDA 8 and earlier (#3103)

* [doc] fix typos and broken links in doc. (#3102)

* [scripts] Fix frame_shift bug in egs/swbd/s5c/local/score_sclite_conf.sh (#3104)

Author: desh2608

egs/callhome_diarization/v1/diarization/nnet3/xvector/extract_xvectors.sh

@@ -102,7 +102,7 @@ if [ $stage -le 0 ]; then
   fi
   utils/data/get_uniform_subsegments.py \
       --max-segment-duration=$window \
-      --overlap-duration=$(echo "$window-$period" | bc) \
+      --overlap-duration=$(perl -e "print ($window-$period);") \
       --max-remaining-duration=$min_segment \
       --constant-duration=True \
       $segments > $dir/subsegments

egs/callhome_diarization/v1/run.sh

@@ -188,7 +188,7 @@ if [ $stage -le 6 ]; then
 
       der=$(grep -oP 'DIARIZATION\ ERROR\ =\ \K[0-9]+([.][0-9]+)?' \
         exp/tuning/${dataset}_t${threshold})
-      if [ $(echo $der'<'$best_der | bc -l) -eq 1 ]; then
+      if [ $(perl -e "print ($der < $best_der ? 1 : 0);") -eq 1 ]; then
         best_der=$der
         best_threshold=$threshold
       fi

egs/callhome_diarization/v2/run.sh

@@ -297,7 +297,7 @@ if [ $stage -le 10 ]; then
 
       der=$(grep -oP 'DIARIZATION\ ERROR\ =\ \K[0-9]+([.][0-9]+)?' \
         $nnet_dir/tuning/${dataset}_t${threshold})
-      if [ $(echo $der'<'$best_der | bc -l) -eq 1 ]; then
+      if [ $(perl -e "print ($der < $best_der ? 1 : 0);") -eq 1 ]; then
         best_der=$der
         best_threshold=$threshold
       fi

egs/dihard_2018/v1/run.sh

@@ -186,7 +186,7 @@ if [ $stage -le 7 ]; then
 
     der=$(grep -oP 'DIARIZATION\ ERROR\ =\ \K[0-9]+([.][0-9]+)?' \
       $ivec_dir/tuning/dihard_2018_dev_t${threshold})
-    if [ $(echo $der'<'$best_der | bc -l) -eq 1 ]; then
+    if [ $(perl -e "print ($der < $best_der ? 1 : 0);") -eq 1 ]; then
       best_der=$der
       best_threshold=$threshold
     fi

egs/dihard_2018/v2/run.sh

@@ -260,7 +260,7 @@ if [ $stage -le 12 ]; then
 
     der=$(grep -oP 'DIARIZATION\ ERROR\ =\ \K[0-9]+([.][0-9]+)?' \
       $nnet_dir/tuning/dihard_2018_dev_t${threshold})
-    if [ $(echo $der'<'$best_der | bc -l) -eq 1 ]; then
+    if [ $(perl -e "print ($der < $best_der ? 1 : 0);") -eq 1 ]; then
       best_der=$der
       best_threshold=$threshold
     fi

egs/rm/README.txt

@@ -9,7 +9,7 @@ About the Resource Management corpus:
 
 Each subdirectory of this directory contains the
 scripts for a sequence of experiments. 
-s5 is the currently recommmended setup.
+s5 is the currently recommended setup.
 
   s5: This is the "new-new-style" recipe.  It is now finished.
       All further work will be on top of this style of recipe.  Note: 

egs/sre08/v1/local/score_sre08.sh

@@ -35,11 +35,11 @@ tot_eer=0.0
 printf '% 12s' 'EER:'
 for condition in $(seq 8); do
   eer=$(awk '{print $3}' $scores | paste - $trials | awk -v c=$condition '{n=4+c; if ($n == "Y") print $1, $4}' | compute-eer - 2>/dev/null)
-  tot_eer=$(echo "$tot_eer+$eer" | bc)
+  tot_eer=$(perl -e "print ($tot_eer+$eer);")
   eers[$condition]=$eer
 done
 
-eers[0]=$(echo "$tot_eer/8" | bc -l)
+eers[0]=$(perl -e "print ($tot_eer/8.0);")
 
 for i in $(seq 0 8); do
   printf '% 7.2f' ${eers[$i]}

egs/swbd/s5c/local/score_sclite_conf.sh

@@ -39,6 +39,12 @@ for f in $data/stm $data/glm $lang/words.txt $lang/phones/word_boundary.int \
   [ ! -f $f ] && echo "$0: expecting file $f to exist" && exit 1;
 done
 
+if [ -f $dir/../frame_subsampling_factor ]; then
+  factor=$(cat $dir/../frame_subsampling_factor) || exit 1
+  frame_shift_opt="--frame-shift=0.0$factor"
+  echo "$0: $dir/../frame_subsampling_factor exists, using $frame_shift_opt"
+fi
+
 name=`basename $data`; # e.g. eval2000
 
 mkdir -p $dir/scoring/log
@@ -51,7 +57,7 @@ if [ $stage -le 0 ]; then
       ACWT=\`perl -e \"print 1.0/LMWT\;\"\` '&&' \
       lattice-add-penalty --word-ins-penalty=$wip "ark:gunzip -c $dir/lat.*.gz|" ark:- \| \
       lattice-align-words $lang/phones/word_boundary.int $model ark:- ark:- \| \
-      lattice-to-ctm-conf --decode-mbr=$decode_mbr --acoustic-scale=\$ACWT  ark:- - \| \
+      lattice-to-ctm-conf $frame_shift_opt --decode-mbr=$decode_mbr --acoustic-scale=\$ACWT  ark:- - \| \
       utils/int2sym.pl -f 5 $lang/words.txt  \| \
       utils/convert_ctm.pl $data/segments $data/reco2file_and_channel \
       '>' $dir/score_LMWT_${wip}/$name.ctm || exit 1;

egs/wsj/s5/local/chain/tuning/run_tdnn_1g.sh

@@ -160,7 +160,7 @@ if [ $stage -le 15 ]; then
   echo "$0: creating neural net configs using the xconfig parser";
 
   num_targets=$(tree-info $tree_dir/tree |grep num-pdfs|awk '{print $2}')
-  learning_rate_factor=$(echo "print 0.5/$xent_regularize" | python)
+  learning_rate_factor=$(echo "print(0.5/$xent_regularize)" | python)
   tdnn_opts="l2-regularize=0.01 dropout-proportion=0.0 dropout-per-dim-continuous=true"
   tdnnf_opts="l2-regularize=0.01 dropout-proportion=0.0 bypass-scale=0.66"
   linear_opts="l2-regularize=0.01 orthonormal-constraint=-1.0"

egs/wsj/s5/steps/segmentation/internal/merge_targets.py

@@ -1,4 +1,4 @@
-#!/usr/bin/env python
+#!/usr/bin/env python3
 
 # Copyright 2017  Vimal Manohar
 # Apache 2.0
@@ -16,8 +16,6 @@
 option.
 """
 
-from __future__ import print_function
-from __future__ import division
 import argparse
 import logging
 import numpy as np
@@ -111,7 +109,7 @@ def should_remove_frame(row, dim):
                                      # source[2] = [ 0 0 0 ]
     """
     assert len(row) % dim == 0
-    num_sources = len(row) / dim
+    num_sources = len(row) // dim
 
     max_idx = np.argmax(row)
     max_val = row[max_idx]

egs/wsj/s5/utils/data/perturb_data_dir_volume.sh

@@ -52,15 +52,15 @@ for line in sys.stdin.readlines():
   parts = line.strip().split()
   if line.strip()[-1] == '|':
     if re.search('sox --vol', ' '.join(parts[-11:])):
-      print 'true'
+      print('true')
       sys.exit(0)
   elif re.search(':[0-9]+$', line.strip()) is not None:
     continue
   else:
     if ' '.join(parts[1:3]) == 'sox --vol':
-      print 'true'
+      print('true')
       sys.exit(0)
-print 'false'
+print('false')
 "` || exit 1
 
 if $volume_perturb_done; then

src/bin/compute-wer-bootci.cc

@@ -162,7 +162,7 @@ int main(int argc, char *argv[]) {
 
   try {
     const char *usage =
-      "Compute a bootstrapping of WER to extract the 95\% confidence interval.\n"
+      "Compute a bootstrapping of WER to extract the 95% confidence interval.\n"
       "Take a reference and a transcription file, in integer or text format,\n"
       "and outputs overall WER statistics to standard output along with its\n"
       "confidence interval using the bootstrap method of Bisani and Ney.\n"
@@ -234,12 +234,12 @@ int main(int argc, char *argv[]) {
     std::cout.precision(2);
     std::cerr.precision(2);
     std::cout << "Set1: %WER " << std::fixed << 100*mean_wer <<
-              " 95\% Conf Interval [ " << 100*mean_wer-100*interval <<
+              " 95% Conf Interval [ " << 100*mean_wer-100*interval <<
               ", " << 100*mean_wer+100*interval << " ]" << '\n';
 
     if(!hyp2_rspecifier.empty()) {
         std::cout << "Set2: %WER " << std::fixed << 100*mean_wer2 <<
-            " 95\% Conf Interval [ " << 100*mean_wer2-100*interval2 <<
+            " 95% Conf Interval [ " << 100*mean_wer2-100*interval2 <<
             ", " << 100*mean_wer2+100*interval2 << " ]" << '\n';
 
         std::cout << "Probability of Set2 improving Set1: " << std::fixed <<

src/cudamatrix/cu-device.cc

@@ -111,12 +111,14 @@ void CuDevice::Initialize() {
     CUBLAS_SAFE_CALL(cublasCreate(&cublas_handle_));
     CUBLAS_SAFE_CALL(cublasSetStream(cublas_handle_, cudaStreamPerThread));
 
+    #if CUDA_VERSION >= 9000 
     if (device_options_.use_tensor_cores) {
       // Enable tensor cores in CUBLAS
       // Note if the device does not support tensor cores this will fall back to normal math mode
       CUBLAS_SAFE_CALL(cublasSetMathMode(cublas_handle_, 
             CUBLAS_TENSOR_OP_MATH));
     }
+    #endif
 
     // Initialize the cuSPARSE library
     CUSPARSE_SAFE_CALL(cusparseCreate(&cusparse_handle_));