Merge branch 'master' into sandbox-oplatek

Conflicts: .gitignore INSTALL README.txt egs/babel/s5/local/generate_proxy_keywords.sh egs/wsj/s5/steps/train_nnet_cpu.sh egs/wsj/s5/utils/nnet-cpu/make_nnet_config_preconditioned.pl src/Makefile src/configure src/lat/Makefile src/makefiles/cygwin.mk src/makefiles/darwin_10_5.mk src/makefiles/darwin_10_6.mk src/makefiles/darwin_10_7.mk src/makefiles/darwin_10_8.mk src/makefiles/linux_atlas.mk src/makefiles/linux_atlas_64bit.mk src/makefiles/linux_clapack.mk src/makefiles/linux_openblas.mk src/nnet-cpu/mixup-nnet.cc src/nnet-cpu/nnet-component-test.cc src/nnet-cpu/nnet-component.cc src/nnet-cpu/nnet-component.h src/nnet-cpu/nnet-nnet.cc src/nnet-cpu/nnet-nnet.h src/nnet-cpu/nnet-update-parallel.cc src/nnet-cpu/nnet-update-parallel.h src/nnet-cpubin/nnet-train-parallel.cc src/nnet/nnet-pdf-prior.h src/nnetbin/nnet-forward.cc tools/Makefile tools/extras/install_portaudio.sh git-svn-id: https://svn.code.sf.net/p/kaldi/code/sandbox/oplatek@2520 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8
vimalmanohar · Jun 18, 2013 · 817ce77 · 817ce77
1 parent f38fe56
commit 817ce77
Show file tree

Hide file tree

Showing 155 changed files with 14,774 additions and 8 deletions.
diff --git a/INSTALL b/INSTALL
@@ -1,4 +1,4 @@
-
+This is the official Kaldi INSTALL. Look also at INSTALL.md for the git mirror installation.
 [for native Windows install, see windows/INSTALL]
 
 (1)

diff --git a/INSTALL.md b/INSTALL.md
@@ -0,0 +1,168 @@
+Installation TIPS for KALDI and installation INSTRUCTIONS for my additional repositories
+=================================================================================
+Intro
+-----
+Kaldi has very good instructions and tutorial
+for building it from source. It is easy and straightforward.
+However, I needed also to build shared libraries
+and maybe you will face some of my problems too.
+So this is the reasons for writing my building procedure down.
+
+Installing external dependencies
+================================
+See `kaldi-trunk/tools/INSTALL` for info.
+Basically it telss you to use `kaldi-trunk/tools/Makefile`, which I used also.
+
+How have I installed OpenBlas?
+----------------------
+Simple enough:
+```bash
+make openblas
+```
+
+How have I installed Openfst?
+----------------------
+In order to install also shared libraries
+I changed the line 37 in 
+`kaldi-trunk/tools/Makefile`
+
+```sh
+*** Makefile 
+************
+*** 34,38 ****
+
+openfst-1.3.2/Makefile: openfst-1.3.2/.patched
+		cd openfst-1.3.2/; \
+!		./configure --prefix=`pwd` --enable-static --disable-shared --enable-far --enable-ngram-fsts
+
+--- 34,38 ----
+
+openfst-1.3.2/Makefile: openfst-1.3.2/.patched
+		cd openfst-1.3.2/; \
+!		./configure --prefix=`pwd` --enable-static --enable-shared --enable-far --enable-ngram-fsts
+
+```
+Than I ran
+```bash
+make openfst_tgt
+```
+
+How have I installed PortAudio?
+--------------------------
+NOTE: Necessary only for Kaldi online decoder
+
+In kaldi-trunk/tools/extras/install_portaudio.sh
+I changed line
+```
+./configure --prefix=`pwd`/install
+```
+to
+```
+./configure --prefix=`pwd`/install --with-pic
+```
+
+Then I ran
+```bash
+extras/install_portaudio.sh
+```
+
+
+How have I built Kaldi?
+------------------
+```bash
+./configure --openblas-root=`pwd`/../tools/OpenBLAS/install --fst-root=`pwd`/../tools/openfst --static-math=no
+```
+
+Edit the `kaldi.mk` and add the `-fPIC` flag.
+TODO It would be nice to do something like
+```bash
+EXTRA_CXXFLAGS=-fPIC make
+EXTRA_CXXFLAGS=-fPIC make ext
+```
+But the local makefiles overrides `EXTRA_CXXFLAGS`.
+
+If you updated from the svn repository do not forget to run `make depend`
+Since by *default it is turned of! I always forget about that!*
+```
+# DO NOT FORGET TO CHANGE kaldi.mk TODO SCRIPT IT!
+# make depend and make ext_depend are necessary only if dependencies changed
+make depend && make ext_depend && make && make ext
+```
+
+How have I updated Kaldi src code?
+----------------------------
+I checkout the kaldi-trunk version.
+
+[Kaldi install instructions](http://kaldi.sourceforge.net/install.html)
+
+Note: If you checkout Kaldi before March 2013 you need to relocate svn. See the instructions in the link above!
+
+
+What setup did I use?
+--------------------
+In order to use Kaldi binaries everywhere I add them to `PATH`. 
+In addition, I needed to add `openfst` directory to `LD_LIBRARY_PATH`, I compiled Kaldi dynamically linked against `openfst`. To conclude, I added following lines to my `.bashrc`.
+```bash
+############# Kaldi ###########
+kaldisrc=/net/work/people/oplatek/kaldi/src
+export PATH="$PATH":$kaldisrc/bin:$kaldisrc/fgmmbin:$kaldisrc/gmmbin:$kaldisrc/nnetbin:$kaldisrc/sgmm2bin:$kaldisrc/tiedbin:$kaldisrc/featbin:$kaldisrc/fstbin:$kaldisrc/latbin:$kaldisrc/onlinebin:$kaldisrc/sgmmbin
+
+### Openfst ###
+openfst=/ha/home/oplatek/50GBmax/kaldi/tools/openfst
+export PATH="$PATH":$openfst/bin
+export LD_LIBRARY_PATH="$LD_LIBRARY_PATH":$openfst/lib 
+```
+
+Which tool for building a Language Model (LM) have I used?
+---------------------------------------------------------
+None. I received built LM in Arpa format.
+
+NOTE: Probably, I should build my own LM. 
+
+
+How have I installed Atlas?
+--------------------
+NOTE: I decided NOT to use Atlas, I USE OpenBlas INSTEAD. It is open source and it allows me to compile both shared and static libraries at one run.
+
+Nevertheless how I install Atlas:
+
+ * I installed version atlas3.10.1.tar.bz2 (available at sourceforge)
+ * I unpackaged it under `kaldi-trunk/tools` which created `kaldi-trunk/tools/ATLAS`
+ * The main problem with building ATLAS was for me disabling CPU throtling.
+ * I solved it by 
+
+```bash
+# running following command under root in my Ubuntu 12.10
+# It does not turn off CPU throttling in fact, but I do not need the things optimaze on my local machine
+# I ran it for all of my 4 cores
+# for n in 0 1 2 3 ; do echo 'performance' > /sys/devices/system/cpu/cpu${n}/cpufreq/scaling_governor ; done
+```
+
+ * Then I needed to install Fortran compiler (The error from configure was little bit covered by consequent errors) by 
+
+```bash
+sudo apt-get install gfortran
+```
+
+ * On Ubuntu 12.04 I had issue with 
+
+```bash
+/usr/include/features.h:323:26: fatal error: bits/predefs.h
+```
+
+   Which I solved by
+
+```bash
+sudo apt-get install --reinstall libc6-dev
+```
+
+ * Finally, in `kaldi-trunk/tools/ATLAS` I run:
+
+```bash
+mkdir build 
+mkdir ../atlas_install
+cd build
+../configure --shared --incdir=`pwd`/../../atlas_install
+make 
+make install
+ ```
diff --git a/README.md b/README.md
@@ -0,0 +1,25 @@
+ABOUT
+=====
+ * This is a Git mirror of [Svn trunk of Kaldi project](http://sourceforge.net/projects/kaldi/)
+   `svn://svn.code.sf.net/p/kaldi/code/trunk`
+ * In the branch `master` I commit my work. In the branch `svn_mirror` I mirror `svn://svn.code.sf.net/p/kaldi/code/trunk`. In the branch `sandbox-oplatek` I am developing changes which I would like to check in back to Kaldi.
+ * Currently, I mirror the repository manually as often as I needed.
+ * The main purpose for mirroring is that I want to build my own decoder and train my models for decoding based on up-to-date Kaldi version.
+ * Recipe for training the models can be found at `egs/kaldi-vystadial-recipe`
+ * Source code for python wrapper for online-decoder is at `src/python-kaldi-decoding` 
+ * Remarks about new decoder are located at `src/vystadial-decoder`
+ * I use the `Fake submodules` approach to merge the 3 subprojects to this repository. More about `Fake submodules` [at this blog](http://debuggable.com/posts/git-fake-submodules:4b563ee4-f3cc-4061-967e-0e48cbdd56cb).
+ * I mirror the svn via `git svn`. [Nice intro to git svn](http://viget.com/extend/effectively-using-git-with-subversion), [Walk through](http://blog.shinetech.com/2009/02/17/my-git-svn-workflow/) and [Multiple svn-remotes](http://blog.shuningbian.net/2011/05/git-with-multiple-svn-remotes.html)
+
+OTHER INFO
+----------
+ * Read `INSTALL.md` and `INSTALL` first!
+ * For training models read `egs/kaldi-vystadial-recipe/s5/README.md`
+ * For building and developing decoder callable from python read `src/python-kaldi-decoding/README.md`
+ * For information about new decoder read `src/vystadial-decoder/README.md`
+ * This work is done under [Vystadial project](https://sites.google.com/site/filipjurcicek/projects/vystadial).
+
+LICENSE
+--------
+ * We release all the changes at pyKaldi under `Apache license 2.0` license. Kaldi also uses `Apache 2.0` license). 
+ * We also want to publicly release the training data in the autumn 2013.
diff --git a/README.txt b/README.txt
@@ -1,4 +1,5 @@
-
+This is oficial Kaldi readme. You are now in Kaldi/trunk mirror.
+Read Kaldi.md and INSTALL.md first!
 
 
 See http://kaldi.sourceforge.net/ for documentation 

diff --git a/egs/babel/s5/local/annotatedKwlist2KWs.pl b/egs/babel/s5/local/annotatedKwlist2KWs.pl
@@ -0,0 +1,124 @@
+#!/usr/bin/perl
+
+# Copyright 2012  Johns Hopkins University (Author: Guoguo Chen)
+# Apache 2.0.
+#
+
+use strict;
+use warnings;
+use Getopt::Long;
+
+my $Usage = <<EOU;
+Usage: annotatedKwlist2KWs.pl [options] <kwlist.annot.xml|-> <keywords|-> [category]
+ e.g.: annotatedKwlist2KWs.pl kwlist.annot.list keywords.list "NGram Order:2,3,4"
+
+This script reads an annotated kwlist xml file and writes a list of keywords, according
+to the given categories. The "category" is a "key:value" pair in the annotated kwlist xml
+file. For example
+1. "NGram Order:2,3,4"
+2. "NGram Order:2"
+3. "NGram Order:-"
+where "NGram Order" is the category name. The first line means print keywords that are
+bigram, trigram and 4gram; The second line means print keywords only for bigram; The last
+line means print all possible ngram keywords.
+If no "category" is specified, the script will print out the possible categories.
+
+Allowed options:
+EOU
+
+GetOptions(); 
+
+@ARGV >= 2 || die $Usage;
+
+# Workout the input/output source
+my $kwlist_filename = shift @ARGV;
+my $kws_filename = shift @ARGV;
+
+my $source = "STDIN";
+if ($kwlist_filename ne "-") {
+  open(KWLIST, "<$kwlist_filename") || die "Fail to open kwlist file: $kwlist_filename\n";
+  $source = "KWLIST";
+}
+
+# Process kwlist.annot.xml
+my %attr;
+my %attr_kws;
+my $kwid="";
+my $name="";
+my $value="";
+while (<$source>) {
+  chomp;
+  if (m/<kw kwid=/) {($kwid) = /kwid="(\S+)"/; next;}
+  if (m/<name>/) {($name) = /<name>(.*)<\/name>/; next;}
+  if (m/<value>/) {
+    ($value) = /<value>(.*)<\/value>/;
+    if (defined($attr{$name})) {
+      $attr{"$name"}->{"$value"} = 1;
+    } else {
+      $attr{"$name"} = {"$value", 1};
+    }
+    if (defined($attr_kws{"${name}_$value"})) {
+      $attr_kws{"${name}_$value"}->{"$kwid"} = 1;
+    } else {
+      $attr_kws{"${name}_$value"} = {"$kwid", 1};
+    }
+  }
+}
+
+my $output = "";
+if (@ARGV == 0) {
+  # If no category provided, print out the possible categories
+  $output .= "Possible categories are:\n\n";
+  foreach my $name (keys %attr) {
+    $output .= "$name:";
+    my $count = 0;
+    foreach my $value (keys %{$attr{$name}}) {
+      if ($value eq "") {$value = "\"\"";}
+      if ($count == 0) {
+        $output .= "$value";
+        $count ++; next;
+      } 
+      if ($count == 6) {
+        $output .= ", ...";
+        last;
+      }
+      $output .= ",$value"; $count ++;
+    }
+    $output .= "\n";
+  }
+  print STDERR $output;
+  $output = "";
+} else {
+  my %keywords;
+  while (@ARGV > 0) {
+    my $category = shift @ARGV;
+    my @col = split(/:/, $category);
+    @col == 2 || die "Bad category \"$category\"\n";
+    $name = $col[0];
+    if ($col[1] eq "-") {
+      foreach my $value (keys %{$attr{$name}}) {
+        foreach my $kw (keys %{$attr_kws{"${name}_$value"}}) {
+          $keywords{$kw} = 1;
+        }
+      }
+    } else {
+      my @col1 = split(/,/, $col[1]);
+      foreach my $value (@col1) {
+        foreach my $kw (keys %{$attr_kws{"${name}_$value"}}) {
+          $keywords{$kw} = 1;
+        }
+      }
+    }
+  }
+  foreach my $kw (keys %keywords) {
+    $output .= "$kw\n";
+  }
+}
+
+if ($kwlist_filename ne "-") {close(KWLIST);}
+if ($kws_filename eq "-") { print $output;}
+else {
+  open(O, ">$kws_filename") || die "Fail to open file $kws_filename\n";
+  print O $output;
+  close(O);
+}