Discrete token-based TTS implementation

egs2/TEMPLATE/tts2/cmd.sh

@@ -0,0 +1,110 @@
+# ====== About run.pl, queue.pl, slurm.pl, and ssh.pl ======
+# Usage: <cmd>.pl [options] JOB=1:<nj> <log> <command...>
+# e.g.
+#   run.pl --mem 4G JOB=1:10 echo.JOB.log echo JOB
+#
+# Options:
+#   --time <time>: Limit the maximum time to execute.
+#   --mem <mem>: Limit the maximum memory usage.
+#   -–max-jobs-run <njob>: Limit the number parallel jobs. This is ignored for non-array jobs.
+#   --num-threads <ngpu>: Specify the number of CPU core.
+#   --gpu <ngpu>: Specify the number of GPU devices.
+#   --config: Change the configuration file from default.
+#
+# "JOB=1:10" is used for "array jobs" and it can control the number of parallel jobs.
+# The left string of "=", i.e. "JOB", is replaced by <N>(Nth job) in the command and the log file name,
+# e.g. "echo JOB" is changed to "echo 3" for the 3rd job and "echo 8" for 8th job respectively.
+# Note that the number must start with a positive number, so you can't use "JOB=0:10" for example.
+#
+# run.pl, queue.pl, slurm.pl, and ssh.pl have unified interface, not depending on its backend.
+# These options are mapping to specific options for each backend and
+# it is configured by "conf/queue.conf" and "conf/slurm.conf" by default.
+# If jobs failed, your configuration might be wrong for your environment.
+#
+#
+# The official documentation for run.pl, queue.pl, slurm.pl, and ssh.pl:
+#   "Parallelization in Kaldi": http://kaldi-asr.org/doc/queue.html
+# =========================================================~
+
+
+# Select the backend used by run.sh from "local", "stdout", "sge", "slurm", or "ssh"
+cmd_backend='local'
+
+# Local machine, without any Job scheduling system
+if [ "${cmd_backend}" = local ]; then
+
+    # The other usage
+    export train_cmd="run.pl"
+    # Used for "*_train.py": "--gpu" is appended optionally by run.sh
+    export cuda_cmd="run.pl"
+    # Used for "*_recog.py"
+    export decode_cmd="run.pl"
+
+# Local machine logging to stdout and log file, without any Job scheduling system
+elif [ "${cmd_backend}" = stdout ]; then
+
+    # The other usage
+    export train_cmd="stdout.pl"
+    # Used for "*_train.py": "--gpu" is appended optionally by run.sh
+    export cuda_cmd="stdout.pl"
+    # Used for "*_recog.py"
+    export decode_cmd="stdout.pl"
+
+
+# "qsub" (Sun Grid Engine, or derivation of it)
+elif [ "${cmd_backend}" = sge ]; then
+    # The default setting is written in conf/queue.conf.
+    # You must change "-q g.q" for the "queue" for your environment.
+    # To know the "queue" names, type "qhost -q"
+    # Note that to use "--gpu *", you have to setup "complex_value" for the system scheduler.
+
+    export train_cmd="queue.pl"
+    export cuda_cmd="queue.pl"
+    export decode_cmd="queue.pl"
+
+
+# "qsub" (Torque/PBS.)
+elif [ "${cmd_backend}" = pbs ]; then
+    # The default setting is written in conf/pbs.conf.
+
+    export train_cmd="pbs.pl"
+    export cuda_cmd="pbs.pl"
+    export decode_cmd="pbs.pl"
+
+
+# "sbatch" (Slurm)
+elif [ "${cmd_backend}" = slurm ]; then
+    # The default setting is written in conf/slurm.conf.
+    # You must change "-p cpu" and "-p gpu" for the "partition" for your environment.
+    # To know the "partion" names, type "sinfo".
+    # You can use "--gpu * " by default for slurm and it is interpreted as "--gres gpu:*"
+    # The devices are allocated exclusively using "${CUDA_VISIBLE_DEVICES}".
+
+    export train_cmd="slurm.pl"
+    export cuda_cmd="slurm.pl"
+    export decode_cmd="slurm.pl"
+
+elif [ "${cmd_backend}" = ssh ]; then
+    # You have to create ".queue/machines" to specify the host to execute jobs.
+    # e.g. .queue/machines
+    #   host1
+    #   host2
+    #   host3
+    # Assuming you can login them without any password, i.e. You have to set ssh keys.
+
+    export train_cmd="ssh.pl"
+    export cuda_cmd="ssh.pl"
+    export decode_cmd="ssh.pl"
+
+# This is an example of specifying several unique options in the JHU CLSP cluster setup.
+# Users can modify/add their own command options according to their cluster environments.
+elif [ "${cmd_backend}" = jhu ]; then
+
+    export train_cmd="queue.pl --mem 2G"
+    export cuda_cmd="queue-freegpu.pl --mem 2G --gpu 1 --config conf/queue.conf"
+    export decode_cmd="queue.pl --mem 4G"
+
+else
+    echo "$0: Error: Unknown cmd_backend=${cmd_backend}" 1>&2
+    return 1
+fi

egs2/TEMPLATE/tts2/conf/mfcc.conf

@@ -0,0 +1,7 @@
+--sample-frequency=16000
+--frame-length=25 # the default is 25
+--low-freq=20 # the default.
+--high-freq=7600 # the default is zero meaning use the Nyquist (8k in this case).
+--num-mel-bins=30
+--num-ceps=30
+--snip-edges=false

egs2/TEMPLATE/tts2/conf/pbs.conf

@@ -0,0 +1,11 @@
+# Default configuration
+command qsub -V -v PATH -S /bin/bash
+option name=* -N $0
+option mem=* -l mem=$0
+option mem=0          # Do not add anything to qsub_opts
+option num_threads=* -l ncpus=$0
+option num_threads=1  # Do not add anything to qsub_opts
+option num_nodes=* -l nodes=$0:ppn=1
+default gpu=0
+option gpu=0
+option gpu=* -l ngpus=$0

egs2/TEMPLATE/tts2/conf/queue.conf

@@ -0,0 +1,12 @@
+# Default configuration
+command qsub -v PATH -cwd -S /bin/bash -j y -l arch=*64*
+option name=* -N $0
+option mem=* -l mem_free=$0,ram_free=$0
+option mem=0          # Do not add anything to qsub_opts
+option num_threads=* -pe smp $0
+option num_threads=1  # Do not add anything to qsub_opts
+option max_jobs_run=* -tc $0
+option num_nodes=* -pe mpi $0  # You must set this PE as allocation_rule=1
+default gpu=0
+option gpu=0
+option gpu=* -l gpu=$0 -q g.q

egs2/TEMPLATE/tts2/conf/slurm.conf

@@ -0,0 +1,14 @@
+# Default configuration
+command sbatch --export=PATH
+option name=* --job-name $0
+option time=* --time $0
+option mem=* --mem-per-cpu $0
+option mem=0
+option num_threads=* --cpus-per-task $0
+option num_threads=1 --cpus-per-task 1
+option num_nodes=* --nodes $0
+default gpu=0
+option gpu=0 -p cpu
+option gpu=* -p gpu --gres=gpu:$0 -c $0  # Recommend allocating more CPU than, or equal to the number of GPU
+# note: the --max-jobs-run option is supported as a special case
+# by slurm.pl and you don't have to handle it in the config file.

egs2/TEMPLATE/tts2/conf/vad.conf

@@ -0,0 +1,4 @@
+--vad-energy-threshold=5.5
+--vad-energy-mean-scale=0.5
+--vad-proportion-threshold=0.12
+--vad-frames-context=2

egs2/TEMPLATE/tts2/db.sh

@@ -0,0 +1 @@
+../asr1/db.sh

egs2/TEMPLATE/tts2/path.sh

@@ -0,0 +1,23 @@
+MAIN_ROOT=$PWD/../../..
+
+export PATH=$PWD/utils/:$PATH
+export LC_ALL=C
+
+if [ -f "${MAIN_ROOT}"/tools/activate_python.sh ]; then
+    . "${MAIN_ROOT}"/tools/activate_python.sh
+else
+    echo "[INFO] "${MAIN_ROOT}"/tools/activate_python.sh is not present"
+fi
+. "${MAIN_ROOT}"/tools/extra_path.sh
+
+export OMP_NUM_THREADS=1
+
+# NOTE(kan-bayashi): Use UTF-8 in Python to avoid UnicodeDecodeError when LC_ALL=C
+export PYTHONIOENCODING=UTF-8
+
+# You need to change or unset NCCL_SOCKET_IFNAME according to your network environment
+# https://docs.nvidia.com/deeplearning/sdk/nccl-developer-guide/docs/env.html#nccl-socket-ifname
+export NCCL_SOCKET_IFNAME="^lo,docker,virbr,vmnet,vboxnet"
+
+# NOTE(kamo): Source at the last to overwrite the setting
+. local/path.sh

egs2/TEMPLATE/tts2/pyscripts

@@ -0,0 +1 @@
+../../TEMPLATE/asr1/pyscripts

egs2/TEMPLATE/tts2/scripts

@@ -0,0 +1 @@
+../../TEMPLATE/asr1/scripts

egs2/TEMPLATE/tts2/setup.sh

@@ -0,0 +1,58 @@
+#!/usr/bin/env bash
+# Set bash to 'debug' mode, it will exit on :
+# -e 'error', -u 'undefined variable', -o ... 'error in pipeline', -x 'print commands',
+set -e
+set -u
+set -o pipefail
+
+log() {
+    local fname=${BASH_SOURCE[1]##*/}
+    echo -e "$(date '+%Y-%m-%dT%H:%M:%S') (${fname}:${BASH_LINENO[0]}:${FUNCNAME[1]}) $*"
+}
+help_message=$(cat << EOF
+Usage: $0 <target-dir>
+EOF
+)
+
+
+if [ $# -ne 1 ]; then
+    log "${help_message}"
+    log "Error: 1 positional argument is required."
+    exit 2
+fi
+
+
+dir=$1
+mkdir -p "${dir}"
+
+if [ ! -d "${dir}"/../../TEMPLATE ]; then
+    log "Error: ${dir}/../../TEMPLATE should exist. You may specify wrong directory."
+    exit 1
+fi
+
+targets=""
+
+# Copy
+for f in cmd.sh conf local; do
+    target="${dir}"/../../TEMPLATE/tts2/"${f}"
+    cp -r "${target}" "${dir}"
+    targets+="${dir}/${target} "
+done
+
+
+# Symlinks to TEMPLATE/tts2
+for f in tts2.sh path.sh sid; do
+    target=../../TEMPLATE/tts2/"${f}"
+    ln -sf "${target}" "${dir}"
+    targets+="${dir}/${target} "
+done
+
+
+# Symlinks to TEMPLATE/asr1
+for f in db.sh scripts pyscripts utils steps; do
+    target=../../TEMPLATE/asr1/"${f}"
+    ln -sf "${target}" "${dir}"
+    targets+="${dir}/${target} "
+done
+
+log "Created: ${targets}"

egs2/TEMPLATE/tts2/sid/README.md

@@ -0,0 +1 @@
+The scripts in this directory were copied from Kaldi-ASR, https://github.com/kaldi-asr/kaldi, and their licenses follow the original license, https://github.com/kaldi-asr/kaldi/blob/master/COPYING, of Kaldi.

egs2/TEMPLATE/tts2/sid/compute_vad_decision.sh

@@ -0,0 +1,86 @@
+#!/bin/bash
+
+# Copyright    2017  Vimal Manohar
+# Apache 2.0
+
+# To be run from .. (one directory up from here)
+# see ../run.sh for example
+
+# Compute energy based VAD output
+
+nj=4
+cmd=run.pl
+vad_config=conf/vad.conf
+
+echo "$0 $@"  # Print the command line for logging
+
+if [ -f path.sh ]; then . ./path.sh; fi
+. parse_options.sh || exit 1;
+
+if [ $# -lt 1 ] || [ $# -gt 3 ]; then
+   echo "Usage: $0 [options] <data-dir> [<log-dir> [<vad-dir>]]";
+   echo "e.g.: $0 data/train exp/make_vad mfcc"
+   echo "Note: <log-dir> defaults to <data-dir>/log, and <vad-dir> defaults to <data-dir>/data"
+   echo " Options:"
+   echo "  --vad-config <config-file>                       # config passed to compute-vad-energy"
+   echo "  --nj <nj>                                        # number of parallel jobs"
+   echo "  --cmd (utils/run.pl|utils/queue.pl <queue opts>) # how to run jobs."
+   exit 1;
+fi
+
+data=$1
+if [ $# -ge 2 ]; then
+  logdir=$2
+else
+  logdir=$data/log
+fi
+if [ $# -ge 3 ]; then
+  vaddir=$3
+else
+  vaddir=$data/data
+fi
+
+
+# make $vaddir an absolute pathname.
+vaddir=`perl -e '($dir,$pwd)= @ARGV; if($dir!~m:^/:) { $dir = "$pwd/$dir"; } print $dir; ' $vaddir ${PWD}`
+
+# use "name" as part of name of the archive.
+name=`basename $data`
+
+mkdir -p $vaddir || exit 1;
+mkdir -p $logdir || exit 1;
+
+if [ -f $data/vad.scp ]; then
+  mkdir -p $data/.backup
+  echo "$0: moving $data/vad.scp to $data/.backup"
+  mv $data/vad.scp $data/.backup
+fi
+
+for f in $data/feats.scp "$vad_config"; do
+  if [ ! -f $f ]; then
+    echo "compute_vad_decision.sh: no such file $f"
+    exit 1;
+  fi
+done
+
+utils/split_data.sh $data $nj || exit 1;
+sdata=$data/split$nj;
+
+$cmd JOB=1:$nj $logdir/vad_${name}.JOB.log \
+  compute-vad --config=$vad_config scp:$sdata/JOB/feats.scp \
+  ark,scp:$vaddir/vad_${name}.JOB.ark,$vaddir/vad_${name}.JOB.scp || exit 1
+
+for ((n=1; n<=nj; n++)); do
+  cat $vaddir/vad_${name}.$n.scp || exit 1;
+done > $data/vad.scp
+
+nc=`cat $data/vad.scp | wc -l`
+nu=`cat $data/feats.scp | wc -l`
+if [ $nc -ne $nu ]; then
+  echo "**Warning it seems not all of the speakers got VAD output ($nc != $nu);"
+  echo "**validate_data_dir.sh will fail; you might want to use fix_data_dir.sh"
+  [ $nc -eq 0 ] && exit 1;
+fi
+
+
+echo "Created VAD output for $name"