download and unzip the dataset

egs/baker_zh/TTS/.gitignore

@@ -0,0 +1 @@
+path.sh

egs/baker_zh/TTS/prepare.sh

@@ -0,0 +1,66 @@
+#!/usr/bin/env bash
+
+# fix segmentation fault reported in https://github.com/k2-fsa/icefall/issues/674
+export PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python
+
+set -eou pipefail
+
+stage=-1
+stop_stage=100
+
+dl_dir=$PWD/download
+mkdir -p $dl_dir
+
+. shared/parse_options.sh || exit 1
+
+# All files generated by this script are saved in "data".
+# You can safely remove "data" and rerun this script to regenerate it.
+mkdir -p data
+
+log() {
+  # This function is from espnet
+  local fname=${BASH_SOURCE[1]##*/}
+  echo -e "$(date '+%Y-%m-%d %H:%M:%S') (${fname}:${BASH_LINENO[0]}:${FUNCNAME[1]}) $*"
+}
+
+log "dl_dir: $dl_dir"
+
+if [ $stage -le -1 ] && [ $stop_stage -ge -1 ]; then
+  log "Stage -1: build monotonic_align lib (used by ./matcha)"
+  for recipe in matcha; do
+    if [ ! -d $recipe/monotonic_align/build ]; then
+      cd $recipe/monotonic_align
+      python3 setup.py build_ext --inplace
+      cd ../../
+    else
+      log "monotonic_align lib for $recipe already built"
+    fi
+  done
+fi
+
+if [ $stage -le 0 ] && [ $stop_stage -ge 0 ]; then
+  log "Stage 0: Download data"
+
+  # The directory $dl_dir/BANSYP contains the following 3 directories
+
+  # ls -lh $dl_dir/BZNSYP/
+  # total 0
+  # drwxr-xr-x 10002 kuangfangjun root 0 Jan  4  2019 PhoneLabeling
+  # drwxr-xr-x     3 kuangfangjun root 0 Jan 31  2019 ProsodyLabeling
+  # drwxr-xr-x 10003 kuangfangjun root 0 Aug 26 17:45 Wave
+
+  # If you have trouble accessing huggingface.co, please use
+  #
+  # cd $dl_dir
+  # wget https://huggingface.co/openspeech/BZNSYP/resolve/main/BZNSYP.tar.bz2
+  # tar xf BZNSYP.tar.bz2
+  # cd ..
+
+  # If you have pre-downloaded it to /path/to/BZNSYP, you can create a symlink
+  #
+  #   ln -sfv /path/to/BZNSYP $dl_dir/BZNSYP
+  #
+  if [ ! -d $dl_dir/BZNSYP/Wave ]; then
+    lhotse download baker-zh $dl_dir
+  fi
+fi

egs/baker_zh/TTS/shared

@@ -0,0 +1 @@
+../../../icefall/shared