run_prep.sh

if [ $stage -le 21 ]; then
  # Create a version of the lang/ directory that has one state per phone in the
  # topo file. [note, it really has two states.. the first one is only repeated
  # once, the second one has zero or more repeats.]
  if [ -d data/lang_chain ]; then
    if [ data/lang_chain/L.fst -nt data/lang_train/L.fst ]; then
      echo "$0: data/lang_chain already exists, not overwriting it; continuing"
    else
      echo "$0: data/lang_chain already exists and seems to be older than data/lang_train..."
      echo " ... not sure what to do. Exiting."
      exit 1;
    fi
  else
    cp -r data/lang_train data/lang_chain
    silphonelist=$(cat data/lang_chain/phones/silence.csl) || exit 1;
    nonsilphonelist=$(cat data/lang_chain/phones/nonsilence.csl) || exit 1;
    # Use our special topology... note that later on may have to tune this
    # topology.
    steps/nnet3/chain/gen_topo.py $nonsilphonelist $silphonelist >data/lang_chain/topo
  fi
fi

if [ $stage -le 22 ]; then
  local/chain/build_new_tree.sh exp/chain/tree
fi

if [ $stage -le 23 ]; then
  srun --mem 24G --time 1-12:0:0 -c8 \
    local/chain/make_shards.py 100 shards/train_960 \
      --num-proc 8 \
      --wavscp data/train_960/split100/JOB/wav.scp \
      --text data/train_960/split100/JOB/text \
      --aliark "gunzip -c exp/chain/tree/ali.JOB.gz | ali-to-pdf exp/chain/tree/final.mdl ark:- ark:- |"

  srun --mem 6G --time 12:0:0 -c2 \
    local/chain/make_shards.py 8 shards/dev_all \
      --num-proc 2 \
      --wavscp data/dev_all/split8/JOB/wav.scp \
      --text data/dev_all/split8/JOB/text \
      --aliark "gunzip -c exp/chain/tree/ali.valid.JOB.gz | ali-to-pdf exp/chain/tree/final.mdl ark:- ark:- |"
fi