run_nnet2_common.sh 3.75 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96
#!/bin/bash

# this script contains some common (shared) parts of the run_nnet*.sh scripts.

. cmd.sh


stage=0
mic=ihm
num_threads_ubm=32

set -e
. cmd.sh
. ./path.sh
. ./utils/parse_options.sh


if [ $stage -le 1 ]; then
  # Create high-resolution MFCC features (with 40 cepstra instead of 13).
  # this shows how you can split across multiple file-systems.  we'll split the
  # MFCC dir across multiple locations.  You might want to be careful here, if you
  # have multiple copies of Kaldi checked out and run the same recipe, not to let
  # them overwrite each other.
  mfccdir=mfcc_${mic}_hires
  if [[ $(hostname -f) == *.clsp.jhu.edu ]] && [ ! -d $mfccdir/storage ]; then
    utils/create_split_dir.pl /export/b0{1,2,3,4}/$USER/kaldi-data/egs/ami-$mic-$(date +'%m_%d_%H_%M')/s5/$mfccdir/storage $mfccdir/storage
  fi

  for datadir in train dev eval; do
    utils/copy_data_dir.sh data/$mic/$datadir data/$mic/${datadir}_hires
    if [ "$datadir" == "train" ]; then
      dir=data/$mic/train_hires
      cat $dir/wav.scp | python -c "
import sys, os, subprocess, re, random
scale_low = 1.0/8
scale_high = 2.0
for line in sys.stdin.readlines():
  if len(line.strip()) == 0:
    continue
  print '{0} sox --vol {1} -t wav - -t wav - |'.format(line.strip(), random.uniform(scale_low, scale_high))
"| sort -k1,1 -u  > $dir/wav.scp_scaled || exit 1;
     mv $dir/wav.scp $dir/wav.scp_nonorm
     mv $dir/wav.scp_scaled $dir/wav.scp
    fi

    steps/make_mfcc.sh --nj 70 --mfcc-config conf/mfcc_hires.conf \
      --cmd "$train_cmd" data/$mic/${datadir}_hires exp/make_${mic}_hires/$datadir $mfccdir || exit 1;
    steps/compute_cmvn_stats.sh data/$mic/${datadir}_hires exp/make_${mic}_hires/$mic/$datadir $mfccdir || exit 1;
  done

fi

if [ $stage -le 2 ]; then
  # Train a system just for its LDA+MLLT transform.  We use --num-iters 13
  # because after we get the transform (12th iter is the last), any further
  # training is pointless.
  steps/train_lda_mllt.sh --cmd "$train_cmd" --num-iters 13 \
    --realign-iters "" \
    --splice-opts "--left-context=3 --right-context=3" \
    5000 10000 data/$mic/train_hires data/lang \
    exp/$mic/tri4a_ali exp/$mic/nnet2_online/tri5
fi


if [ $stage -le 3 ]; then
  mkdir -p exp/nnet2_online
  steps/online/nnet2/train_diag_ubm.sh --cmd "$train_cmd" --nj 30 --num-frames 700000 \
    --num-threads $num_threads_ubm \
    data/$mic/train_hires 512 exp/$mic/nnet2_online/tri5 exp/$mic/nnet2_online/diag_ubm
fi

if [ $stage -le 4 ]; then
  # iVector extractors can in general be sensitive to the amount of data, but
  # this one has a fairly small dim (defaults to 100)
  steps/online/nnet2/train_ivector_extractor.sh --cmd "$train_cmd" --nj 10 \
    data/$mic/train_hires exp/$mic/nnet2_online/diag_ubm exp/$mic/nnet2_online/extractor || exit 1;
fi

if [ $stage -le 5 ]; then
  ivectordir=exp/$mic/nnet2_online/ivectors_train_hires
  if [[ $(hostname -f) == *.clsp.jhu.edu ]] && [ ! -d $ivectordir/storage ]; then
    utils/create_split_dir.pl /export/b0{1,2,3,4}/$USER/kaldi-data/egs/ami-$mic-$(date +'%m_%d_%H_%M')/s5/$ivectordir/storage $ivectordir/storage
  fi
  # We extract iVectors on all the train data, which will be what we train the
  # system on.  With --utts-per-spk-max 2, the script.  pairs the utterances
  # into twos, and treats each of these pairs as one speaker.  Note that these
  # are extracted 'online'.

  # having a larger number of speakers is helpful for generalization, and to
  # handle per-utterance decoding well (iVector starts at zero).
  steps/online/nnet2/copy_data_dir.sh --utts-per-spk-max 2 data/$mic/train_hires data/$mic/train_hires_max2
  steps/online/nnet2/extract_ivectors_online.sh --cmd "$train_cmd" --nj 30 \
    data/$mic/train_hires_max2 exp/$mic/nnet2_online/extractor exp/$mic/nnet2_online/ivectors_train_hires || exit 1;
fi

exit 0;