kaldi 学习笔记1

# 指定bash
#!/bin/bash

# 包含文件
. ./path.sh || exit 1
. ./cmd.sh || exit 1

# 配置
nj=1       # number of parallel jobs - 1 is perfect for such a small dataset
lm_order=1 # language model order (n-gram quantity) - 1 is enough for digits grammar

# 安全检查
. utils/parse_options.sh || exit 1
[[ $# -ge 1 ]] && { echo "Wrong arguments!"; exit 1; }

# 去除历史文件
rm -rf exp mfcc data/train/spk2utt data/train/cmvn.scp data/train/feats.scp data/train/split1 data/test/spk2utt data/test/cmvn.scp data/test/feats.scp data/test/split1 data/local/lang data/lang data/local/tmp data/local/dict/lexiconp.txt

## 1.准备声学数据
# spk2gender  [ ]
# wav.scp     [ ]
# text        [ ]
# utt2spk     [ ]
# corpus.txt  []

# 生成spk2utt
utils/utt2spk_to_spk2utt.pl data/train/utt2spk > data/train/spk2utt
utils/utt2spk_to_spk2utt.pl data/test/utt2spk > data/test/spk2utt

## 2.特征提取
# 检测数据合法性
mfccdir=mfcc
utils/validate_data_dir.sh data/train     # script for checking prepared data - here: for data/train directory
utils/fix_data_dir.sh data/train          # tool for data proper sorting if needed - here: for data/train directory
utils/validate_data_dir.sh data/test
utils/fix_data_dir.sh data/test

# 提取特征
# feats.scp是在提取特征中产生的，cmvn.scp是对提取的特征做进一步处理产生的文件
steps/make_mfcc.sh --nj $nj --cmd "$train_cmd" data/train exp/make_mfcc/train $mfccdir
steps/make_mfcc.sh --nj $nj --cmd "$train_cmd" data/test exp/make_mfcc/test $mfccdir
# 生成cmvn.scp
steps/compute_cmvn_stats.sh data/train exp/make_mfcc/train $mfccdir
steps/compute_cmvn_stats.sh data/test exp/make_mfcc/test $mfccdir

## 2.准备语言数据
# lexicon.txt           [   ...]
# nonsilence_phones.txt []
# silence_phones.txt    []
# optional_silence.txt  []

# 准备语言数据
utils/prepare_lang.sh data/local/dict "" data/local/lang data/lang

## 3.建立语言模型
# 生成 lm.arpa
loc=`which ngram-count`;
if [ -z $loc ]; then
        if uname -a | grep 64 >/dev/null; then
                sdir=$KALDI_ROOT/tools/srilm/bin/i686-m64
        else
                        sdir=$KALDI_ROOT/tools/srilm/bin/i686
        fi
        if [ -f $sdir/ngram-count ]; then
                        echo "Using SRILM language modelling tool from $sdir"
                        export PATH=$PATH:$sdir
        else
                        echo "SRILM toolkit is probably not installed.
                                Instructions: tools/install_srilm.sh"
                        exit 1
        fi
fi

local=data/local
mkdir $local/tmp
ngram-count -order $lm_order -write-vocab $local/tmp/vocab-full.txt -wbdiscount -text $local/corpus.txt -lm $local/tmp/lm.arpa

# 生成G.fst
lang=data/lang
arpa2fst --disambig-symbol=#0 --read-symbol-table=$lang/words.txt $local/tmp/lm.arpa $lang/G.fst

# 单音素训练
steps/train_mono.sh --nj $nj --cmd "$train_cmd" data/train data/lang exp/mono  || exit 1

# 单音素解码
utils/mkgraph.sh --mono data/lang exp/mono exp/mono/graph || exit 1
steps/decode.sh --config conf/decode.config --nj $nj --cmd "$decode_cmd" exp/mono/graph data/test exp/mono/decode

# 单音素对齐
steps/align_si.sh --nj $nj --cmd "$train_cmd" data/train data/lang exp/mono exp/mono_ali || exit 1

# TRI1 (first triphone pass) TRAINING
steps/train_deltas.sh --cmd "$train_cmd" 2000 11000 data/train data/lang exp/mono_ali exp/tri1 || exit 1

# TRI1 (first triphone pass) DECODING
utils/mkgraph.sh data/lang exp/tri1 exp/tri1/graph || exit 1
steps/decode.sh --config conf/decode.config --nj $nj --cmd "$decode_cmd" exp/tri1/graph data/test exp/tri1/decode