#!/bin/bash

# Copyright 2012 Vassil Panayotov

# Apache 2.0

# Note: you have to do 'make ext' in ../../../src/ before running this.

# Set the paths to the binaries and scripts needed

KALDI_ROOT=`pwd`/../../..

export PATH=$PWD/../s5/utils/:$KALDI_ROOT/src/onlinebin:$KALDI_ROOT/src/bin:$PATH

data_file="online-data"

data_url="http://sourceforge.net/projects/kaldi/files/online-data.tar.bz2"

# Change this to "tri2a" if you like to test using a ML-trained model

ac_model_type=tri2b_mmi

# Alignments and decoding results are saved in this directory(simulated decoding only)

decode_dir="./work"

# Change this to "live" either here or using command line switch like:

# --test-mode live

test_mode="simulated"

. parse_options.sh

ac_model=${data_file}/models/$ac_model_type

trans_matrix=""

audio=${data_file}/audio

if [ ! -s ${data_file}.tar.bz2 ]; then   #下载语音数据，用于仿真测试用

    echo "Downloading test models and data ..."

    wget -T 10 -t 3 $data_url;

    if [ ! -s ${data_file}.tar.bz2 ]; then

        echo "Download of $data_file has failed!"

        exit 1

    fi

fi

if [ ! -d $ac_model ]; then   #验证模型是否存在

    echo "Extracting the models and data ..."

    tar xf ${data_file}.tar.bz2

fi

if [ -s $ac_model/matrix ]; then   #设置转移矩阵

    trans_matrix=$ac_model/matrix

fi

case $test_mode in

    live)#实时在线解码模式

        echo

        echo -e "  LIVE DEMO MODE - you can use a microphone and say something\n"

        echo "  The (bigram) language model used to build the decoding graph was"

        echo "  estimated on an audio book's text. The text in question is"

        echo "  \"King Solomon's Mines\" (http://www.gutenberg.org/ebooks/2166)."

        echo "  You may want to read some sentences from this book first ..."

        echo

        online-gmm-decode-faster --rt-min=0.5 --rt-max=0.7 --max-active=4000 \

           --beam=12.0 --acoustic-scale=0.0769 $ac_model/model $ac_model/HCLG.fst \

           $ac_model/words.txt '1:2:3:4:5' $trans_matrix;;

    simulated)#离线文件识别

        echo

        echo -e "  SIMULATED ONLINE DECODING - pre-recorded audio is used\n"

        echo "  The (bigram) language model used to build the decoding graph was"

        echo "  estimated on an audio book's text. The text in question is"

        echo "  \"King Solomon's Mines\" (http://www.gutenberg.org/ebooks/2166)."

        echo "  The audio chunks to be decoded were taken from the audio book read"

        echo "  by John Nicholson(http://librivox.org/king-solomons-mines-by-haggard/)"

        echo

        echo "  NOTE: Using utterances from the book, on which the LM was estimated"

        echo "        is considered to be \"cheating\" and we are doing this only for"

        echo "        the purposes of the demo."

        echo

        echo "  You can type \"./run.sh --test-mode live\" to try it using your"

        echo "  own voice!"

        echo

        mkdir -p $decode_dir

        # make an input .scp file

        > $decode_dir/input.scp

        for f in $audio/*.wav; do

            bf=`basename $f`

            bf=${bf%.wav}

            echo $bf $f >> $decode_dir/input.scp

        done

        online-wav-gmm-decode-faster --verbose=1 --rt-min=0.8 --rt-max=0.85\

            --max-active=4000 --beam=12.0 --acoustic-scale=0.0769 \

            scp:$decode_dir/input.scp $ac_model/model $ac_model/HCLG.fst \

            $ac_model/words.txt '1:2:3:4:5' ark,t:$decode_dir/trans.txt \

            ark,t:$decode_dir/ali.txt $trans_matrix;;# ali.txt记录对齐的状态与帧之间关系   trans.txt记录解码结果的数字

    *)

        echo "Invalid test mode! Should be either \"live\" or \"simulated\"!";

        exit 1;;

esac

# Estimate the error rate for the simulated decoding

if [ $test_mode == "simulated" ]; then

    # Convert the reference transcripts from symbols to word IDs

    sym2int.pl -f 2- $ac_model/words.txt < $audio/trans.txt > $decode_dir/ref.txt #结合words.txt将trans.txt标记参考文本符号  转成   int符号

    # Compact the hypotheses belonging to the same test utterance

    cat $decode_dir/trans.txt |\

        sed -e 's/^\(test[0-9]\+\)\([^ ]\+\)\(.*\)/\1 \3/' |\

        gawk '{key=$1; $1=""; arr[key]=arr[key] " " $0; } END { for (k in arr) { print k " " arr[k]} }' > $decode_dir/hyp.txt
    #将trans.txt变成类似ref.txt的格式，便于对比分析

   # Finally compute WER

   compute-wer --mode=present ark,t:$decode_dir/ref.txt ark,t:$decode_dir/hyp.txt  #将ref.txt与hyp.txt做对比，计算wer率

fi

Usage: online-gmm-decode-faster [options] <model-in><fst-in> <word-symbol-table> <silence-phones> [<lda-matrix-in>]
                                          #模型      fst状态机      词符号表          静音音素          lda-矩阵

Example: online-gmm-decode-faster --rt-min=0.3 --rt-max=0.5 --max-active=4000 --beam=12.0 --acoustic-scale=0.0769 model HCLG.fst words.txt '1:2:3:4:5' lda-matrix

Options:

  --acoustic-scale            : Scaling factor for acoustic likelihoods (float, default = 0.1)      声学似然度 伸缩系数

  --batch-size                : Number of feature vectors processed w/o interruption (int, default = 27)  特征矢量batch数目设定

  --beam                      : Decoding beam.  Larger->slower, more accurate. (float, default = 16)     解码beam，beam越大，则越慢，越精确

  --beam-delta                : Increment used in decoder [obscure setting] (float, default = 0.5)   解码器中的增量

  --beam-update               : Beam update rate (float, default = 0.01)  beam更新速率

  --cmn-window                : Number of feat. vectors used in the running average CMN calculation (int, default = 600)   cmn的窗，决定了feat的数目

  --delta-order               : Order of delta computation (int, default = 2)  delta的阶数

  --delta-window              : Parameter controlling window for delta computation (actual window size for each delta order is 1 + 2*delta-window-size) (int, default = 2) #delta控制窗

  --hash-ratio                : Setting used in decoder to control hash behavior (float, default = 2) 解码器中控制hash的设置

  --inter-utt-sil             : Maximum # of silence frames to trigger new utterance (int, default = 50)  #slience最大帧数，超过这个就会激活新的发音

  --left-context              : Number of frames of left context (int, default = 4)#左边上下文的帧数

  --max-active                : Decoder max active states.  Larger->slower; more accurate (int, default = 2147483647) #解码器最大的有效状态，  越大，则越慢，越准确

  --max-beam-update           : Max beam update rate (float, default = 0.05) #最大的beam的更新率

  --max-utt-length            : If the utterance becomes longer than this number of frames, shorter silence is acceptable as an utterance separator (int, default = 1500)#如果发音超过这个帧数，短时静音是可接受的，作为分割符

  --min-active                : Decoder min active states (don't prune if #active less than this). (int, default = 20)#解码器的最小有效状态

  --min-cmn-window            : Minumum CMN window used at start of decoding (adds latency only at start) (int, default = 100) #最小CMN窗

  --num-tries                 : Number of successive repetitions of timeout before we terminate stream (int, default = 5)#再我们终止流时，超时连续重复的数目

  --right-context             : Number of frames of right context (int, default = 4) #右上下文帧数

  --rt-max                    : Approximate maximum decoding run time factor (float, default = 0.75)#近似最大解码动态时间系数

  --rt-min                    : Approximate minimum decoding run time factor (float, default = 0.7)#

  --update-interval           : Beam update interval in frames (int, default = 3)#beam更新间隔

Standard options:

  --config                    : Configuration file to read (this option may be repeated) (string, default = "")

  --help                      : Print out usage message (bool, default = false)

  --print-args                : Print the command line arguments (to stderr) (bool, default = true)

  --verbose                   : Verbose level (higher->more logging) (int, default = 0)