Dev bat (#701)

aky15

2023-07-04 3360a1d9453ef0ce441cc41b0090d09b3bb296bb

Dev bat (#701)

* boundary aware transducer

* resolve conflict

* delete type check

* add bat egs and results

---------

Co-authored-by: aky15 <ankeyu.aky@11.17.44.249>

 egs/aishell/bat/README.md

New file
@@ -0,0 +1,16 @@
# Boundary Aware Transducer (BAT) Result

## Training Config
- 8 gpu(Tesla V100)
- Feature info: using 80 dims fbank, global cmvn, speed perturb(0.9, 1.0, 1.1), specaugment
- Train config: conf/train_conformer_bat.yaml
- LM config: LM was not used
- Model size: 90M

## Results (CER)
- Decode config: conf/decode_bat_conformer.yaml

|   testset   |  CER(%) |
|:-----------:|:-------:|
|     dev     |  4.56   |
|    test     |  4.97   |

 egs/aishell/bat/conf/decode_bat_conformer.yaml

New file
@@ -0,0 +1 @@
beam_size: 10

 egs/aishell/bat/conf/train_conformer_bat.yaml

New file
@@ -0,0 +1,108 @@
encoder: chunk_conformer
encoder_conf:
      activation_type: swish
      positional_dropout_rate: 0.5
      time_reduction_factor: 2
      embed_vgg_like: false
      subsampling_factor: 4
      linear_units: 2048
      output_size: 512
      attention_heads: 8
      dropout_rate: 0.5
      positional_dropout_rate: 0.5
      attention_dropout_rate: 0.5
      cnn_module_kernel: 15
      num_blocks: 12    

# decoder related
rnnt_decoder: rnnt
rnnt_decoder_conf:
    embed_size: 512
    hidden_size: 512
    embed_dropout_rate: 0.5
    dropout_rate: 0.5
    use_embed_mask: true

predictor: bat_predictor
predictor_conf:
  idim: 512
  threshold: 1.0
  l_order: 1
  r_order: 1
  return_accum: true

joint_network_conf:
    joint_space_size: 512

# frontend related
frontend: wav_frontend
frontend_conf:
    fs: 16000
    window: hamming
    n_mels: 80
    frame_length: 25
    frame_shift: 10
    lfr_m: 1
    lfr_n: 1


# Auxiliary CTC
model: bat
model_conf:
    auxiliary_ctc_weight: 0.0
    cif_weight: 1.0
    r_d: 3
    r_u: 5

# minibatch related
use_amp: true

# optimization related
accum_grad: 1
grad_clip: 5
max_epoch: 100
val_scheduler_criterion:
    - valid
    - loss
best_model_criterion:
-   - valid
    - cer_transducer
    - min
keep_nbest_models: 10

optim: adam
optim_conf:
   lr: 0.001
scheduler: warmuplr
scheduler_conf:
   warmup_steps: 25000

specaug: specaug
specaug_conf:
    apply_time_warp: true
    time_warp_window: 5
    time_warp_mode: bicubic
    apply_freq_mask: true
    freq_mask_width_range:
    - 0
    - 40
    num_freq_mask: 2
    apply_time_mask: true
    time_mask_width_range:
    - 0
    - 50
    num_time_mask: 5

dataset_conf:
    data_names: speech,text
    data_types: sound,text
    shuffle: True
    shuffle_conf:
        shuffle_size: 2048
        sort_size: 500
    batch_conf:
        batch_type: token
        batch_size: 25000
    num_workers: 8

log_interval: 50

 egs/aishell/bat/local/aishell_data_prep.sh

New file
@@ -0,0 +1,66 @@
#!/bin/bash

# Copyright 2017 Xingyu Na
# Apache 2.0

#. ./path.sh || exit 1;

if [ $# != 3 ]; then
  echo "Usage: $0 <audio-path> <text-path> <output-path>"
  echo " $0 /export/a05/xna/data/data_aishell/wav /export/a05/xna/data/data_aishell/transcript data"
  exit 1;
fi

aishell_audio_dir=$1
aishell_text=$2/aishell_transcript_v0.8.txt
output_dir=$3

train_dir=$output_dir/data/local/train
dev_dir=$output_dir/data/local/dev
test_dir=$output_dir/data/local/test
tmp_dir=$output_dir/data/local/tmp

mkdir -p $train_dir
mkdir -p $dev_dir
mkdir -p $test_dir
mkdir -p $tmp_dir

# data directory check
if [ ! -d $aishell_audio_dir ] || [ ! -f $aishell_text ]; then
  echo "Error: $0 requires two directory arguments"
  exit 1;
fi

# find wav audio file for train, dev and test resp.
find $aishell_audio_dir -iname "*.wav" > $tmp_dir/wav.flist
n=`cat $tmp_dir/wav.flist | wc -l`
[ $n -ne 141925 ] && \
  echo Warning: expected 141925 data data files, found $n

grep -i "wav/train" $tmp_dir/wav.flist > $train_dir/wav.flist || exit 1;
grep -i "wav/dev" $tmp_dir/wav.flist > $dev_dir/wav.flist || exit 1;
grep -i "wav/test" $tmp_dir/wav.flist > $test_dir/wav.flist || exit 1;

rm -r $tmp_dir

# Transcriptions preparation
for dir in $train_dir $dev_dir $test_dir; do
  echo Preparing $dir transcriptions
  sed -e 's/\.wav//' $dir/wav.flist | awk -F '/' '{print $NF}' > $dir/utt.list
  paste -d' ' $dir/utt.list $dir/wav.flist > $dir/wav.scp_all
  utils/filter_scp.pl -f 1 $dir/utt.list $aishell_text > $dir/transcripts.txt
  awk '{print $1}' $dir/transcripts.txt > $dir/utt.list
  utils/filter_scp.pl -f 1 $dir/utt.list $dir/wav.scp_all | sort -u > $dir/wav.scp
  sort -u $dir/transcripts.txt > $dir/text
done

mkdir -p $output_dir/data/train $output_dir/data/dev $output_dir/data/test

for f in wav.scp text; do
  cp $train_dir/$f $output_dir/data/train/$f || exit 1;
  cp $dev_dir/$f $output_dir/data/dev/$f || exit 1;
  cp $test_dir/$f $output_dir/data/test/$f || exit 1;
done

echo "$0: AISHELL data preparation succeeded"
exit 0;

 egs/aishell/bat/path.sh

New file
@@ -0,0 +1,5 @@
export FUNASR_DIR=$PWD/../../..

# NOTE(kan-bayashi): Use UTF-8 in Python to avoid UnicodeDecodeError when LC_ALL=C
export PYTHONIOENCODING=UTF-8
export PATH=$FUNASR_DIR/funasr/bin:$PATH

 egs/aishell/bat/run.sh

New file
@@ -0,0 +1,210 @@
#!/usr/bin/env bash

. ./path.sh || exit 1;

# machines configuration
CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
gpu_num=8
count=1
gpu_inference=true  # Whether to perform gpu decoding, set false for cpu decoding
# for gpu decoding, inference_nj=ngpu*njob; for cpu decoding, inference_nj=njob
njob=5
train_cmd=utils/run.pl
infer_cmd=utils/run.pl

# general configuration
feats_dir="../DATA" #feature output dictionary
exp_dir="."
lang=zh
token_type=char
type=sound
scp=wav.scp
speed_perturb="0.9 1.0 1.1"
stage=0
stop_stage=5

# feature configuration
feats_dim=80
nj=64

# data
raw_data=../raw_data
data_url=www.openslr.org/resources/33

# exp tag
tag="exp1"

. utils/parse_options.sh || exit 1;

# Set bash to 'debug' mode, it will exit on :
# -e 'error', -u 'undefined variable', -o ... 'error in pipeline', -x 'print commands',
set -e
set -u
set -o pipefail

train_set=train
valid_set=dev
test_sets="dev test"

asr_config=conf/train_conformer_bat.yaml
model_dir="baseline_$(basename "${asr_config}" .yaml)_${lang}_${token_type}_${tag}"

inference_config=conf/decode_bat_conformer.yaml
inference_asr_model=valid.cer_transducer.ave_10best.pb

# you can set gpu num for decoding here
gpuid_list=$CUDA_VISIBLE_DEVICES  # set gpus for decoding, the same as training stage by default
ngpu=$(echo $gpuid_list | awk -F "," '{print NF}')

if ${gpu_inference}; then
    inference_nj=$[${ngpu}*${njob}]
    _ngpu=1
else
    inference_nj=$njob
    _ngpu=0
fi

if [ ${stage} -le -1 ] && [ ${stop_stage} -ge -1 ]; then
    echo "stage -1: Data Download"
    local/download_and_untar.sh ${raw_data} ${data_url} data_aishell
    local/download_and_untar.sh ${raw_data} ${data_url} resource_aishell
fi

if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
    echo "stage 0: Data preparation"
    # Data preparation
    local/aishell_data_prep.sh ${raw_data}/data_aishell/wav ${raw_data}/data_aishell/transcript ${feats_dir}
    for x in train dev test; do
        cp ${feats_dir}/data/${x}/text ${feats_dir}/data/${x}/text.org
        paste -d " " <(cut -f 1 -d" " ${feats_dir}/data/${x}/text.org) <(cut -f 2- -d" " ${feats_dir}/data/${x}/text.org | tr -d " ") \
            > ${feats_dir}/data/${x}/text
        utils/text2token.py -n 1 -s 1 ${feats_dir}/data/${x}/text > ${feats_dir}/data/${x}/text.org
        mv ${feats_dir}/data/${x}/text.org ${feats_dir}/data/${x}/text
    done
fi

if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
    echo "stage 1: Feature and CMVN Generation"
    utils/compute_cmvn.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} ${feats_dir}/data/${train_set}
fi

token_list=${feats_dir}/data/${lang}_token_list/char/tokens.txt
echo "dictionary: ${token_list}"
if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
    echo "stage 2: Dictionary Preparation"
    mkdir -p ${feats_dir}/data/${lang}_token_list/char/

    echo "make a dictionary"
    echo "<blank>" > ${token_list}
    echo "<s>" >> ${token_list}
    echo "</s>" >> ${token_list}
    utils/text2token.py -s 1 -n 1 --space "" ${feats_dir}/data/$train_set/text | cut -f 2- -d" " | tr " " "\n" \
        | sort | uniq | grep -a -v -e '^\s*$' | awk '{print $0}' >> ${token_list}
    echo "<unk>" >> ${token_list}
fi

# LM Training Stage
world_size=$gpu_num  # run on one machine
if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
    echo "stage 3: LM Training"
fi

# ASR Training Stage
world_size=$gpu_num  # run on one machine
if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
    echo "stage 4: ASR Training"
    mkdir -p ${exp_dir}/exp/${model_dir}
    mkdir -p ${exp_dir}/exp/${model_dir}/log
    INIT_FILE=./ddp_init
    if [ -f $INIT_FILE ];then
        rm -f $INIT_FILE
    fi 
    init_method=file://$(readlink -f $INIT_FILE)
    echo "$0: init method is $init_method"
    for ((i = 0; i < $gpu_num; ++i)); do
        {
            rank=$i
            local_rank=$i
            gpu_id=$(echo $CUDA_VISIBLE_DEVICES | cut -d',' -f$[$i+1])
            train.py \
                --task_name asr \
                --gpu_id $gpu_id \
                --use_preprocessor true \
                --token_type char \
                --token_list $token_list \
                --data_dir ${feats_dir}/data \
                --train_set ${train_set} \
                --valid_set ${valid_set} \
                --data_file_names "wav.scp,text" \
                --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
                --speed_perturb ${speed_perturb} \
                --resume true \
                --output_dir ${exp_dir}/exp/${model_dir} \
                --config $asr_config \
                --ngpu $gpu_num \
                --num_worker_count $count \
                --dist_init_method $init_method \
                --dist_world_size $world_size \
                --dist_rank $rank \
                --local_rank $local_rank 1> ${exp_dir}/exp/${model_dir}/log/train.log.$i 2>&1
        } &
        done
        wait
fi

# Testing Stage
if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then
    echo "stage 5: Inference"
    for dset in ${test_sets}; do
        asr_exp=${exp_dir}/exp/${model_dir}
        inference_tag="$(basename "${inference_config}" .yaml)"
        _dir="${asr_exp}/${inference_tag}/${inference_asr_model}/${dset}"
        _logdir="${_dir}/logdir"
        if [ -d ${_dir} ]; then
            echo "${_dir} is already exists. if you want to decode again, please delete this dir first."
            exit 0
        fi
        mkdir -p "${_logdir}"
        _data="${feats_dir}/data/${dset}"
        key_file=${_data}/${scp}
        num_scp_file="$(<${key_file} wc -l)"
        _nj=$([ $inference_nj -le $num_scp_file ] && echo "$inference_nj" || echo "$num_scp_file")
        split_scps=
        for n in $(seq "${_nj}"); do
            split_scps+=" ${_logdir}/keys.${n}.scp"
        done
        # shellcheck disable=SC2086
        utils/split_scp.pl "${key_file}" ${split_scps}
        _opts=
        if [ -n "${inference_config}" ]; then
            _opts+="--config ${inference_config} "
        fi
        ${infer_cmd} --gpu "${_ngpu}" --max-jobs-run "${_nj}" JOB=1:"${_nj}" "${_logdir}"/asr_inference.JOB.log \
            python -m funasr.bin.asr_inference_launch \
                --batch_size 1 \
                --ngpu "${_ngpu}" \
                --njob ${njob} \
                --gpuid_list ${gpuid_list} \
                --data_path_and_name_and_type "${_data}/${scp},speech,${type}" \
                --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
                --key_file "${_logdir}"/keys.JOB.scp \
                --asr_train_config "${asr_exp}"/config.yaml \
                --asr_model_file "${asr_exp}"/"${inference_asr_model}" \
                --output_dir "${_logdir}"/output.JOB \
                --mode bat \
                ${_opts}

        for f in token token_int score text; do
            if [ -f "${_logdir}/output.1/1best_recog/${f}" ]; then
                for i in $(seq "${_nj}"); do
                    cat "${_logdir}/output.${i}/1best_recog/${f}"
                done | sort -k1 >"${_dir}/${f}"
            fi
        done
        python utils/proce_text.py ${_dir}/text ${_dir}/text.proc
        python utils/proce_text.py ${_data}/text ${_data}/text.proc
        python utils/compute_wer.py ${_data}/text.proc ${_dir}/text.proc ${_dir}/text.cer
        tail -n 3 ${_dir}/text.cer > ${_dir}/text.cer.txt
        cat ${_dir}/text.cer.txt
    done
fi

 egs/aishell/bat/utils

New file
@@ -0,0 +1 @@
../transformer/utils