update version 0.1.6

jmwang66

2023-01-16 ee8c98073234e13a70f9c406dff6c986c5f27fd2

update version 0.1.6

 egs/aishell/data2vec_finetune/conf/decode_asr_transformer.yaml

New file
@@ -0,0 +1,6 @@
beam_size: 10
penalty: 0.0
maxlenratio: 0.0
minlenratio: 0.0
ctc_weight: 1.0
lm_weight: 0.7

 egs/aishell/data2vec_finetune/conf/train_asr_transformer_12e_6d_3072_768.yaml

New file
@@ -0,0 +1,95 @@
# network architecture
# encoder related
encoder: data2vec_encoder
encoder_conf:
  extractor_mode: layer_norm
  encoder_layerdrop: 0.1
  dropout_input: 0.0
  dropout_features: 0.0
  feature_grad_mult: 0.0
  encoder_embed_dim: 768

  mask_prob: 0.65
  mask_length: 10

  loss_beta: 0
  loss_scale: null

  instance_norm_target_layer: true
  average_top_k_layers: 8

  pos_conv_depth: 5
  conv_pos: 95

  ema_decay: 0.999
  ema_end_decay: 0.9999
  ema_anneal_end_step: 30000
  ema_transformer_only: true
  ema_layers_only: true

  require_same_masks: true
  mask_dropout: 0

# hybrid CTC/attention
model_conf:
    ctc_weight: 1.0
    lsm_weight: 0.1     # label smoothing option
    length_normalized_loss: false

# for logger
log_interval: 50

# minibatch related
batch_type: length
batch_bins: 16000
num_workers: 16

# optimization related
accum_grad: 1
grad_clip: 5
patience: none
max_epoch: 50
val_scheduler_criterion:
    - valid
    - acc
best_model_criterion:
-   - valid
    - cer_ctc
    - min
keep_nbest_models: 10
unused_parameters: true
normalize: None

# NoamLR is deprecated. Use WarmupLR.
# The following is equivalent setting for NoamLR:
#
#    optim: adam
#    optim_conf:
#        lr: 10.
#    scheduler: noamlr
#    scheduler_conf:
#        model_size: 256
#        warmup_steps: 25000
#
optim: adam
optim_conf:
    lr: 0.00005
scheduler: warmuplr     # pytorch v1.1.0+ required
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
    - 30
    num_freq_mask: 2
    apply_time_mask: true
    time_mask_width_range:
    - 0
    - 40
    num_time_mask: 2

 egs/aishell/data2vec_finetune/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/data2vec_finetune/local/prepare_data.sh

New file
@@ -0,0 +1,53 @@
#!/usr/bin/env bash
# Copyright 2018 AIShell-Foundation(Authors:Jiayu DU, Xingyu NA, Bengu WU, Hao ZHENG)
#           2018 Beijing Shell Shell Tech. Co. Ltd. (Author: Hui BU)
# Apache 2.0

# transform raw AISHELL-2 data to kaldi format

. ./path.sh || exit 1;

tmp=
dir=

if [ $# != 3 ]; then
  echo "Usage: $0 <corpus-data-dir> <tmp-dir> <output-dir>"
  echo " $0 /export/AISHELL-2/iOS/train data/local/train data/train"
  exit 1;
fi

corpus=$1
tmp=$2
dir=$3

echo "prepare_data.sh: Preparing data in $corpus"

mkdir -p $tmp
mkdir -p $dir

# corpus check
if [ ! -d $corpus ] || [ ! -f $corpus/wav.scp ] || [ ! -f $corpus/trans.txt ]; then
  echo "Error: $0 requires wav.scp and trans.txt under $corpus directory."
  exit 1;
fi

# validate utt-key list, IC0803W0380 is a bad utterance
awk '{print $1}' $corpus/wav.scp | grep -v 'IC0803W0380' > $tmp/wav_utt.list
awk '{print $1}' $corpus/trans.txt > $tmp/trans_utt.list
utils/filter_scp.pl -f 1 $tmp/wav_utt.list $tmp/trans_utt.list > $tmp/utt.list

# wav.scp
awk -F'\t' -v path_prefix=$corpus '{printf("%s\t%s/%s\n",$1,path_prefix,$2)}' $corpus/wav.scp > $tmp/tmp_wav.scp
utils/filter_scp.pl -f 1 $tmp/utt.list $tmp/tmp_wav.scp | sort -k 1 | uniq > $tmp/wav.scp

# text
utils/filter_scp.pl -f 1 $tmp/utt.list $corpus/trans.txt | sort -k 1 | uniq > $tmp/text

# copy prepared resources from tmp_dir to target dir
mkdir -p $dir
for f in wav.scp text; do
  cp $tmp/$f $dir/$f || exit 1;
done

echo "local/prepare_data.sh succeeded"
exit 0;

 egs/aishell/data2vec_finetune/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/data2vec_finetune/run.sh

New file
@@ -0,0 +1,252 @@
#!/usr/bin/env bash

. ./path.sh || exit 1;

# machines configuration
CUDA_VISIBLE_DEVICES="0,1"
gpu_num=2
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, for large data
exp_dir="."
lang=zh
dumpdir=dump/fbank
feats_type=fbank
token_type=char
scp=feats.scp
type=kaldi_ark
stage=0
stop_stage=4

# feature configuration
feats_dim=80
sample_frequency=16000
nj=32
speed_perturb="0.9,1.0,1.1"

# data
data_aishell=

# exp tag
tag=""

model_name=damo/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch
init_param="$HOME/.cache/modelscope/hub/$model_name/basemodel.pb"

. 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_asr_transformer_12e_6d_3072_768.yaml
model_dir="baseline_$(basename "${asr_config}" .yaml)_${feats_type}_${lang}_${token_type}_${tag}"

inference_config=conf/decode_asr_transformer.yaml
inference_asr_model=valid.cer_ctc.ave_10best.pth

# 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 0 ] && [ ${stop_stage} -ge 0 ]; then
    echo "stage 0: Data preparation"
    # Data preparation
    local/aishell_data_prep.sh ${data_aishell}/data_aishell/wav ${data_aishell}/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

feat_train_dir=${feats_dir}/${dumpdir}/train; mkdir -p ${feat_train_dir}
feat_dev_dir=${feats_dir}/${dumpdir}/dev; mkdir -p ${feat_dev_dir}
feat_test_dir=${feats_dir}/${dumpdir}/test; mkdir -p ${feat_test_dir}
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
    echo "stage 1: Feature Generation"
    # compute fbank features
    fbankdir=${feats_dir}/fbank
    utils/compute_fbank.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --sample_frequency ${sample_frequency} --speed_perturb ${speed_perturb} \
        ${feats_dir}/data/train ${exp_dir}/exp/make_fbank/train ${fbankdir}/train
    utils/fix_data_feat.sh ${fbankdir}/train
    utils/compute_fbank.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --sample_frequency ${sample_frequency} \
        ${feats_dir}/data/dev ${exp_dir}/exp/make_fbank/dev ${fbankdir}/dev
    utils/fix_data_feat.sh ${fbankdir}/dev
    utils/compute_fbank.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --sample_frequency ${sample_frequency} \
        ${feats_dir}/data/test ${exp_dir}/exp/make_fbank/test ${fbankdir}/test
    utils/fix_data_feat.sh ${fbankdir}/test
     
    # compute global cmvn
    utils/compute_cmvn.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} \
        ${fbankdir}/train ${exp_dir}/exp/make_fbank/train

    # apply cmvn 
    utils/apply_cmvn.sh --cmd "$train_cmd" --nj $nj \
        ${fbankdir}/train ${fbankdir}/train/cmvn.json ${exp_dir}/exp/make_fbank/train ${feat_train_dir}
    utils/apply_cmvn.sh --cmd "$train_cmd" --nj $nj \
        ${fbankdir}/dev ${fbankdir}/train/cmvn.json ${exp_dir}/exp/make_fbank/dev ${feat_dev_dir}
    utils/apply_cmvn.sh --cmd "$train_cmd" --nj $nj \
        ${fbankdir}/test ${fbankdir}/train/cmvn.json ${exp_dir}/exp/make_fbank/test ${feat_test_dir}
    
    cp ${fbankdir}/train/text ${fbankdir}/train/speech_shape ${fbankdir}/train/text_shape ${feat_train_dir}
    cp ${fbankdir}/dev/text ${fbankdir}/dev/speech_shape ${fbankdir}/dev/text_shape ${feat_dev_dir}
    cp ${fbankdir}/test/text ${fbankdir}/test/speech_shape ${fbankdir}/test/text_shape ${feat_test_dir}

    utils/fix_data_feat.sh ${feat_train_dir}
    utils/fix_data_feat.sh ${feat_dev_dir}
    utils/fix_data_feat.sh ${feat_test_dir}

    #generate ark list 
    utils/gen_ark_list.sh --cmd "$train_cmd" --nj $nj ${feat_train_dir} ${fbankdir}/train ${feat_train_dir}
    utils/gen_ark_list.sh --cmd "$train_cmd" --nj $nj ${feat_dev_dir} ${fbankdir}/dev ${feat_dev_dir}
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 "" ${feats_dir}/data/train/text | cut -f 2- -d" " | tr " " "\n" \
        | sort | uniq | grep -a -v -e '^\s*$' | awk '{print $0}' >> ${token_list}
    num_token=$(cat ${token_list} | wc -l)
    echo "<unk>" >> ${token_list}
    vocab_size=$(cat ${token_list} | wc -l)
    awk -v v=,${vocab_size} '{print $0v}' ${feat_train_dir}/text_shape > ${feat_train_dir}/text_shape.char
    awk -v v=,${vocab_size} '{print $0v}' ${feat_dev_dir}/text_shape > ${feat_dev_dir}/text_shape.char
    mkdir -p ${feats_dir}/asr_stats_fbank_zh_char/train 
    mkdir -p ${feats_dir}/asr_stats_fbank_zh_char/dev
    cp ${feat_train_dir}/speech_shape ${feat_train_dir}/text_shape ${feat_train_dir}/text_shape.char ${feats_dir}/asr_stats_fbank_zh_char/train
    cp ${feat_dev_dir}/speech_shape ${feat_dev_dir}/text_shape ${feat_dev_dir}/text_shape.char ${feats_dir}/asr_stats_fbank_zh_char/dev
fi

# Training Stage
world_size=$gpu_num  # run on one machine
if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
    echo "stage 3: Training"
    python utils/download_model.py  --model_name ${model_name}  # download pretrained model on ModelScope
    mkdir -p ${exp_dir}/exp/${model_dir}
    mkdir -p ${exp_dir}/exp/${model_dir}/log
    INIT_FILE=${exp_dir}/exp/${model_dir}/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])
            asr_train.py \
                --gpu_id $gpu_id \
                --use_preprocessor true \
                --token_type char \
                --token_list $token_list \
                --train_data_path_and_name_and_type ${feats_dir}/${dumpdir}/${train_set}/${scp},speech,${type} \
                --train_data_path_and_name_and_type ${feats_dir}/${dumpdir}/${train_set}/text,text,text \
                --train_shape_file ${feats_dir}/asr_stats_fbank_zh_char/${train_set}/speech_shape \
                --train_shape_file ${feats_dir}/asr_stats_fbank_zh_char/${train_set}/text_shape.char \
                --valid_data_path_and_name_and_type ${feats_dir}/${dumpdir}/${valid_set}/${scp},speech,${type} \
                --valid_data_path_and_name_and_type ${feats_dir}/${dumpdir}/${valid_set}/text,text,text \
                --valid_shape_file ${feats_dir}/asr_stats_fbank_zh_char/${valid_set}/speech_shape \
                --valid_shape_file ${feats_dir}/asr_stats_fbank_zh_char/${valid_set}/text_shape.char  \
                --init_param ${init_param} \
                --resume true \
                --output_dir ${exp_dir}/exp/${model_dir} \
                --config $asr_config \
                --input_size $feats_dim \
                --ngpu $gpu_num \
                --num_worker_count $count \
                --multiprocessing_distributed true \
                --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 4 ] && [ ${stop_stage} -ge 4 ]; then
    echo "stage 4: 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}/${dumpdir}/${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}" \
                --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 asr \
                ${_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/data2vec_finetune/utils

New file
@@ -0,0 +1 @@
../../aishell/tranformer/utils