From 3360a1d9453ef0ce441cc41b0090d09b3bb296bb Mon Sep 17 00:00:00 2001
From: aky15 <ankeyuthu@gmail.com>
Date: 星期二, 04 七月 2023 20:02:45 +0800
Subject: [PATCH] Dev bat (#701)
---
egs/aishell/bat/utils | 1
egs/aishell/bat/README.md | 16 ++
egs/aishell/bat/local/aishell_data_prep.sh | 66 +++++++++
egs/aishell/bat/run.sh | 210 ++++++++++++++++++++++++++++++
egs/aishell/bat/conf/decode_bat_conformer.yaml | 1
egs/aishell/bat/path.sh | 5
egs/aishell/bat/conf/train_conformer_bat.yaml | 108 +++++++++++++++
7 files changed, 407 insertions(+), 0 deletions(-)
diff --git a/egs/aishell/bat/README.md b/egs/aishell/bat/README.md
new file mode 100644
index 0000000..ed2a6da
--- /dev/null
+++ b/egs/aishell/bat/README.md
@@ -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 |
diff --git a/egs/aishell/bat/conf/decode_bat_conformer.yaml b/egs/aishell/bat/conf/decode_bat_conformer.yaml
new file mode 100644
index 0000000..9a71e66
--- /dev/null
+++ b/egs/aishell/bat/conf/decode_bat_conformer.yaml
@@ -0,0 +1 @@
+beam_size: 10
diff --git a/egs/aishell/bat/conf/train_conformer_bat.yaml b/egs/aishell/bat/conf/train_conformer_bat.yaml
new file mode 100644
index 0000000..46ca9bf
--- /dev/null
+++ b/egs/aishell/bat/conf/train_conformer_bat.yaml
@@ -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
diff --git a/egs/aishell/bat/local/aishell_data_prep.sh b/egs/aishell/bat/local/aishell_data_prep.sh
new file mode 100755
index 0000000..83f489b
--- /dev/null
+++ b/egs/aishell/bat/local/aishell_data_prep.sh
@@ -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 "$0: AISHELL data preparation succeeded"
+exit 0;
diff --git a/egs/aishell/bat/path.sh b/egs/aishell/bat/path.sh
new file mode 100644
index 0000000..7972642
--- /dev/null
+++ b/egs/aishell/bat/path.sh
@@ -0,0 +1,5 @@
+export FUNASR_DIR=$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
diff --git a/egs/aishell/bat/run.sh b/egs/aishell/bat/run.sh
new file mode 100755
index 0000000..54f1d87
--- /dev/null
+++ b/egs/aishell/bat/run.sh
@@ -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
diff --git a/egs/aishell/bat/utils b/egs/aishell/bat/utils
new file mode 120000
index 0000000..4072eac
--- /dev/null
+++ b/egs/aishell/bat/utils
@@ -0,0 +1 @@
+../transformer/utils
\ No newline at end of file
--
Gitblit v1.9.1