From 62f490ef6f2bc9250a51ad06c6c72d2b9adbd0c0 Mon Sep 17 00:00:00 2001
From: chong.zhang <chong.zhang@alibaba-inc.com>
Date: 星期二, 23 五月 2023 16:51:19 +0800
Subject: [PATCH] add speech_UniASR_asr_2pass-tr-16k-common-vocab1582-pytorch
---
egs/librispeech_100h/conformer/run.sh | 219 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 219 insertions(+), 0 deletions(-)
diff --git a/egs/librispeech_100h/conformer/run.sh b/egs/librispeech_100h/conformer/run.sh
new file mode 100755
index 0000000..f0db69c
--- /dev/null
+++ b/egs/librispeech_100h/conformer/run.sh
@@ -0,0 +1,219 @@
+#!/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
+exp_dir="."
+lang=en
+token_type=bpe
+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=
+data_url=www.openslr.org/resources/12
+
+# bpe model
+nbpe=5000
+bpemode=unigram
+
+# 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_clean_100
+valid_set=dev
+test_sets="test_clean test_other dev_clean dev_other"
+
+asr_config=conf/train_asr_conformer.yaml
+model_dir="baseline_$(basename "${asr_config}" .yaml)_${lang}_${token_type}_${tag}"
+
+#inference_config=conf/decode_asr_transformer_ctc0.3_beam1.yaml
+inference_config=conf/decode_asr_transformer_ctc0.3_beam5.yaml
+#inference_config=conf/decode_asr_transformer_ctc0.3_beam20.yaml
+inference_asr_model=valid.acc.ave_10best.pb
+
+# you can set gpu num for decoding here
+gpuid_list=$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"
+ for part in dev-clean test-clean dev-other test-other train-clean-100; do
+ local/download_and_untar.sh ${raw_data} ${data_url} ${part}
+ done
+fi
+
+if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
+ echo "stage 0: Data preparation"
+ # Data preparation
+ for x in dev-clean dev-other test-clean test-other train-clean-100; do
+ local/data_prep.sh ${raw_data}/LibriSpeech/${x} ${feats_dir}/data/${x//-/_}
+ done
+ mkdir $feats_dir/data/$valid_set
+ dev_sets="dev_clean dev_other"
+ for file in wav.scp text; do
+ ( for f in $dev_sets; do cat $feats_dir/data/$f/$file; done ) | sort -k1 > $feats_dir/data/$valid_set/$file || exit 1;
+ 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=${feats_dir}/data/lang_char/${train_set}_${bpemode}${nbpe}_units.txt
+bpemodel=${feats_dir}/data/lang_char/${train_set}_${bpemode}${nbpe}
+echo "dictionary: ${token_list}"
+if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
+ ### Task dependent. You have to check non-linguistic symbols used in the corpus.
+ echo "stage 2: Dictionary and Json Data Preparation"
+ mkdir -p ${feats_dir}/data/lang_char/
+ echo "<blank>" > ${token_list}
+ echo "<s>" >> ${token_list}
+ echo "</s>" >> ${token_list}
+ cut -f 2- -d" " ${feats_dir}/data/${train_set}/text > ${feats_dir}/data/lang_char/input.txt
+ local/spm_train.py --input=${feats_dir}/data/lang_char/input.txt --vocab_size=${nbpe} --model_type=${bpemode} --model_prefix=${bpemodel} --input_sentence_size=100000000
+ local/spm_encode.py --model=${bpemodel}.model --output_format=piece < ${feats_dir}/data/lang_char/input.txt | tr ' ' '\n' | sort | uniq | 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=${exp_dir}/exp/${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])
+ train.py \
+ --task_name asr \
+ --gpu_id $gpu_id \
+ --use_preprocessor true \
+ --split_with_space false \
+ --bpemodel ${bpemodel}.model \
+ --token_type $token_type \
+ --token_list $token_list \
+ --data_dir ${feats_dir}/data \
+ --train_set ${train_set} \
+ --valid_set ${valid_set} \
+ --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 \
+ --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 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 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/compute_wer.py ${_data}/text ${_dir}/text ${_dir}/text.cer
+ tail -n 3 ${_dir}/text.cer > ${_dir}/text.cer.txt
+ cat ${_dir}/text.cer.txt
+ done
+fi
\ No newline at end of file
--
Gitblit v1.9.1