From 3d9f094e9652d4b84894c6fd4eae39a4a753b0f0 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 16 五月 2023 23:48:00 +0800
Subject: [PATCH] train
---
egs/aishell2/conformer/run.sh | 42 ++++++++++++++++++++++++++----------------
1 files changed, 26 insertions(+), 16 deletions(-)
diff --git a/egs/aishell2/conformer/run.sh b/egs/aishell2/conformer/run.sh
index 243ce37..c3b4065 100755
--- a/egs/aishell2/conformer/run.sh
+++ b/egs/aishell2/conformer/run.sh
@@ -20,16 +20,17 @@
type=sound
scp=wav.scp
speed_perturb="0.9 1.0 1.1"
-stage=2
-stop_stage=2
+dataset_type=large
+stage=0
+stop_stage=5
# feature configuration
feats_dim=80
nj=64
# data
-tr_dir=/nfs/wangjiaming.wjm/asr_data/aishell2/AISHELL-2/iOS/data
-dev_tst_dir=/nfs/wangjiaming.wjm/asr_data/aishell2/AISHELL-DEV-TEST-SET
+tr_dir=
+dev_tst_dir=
# exp tag
tag="exp1"
@@ -99,17 +100,23 @@
echo "<blank>" > ${token_list}
echo "<s>" >> ${token_list}
echo "</s>" >> ${token_list}
- tools/text2token.py -s 1 -n 1 --space "" ${feats_dir}/data/${train_set}/text | cut -f 2- -d" " | tr " " "\n" \
+ 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}
mkdir -p ${feats_dir}/asr_stats_fbank_zh_char/${train_set}
mkdir -p ${feats_dir}/asr_stats_fbank_zh_char/${valid_set}
fi
-# Training Stage
+# LM Training Stage
world_size=$gpu_num # run on one machine
if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
- echo "stage 3: Training"
+ echo "stage 3: LM Training"
+fi
+
+# ASR Training Stage
+world_size=$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
@@ -123,21 +130,23 @@
rank=$i
local_rank=$i
gpu_id=$(echo $CUDA_VISIBLE_DEVICES | cut -d',' -f$[$i+1])
- asr_train.py \
+ train.py \
+ --task_name asr \
--gpu_id $gpu_id \
--use_preprocessor true \
- --dataset_type $dataset_type \
--token_type char \
--token_list $token_list \
- --train_data_file $feats_dir/$dumpdir/${train_set}/data.list \
- --valid_data_file $feats_dir/$dumpdir/${valid_set}/data.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} \
+ --dataset_type $dataset_type \
--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 \
@@ -148,8 +157,8 @@
fi
# Testing Stage
-if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
- echo "stage 4: Inference"
+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 "${inference_config}" .yaml)"
@@ -160,7 +169,7 @@
exit 0
fi
mkdir -p "${_logdir}"
- _data="${feats_dir}/${dumpdir}/${dset}"
+ _data="${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")
@@ -181,6 +190,7 @@
--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}" \
--
Gitblit v1.9.1