From cefa8ff17e3e2f4a7745d15a59beef0a255fabfd Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期四, 25 五月 2023 10:54:53 +0800
Subject: [PATCH] update repo
---
egs/aishell2/transformer/run.sh | 31 ++++++++++++++++++-------------
1 files changed, 18 insertions(+), 13 deletions(-)
diff --git a/egs/aishell2/transformer/run.sh b/egs/aishell2/transformer/run.sh
index cb1fd72..bd46e60 100755
--- a/egs/aishell2/transformer/run.sh
+++ b/egs/aishell2/transformer/run.sh
@@ -21,16 +21,16 @@
scp=wav.scp
speed_perturb="0.9 1.0 1.1"
dataset_type=large
-stage=3
-stop_stage=4
+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"
@@ -87,7 +87,7 @@
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}
+ utils/compute_cmvn.sh ${feats_dir}/data/${train_set} --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --config $asr_config --scale 1.0
fi
token_list=${feats_dir}/data/${lang}_token_list/char/tokens.txt
@@ -103,14 +103,18 @@
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
@@ -133,7 +137,8 @@
--data_dir ${feats_dir}/data \
--train_set ${train_set} \
--valid_set ${valid_set} \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --data_file_names "wav.scp,text" \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--speed_perturb ${speed_perturb} \
--dataset_type $dataset_type \
--resume true \
@@ -151,8 +156,8 @@
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)"
@@ -184,7 +189,7 @@
--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 \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.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