From e3401f22ae01a611cbc88fd226ec2da1e66924c5 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期三, 24 五月 2023 14:57:13 +0800
Subject: [PATCH] update repo
---
egs/aishell2/paraformerbert/run.sh | 30 ++++++++++++++++++------------
1 files changed, 18 insertions(+), 12 deletions(-)
diff --git a/egs/aishell2/paraformerbert/run.sh b/egs/aishell2/paraformerbert/run.sh
index 26c8063..efab853 100755
--- a/egs/aishell2/paraformerbert/run.sh
+++ b/egs/aishell2/paraformerbert/run.sh
@@ -21,8 +21,8 @@
scp=wav.scp
speed_perturb="0.9 1.0 1.1"
dataset_type=large
-stage=3
-stop_stage=4
+stage=0
+stop_stage=5
skip_extract_embed=false
bert_model_name="bert-base-chinese"
@@ -32,8 +32,8 @@
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"
@@ -90,7 +90,7 @@
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
@@ -108,10 +108,16 @@
echo "<unk>" >> ${token_list}
fi
-# Training Stage
+# LM Training Stage
world_size=$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 ] && [ ${stop_stage} -ge 4 ]; then
+ echo "stage 4: ASR Training"
if ! "${skip_extract_embed}"; then
echo "extract embeddings..."
local/extract_embeds.sh \
@@ -141,8 +147,8 @@
--data_dir ${feats_dir}/data \
--train_set ${train_set} \
--valid_set ${valid_set} \
- --embed_path ${feats_dir}/data \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --data_file_names "wav.scp,text,embeds.scp" \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--speed_perturb ${speed_perturb} \
--dataset_type $dataset_type \
--resume true \
@@ -160,8 +166,8 @@
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)"
@@ -193,7 +199,7 @@
--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