From 2a66366be4c2715870e4859fd5a5db6e8a9dc00a Mon Sep 17 00:00:00 2001
From: chenmengzheAAA <123789350+chenmengzheAAA@users.noreply.github.com>
Date: 星期四, 14 九月 2023 19:00:17 +0800
Subject: [PATCH] Merge pull request #956 from alibaba-damo-academy/chenmengzheAAA-patch-4
---
egs/aishell2/data2vec_pretrain/run.sh | 56 +++++---------------------------------------------------
1 files changed, 5 insertions(+), 51 deletions(-)
diff --git a/egs/aishell2/data2vec_pretrain/run.sh b/egs/aishell2/data2vec_pretrain/run.sh
index d80fa60..3df39af 100755
--- a/egs/aishell2/data2vec_pretrain/run.sh
+++ b/egs/aishell2/data2vec_pretrain/run.sh
@@ -16,11 +16,10 @@
token_type=char
speed_perturb="0.9 1.0 1.1"
dataset_type=large
-stage=3
+stage=0
stop_stage=3
# feature configuration
-feats_dim=80
nj=64
# data
@@ -42,7 +41,7 @@
valid_set=dev_ios
asr_config=conf/train_pretrain_transformer.yaml
-model_dir="baseline_$(basename "${asr_config}" .yaml) _${lang}_${token_type}_${tag}"
+model_dir="baseline_$(basename "${asr_config}" .yaml)_${lang}_${token_type}_${tag}"
if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
echo "stage 0: Data preparation"
@@ -66,7 +65,7 @@
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 --fbankdir ${feats_dir}/data/${train_set} --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --config_file "$asr_config" --scale 1.0
fi
token_list=${feats_dir}/data/${lang}_token_list/char/tokens.txt
@@ -82,52 +81,7 @@
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
-world_size=$gpu_num # run on one machine
-if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
- echo "stage 3: 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 \
- --token_type char \
- --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} \
- --dataset_type $dataset_type \
- --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.$i 2>&1
- } &
- done
- wait
-fi
# Training Stage
world_size=$gpu_num # run on one machine
@@ -153,13 +107,13 @@
--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" \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.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 \
--
Gitblit v1.9.1