From 6f7e27eb7c2d0a7649ec8f14d167c8da8e29f906 Mon Sep 17 00:00:00 2001
From: jmwang66 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期二, 16 五月 2023 15:07:20 +0800
Subject: [PATCH] Merge pull request #518 from alibaba-damo-academy/dev_wjm2
---
egs/aishell/paraformerbert/run.sh | 114 ++++++++++++++++-----------------------------------------
1 files changed, 32 insertions(+), 82 deletions(-)
diff --git a/egs/aishell/paraformerbert/run.sh b/egs/aishell/paraformerbert/run.sh
index 2487eac..a4ad195 100755
--- a/egs/aishell/paraformerbert/run.sh
+++ b/egs/aishell/paraformerbert/run.sh
@@ -8,7 +8,7 @@
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
+njob=1
train_cmd=utils/run.pl
infer_cmd=utils/run.pl
@@ -16,29 +16,26 @@
feats_dir="../DATA" #feature output dictionary, for large data
exp_dir="."
lang=zh
-dumpdir=dump/fbank
-feats_type=fbank
token_type=char
-scp=feats.scp
-type=kaldi_ark
-stage=0
+type=sound
+scp=wav.scp
+speed_perturb="0.9 1.0 1.1"
+stage=3
stop_stage=4
skip_extract_embed=false
-bert_model_root="../../huggingface_models"
bert_model_name="bert-base-chinese"
# feature configuration
feats_dim=80
-sample_frequency=16000
-nj=32
-speed_perturb="0.9,1.0,1.1"
+nj=64
# data
-data_aishell=
+raw_data=
+data_url=www.openslr.org/resources/33
# exp tag
-tag=""
+tag="exp1"
. utils/parse_options.sh || exit 1;
@@ -53,7 +50,7 @@
test_sets="dev test"
asr_config=conf/train_asr_paraformerbert_conformer_12e_6d_2048_256.yaml
-model_dir="baseline_$(basename "${asr_config}" .yaml)_${feats_type}_${lang}_${token_type}_${tag}"
+model_dir="baseline_$(basename "${asr_config}" .yaml)_${lang}_${token_type}_${tag}"
inference_config=conf/decode_asr_transformer_noctc_1best.yaml
inference_asr_model=valid.acc.ave_10best.pb
@@ -70,10 +67,17 @@
_ngpu=0
fi
+if [ ${stage} -le -1 ] && [ ${stop_stage} -ge -1 ]; then
+ echo "stage -1: Data Download"
+ local/download_and_untar.sh ${raw_data} ${data_url} data_aishell
+ local/download_and_untar.sh ${raw_data} ${data_url} resource_aishell
+fi
+
+
if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
echo "stage 0: Data preparation"
# Data preparation
- local/aishell_data_prep.sh ${data_aishell}/data_aishell/wav ${data_aishell}/data_aishell/transcript ${feats_dir}
+ local/aishell_data_prep.sh ${raw_data}/data_aishell/wav ${raw_data}/data_aishell/transcript ${feats_dir}
for x in train dev test; do
cp ${feats_dir}/data/${x}/text ${feats_dir}/data/${x}/text.org
paste -d " " <(cut -f 1 -d" " ${feats_dir}/data/${x}/text.org) <(cut -f 2- -d" " ${feats_dir}/data/${x}/text.org | tr -d " ") \
@@ -83,46 +87,9 @@
done
fi
-feat_train_dir=${feats_dir}/${dumpdir}/train; mkdir -p ${feat_train_dir}
-feat_dev_dir=${feats_dir}/${dumpdir}/dev; mkdir -p ${feat_dev_dir}
-feat_test_dir=${feats_dir}/${dumpdir}/test; mkdir -p ${feat_test_dir}
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
- echo "stage 1: Feature Generation"
- # compute fbank features
- fbankdir=${feats_dir}/fbank
- utils/compute_fbank.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --sample_frequency ${sample_frequency} --speed_perturb ${speed_perturb} \
- ${feats_dir}/data/train ${exp_dir}/exp/make_fbank/train ${fbankdir}/train
- utils/fix_data_feat.sh ${fbankdir}/train
- utils/compute_fbank.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --sample_frequency ${sample_frequency} \
- ${feats_dir}/data/dev ${exp_dir}/exp/make_fbank/dev ${fbankdir}/dev
- utils/fix_data_feat.sh ${fbankdir}/dev
- utils/compute_fbank.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --sample_frequency ${sample_frequency} \
- ${feats_dir}/data/test ${exp_dir}/exp/make_fbank/test ${fbankdir}/test
- utils/fix_data_feat.sh ${fbankdir}/test
-
- # compute global cmvn
- utils/compute_cmvn.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} \
- ${fbankdir}/train ${exp_dir}/exp/make_fbank/train
-
- # apply cmvn
- utils/apply_cmvn.sh --cmd "$train_cmd" --nj $nj \
- ${fbankdir}/train ${fbankdir}/train/cmvn.json ${exp_dir}/exp/make_fbank/train ${feat_train_dir}
- utils/apply_cmvn.sh --cmd "$train_cmd" --nj $nj \
- ${fbankdir}/dev ${fbankdir}/train/cmvn.json ${exp_dir}/exp/make_fbank/dev ${feat_dev_dir}
- utils/apply_cmvn.sh --cmd "$train_cmd" --nj $nj \
- ${fbankdir}/test ${fbankdir}/train/cmvn.json ${exp_dir}/exp/make_fbank/test ${feat_test_dir}
-
- cp ${fbankdir}/train/text ${fbankdir}/train/speech_shape ${fbankdir}/train/text_shape ${feat_train_dir}
- cp ${fbankdir}/dev/text ${fbankdir}/dev/speech_shape ${fbankdir}/dev/text_shape ${feat_dev_dir}
- cp ${fbankdir}/test/text ${fbankdir}/test/speech_shape ${fbankdir}/test/text_shape ${feat_test_dir}
-
- utils/fix_data_feat.sh ${feat_train_dir}
- utils/fix_data_feat.sh ${feat_dev_dir}
- utils/fix_data_feat.sh ${feat_test_dir}
-
- #generate ark list
- utils/gen_ark_list.sh --cmd "$train_cmd" --nj $nj ${feat_train_dir} ${fbankdir}/train ${feat_train_dir}
- utils/gen_ark_list.sh --cmd "$train_cmd" --nj $nj ${feat_dev_dir} ${fbankdir}/dev ${feat_dev_dir}
+ echo "stage 1: Feature and CMVN Generation"
+ utils/compute_cmvn.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} ${feats_dir}/data/${train_set}
fi
token_list=${feats_dir}/data/${lang}_token_list/char/tokens.txt
@@ -135,17 +102,9 @@
echo "<blank>" > ${token_list}
echo "<s>" >> ${token_list}
echo "</s>" >> ${token_list}
- utils/text2token.py -s 1 -n 1 --space "" ${feats_dir}/data/train/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}' >> ${token_list}
- num_token=$(cat ${token_list} | wc -l)
echo "<unk>" >> ${token_list}
- vocab_size=$(cat ${token_list} | wc -l)
- awk -v v=,${vocab_size} '{print $0v}' ${feat_train_dir}/text_shape > ${feat_train_dir}/text_shape.char
- awk -v v=,${vocab_size} '{print $0v}' ${feat_dev_dir}/text_shape > ${feat_dev_dir}/text_shape.char
- mkdir -p ${feats_dir}/asr_stats_fbank_zh_char/train
- mkdir -p ${feats_dir}/asr_stats_fbank_zh_char/dev
- cp ${feat_train_dir}/speech_shape ${feat_train_dir}/text_shape ${feat_train_dir}/text_shape.char ${feats_dir}/asr_stats_fbank_zh_char/train
- cp ${feat_dev_dir}/speech_shape ${feat_dev_dir}/text_shape ${feat_dev_dir}/text_shape.char ${feats_dir}/asr_stats_fbank_zh_char/dev
fi
# Training Stage
@@ -155,9 +114,9 @@
if ! "${skip_extract_embed}"; then
echo "extract embeddings..."
local/extract_embeds.sh \
- --bert_model_root ${bert_model_root} \
--bert_model_name ${bert_model_name} \
- --raw_dataset_path ${feats_dir}
+ --raw_dataset_path ${feats_dir} \
+ --nj $nj
fi
mkdir -p ${exp_dir}/exp/${model_dir}
mkdir -p ${exp_dir}/exp/${model_dir}/log
@@ -172,31 +131,23 @@
rank=$i
local_rank=$i
gpu_id=$(echo $CUDA_VISIBLE_DEVICES | cut -d',' -f$[$i+1])
- asr_train_paraformer.py \
+ train.py \
+ --task_name asr \
--gpu_id $gpu_id \
--use_preprocessor true \
--token_type char \
--token_list $token_list \
- --train_data_path_and_name_and_type ${feats_dir}/${dumpdir}/${train_set}/${scp},speech,${type} \
- --train_data_path_and_name_and_type ${feats_dir}/${dumpdir}/${train_set}/text,text,text \
- --train_data_path_and_name_and_type ${feats_dir}/embeds/${bert_model_name}/${train_set}/embeds.scp,embed,${type} \
- --train_shape_file ${feats_dir}/asr_stats_fbank_zh_char/${train_set}/speech_shape \
- --train_shape_file ${feats_dir}/asr_stats_fbank_zh_char/${train_set}/text_shape.char \
- --train_shape_file ${feats_dir}/embeds/${bert_model_name}/${train_set}/embeds.shape \
- --valid_data_path_and_name_and_type ${feats_dir}/${dumpdir}/${valid_set}/${scp},speech,${type} \
- --valid_data_path_and_name_and_type ${feats_dir}/${dumpdir}/${valid_set}/text,text,text \
- --valid_data_path_and_name_and_type ${feats_dir}/embeds/${bert_model_name}/${valid_set}/embeds.scp,embed,${type} \
- --valid_shape_file ${feats_dir}/asr_stats_fbank_zh_char/${valid_set}/speech_shape \
- --valid_shape_file ${feats_dir}/asr_stats_fbank_zh_char/${valid_set}/text_shape.char \
- --valid_shape_file ${feats_dir}/embeds/${bert_model_name}/${valid_set}/embeds.shape \
+ --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 \
+ --speed_perturb ${speed_perturb} \
--resume true \
--output_dir ${exp_dir}/exp/${model_dir} \
--config $asr_config \
- --allow_variable_data_keys true \
- --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 \
@@ -260,5 +211,4 @@
tail -n 3 ${_dir}/text.cer > ${_dir}/text.cer.txt
cat ${_dir}/text.cer.txt
done
-fi
-
+fi
\ No newline at end of file
--
Gitblit v1.9.1