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/aishell/data2vec_paraformer_finetune/run.sh | 23 +++++++++++++++++++----
1 files changed, 19 insertions(+), 4 deletions(-)
diff --git a/egs/aishell/data2vec_paraformer_finetune/run.sh b/egs/aishell/data2vec_paraformer_finetune/run.sh
index bf6d231..42e590b 100755
--- a/egs/aishell/data2vec_paraformer_finetune/run.sh
+++ b/egs/aishell/data2vec_paraformer_finetune/run.sh
@@ -28,7 +28,7 @@
nj=64
# data
-raw_data=
+raw_data=../raw_data
data_url=www.openslr.org/resources/33
# exp tag
@@ -88,7 +88,7 @@
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
@@ -141,7 +141,7 @@
--valid_set ${valid_set} \
--data_file_names "wav.scp,text" \
--init_param ${init_param} \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--resume true \
--output_dir ${exp_dir}/exp/${model_dir} \
--config $asr_config \
@@ -190,7 +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 \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--speed_perturb ${speed_perturb} \
--key_file "${_logdir}"/keys.JOB.scp \
--asr_train_config "${asr_exp}"/config.yaml \
@@ -212,4 +212,19 @@
tail -n 3 ${_dir}/text.cer > ${_dir}/text.cer.txt
cat ${_dir}/text.cer.txt
done
+fi
+
+# Prepare files for ModelScope fine-tuning and inference
+if [ ${stage} -le 6 ] && [ ${stop_stage} -ge 6 ]; then
+ echo "stage 6: ModelScope Preparation"
+ cp ${feats_dir}/data/${train_set}/cmvn/am.mvn ${exp_dir}/exp/${model_dir}/am.mvn
+ vocab_size=$(cat ${token_list} | wc -l)
+ python utils/gen_modelscope_configuration.py \
+ --am_model_name $inference_asr_model \
+ --mode paraformer \
+ --model_name data2vec_finetune_paraformer \
+ --dataset aishell \
+ --output_dir $exp_dir/exp/$model_dir \
+ --vocab_size $vocab_size \
+ --tag $tag
fi
\ No newline at end of file
--
Gitblit v1.9.1