From 4ace5a95b052d338947fc88809a440ccd55cf6b4 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 16 十一月 2023 16:39:52 +0800
Subject: [PATCH] funasr pages
---
egs/aishell2/conformer/run.sh | 28 ++++++++++++++++++++--------
1 files changed, 20 insertions(+), 8 deletions(-)
diff --git a/egs/aishell2/conformer/run.sh b/egs/aishell2/conformer/run.sh
index d3416f8..193c4a3 100755
--- a/egs/aishell2/conformer/run.sh
+++ b/egs/aishell2/conformer/run.sh
@@ -87,14 +87,14 @@
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
+token_list=${feats_dir}/data/${lang}_token_list/$token_type/tokens.txt
echo "dictionary: ${token_list}"
if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
echo "stage 2: Dictionary Preparation"
- mkdir -p ${feats_dir}/data/${lang}_token_list/char/
+ mkdir -p ${feats_dir}/data/${lang}_token_list/$token_type/
echo "make a dictionary"
echo "<blank>" > ${token_list}
@@ -103,8 +103,6 @@
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
# LM Training Stage
@@ -134,13 +132,13 @@
--task_name asr \
--gpu_id $gpu_id \
--use_preprocessor true \
- --token_type char \
+ --token_type $token_type \
--token_list $token_list \
--data_dir ${feats_dir}/data \
--train_set ${train_set} \
--valid_set ${valid_set} \
--data_file_names "wav.scp,text" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--speed_perturb ${speed_perturb} \
--dataset_type $dataset_type \
--resume true \
@@ -191,7 +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}" \
@@ -214,5 +212,19 @@
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 asr \
+ --model_name conformer \
+ --dataset aishell2 \
+ --output_dir $exp_dir/exp/$model_dir \
+ --vocab_size $vocab_size \
+ --tag $tag
+fi
--
Gitblit v1.9.1