From 580b11b57ac4b62f7e2acda73813a4e10e8e4cd3 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 10 十月 2023 17:17:29 +0800
Subject: [PATCH] v0.8.0

---
 egs/aishell/data2vec_paraformer_finetune/run.sh |   53 +++++++++++++++++++++++++++++++++++++++--------------
 1 files changed, 39 insertions(+), 14 deletions(-)

diff --git a/egs/aishell/data2vec_paraformer_finetune/run.sh b/egs/aishell/data2vec_paraformer_finetune/run.sh
index 42b4425..1f96873 100755
--- a/egs/aishell/data2vec_paraformer_finetune/run.sh
+++ b/egs/aishell/data2vec_paraformer_finetune/run.sh
@@ -19,15 +19,16 @@
 token_type=char
 type=sound
 scp=wav.scp
-stage=3
-stop_stage=4
+speed_perturb="0.9 1.0 1.1"
+stage=0
+stop_stage=5
 
 # feature configuration
 feats_dim=80
 nj=64
 
 # data
-raw_data=
+raw_data=../raw_data
 data_url=www.openslr.org/resources/33
 
 # exp tag
@@ -87,14 +88,14 @@
 
 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}
@@ -105,11 +106,17 @@
     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"
-     python utils/download_model.py  --model_name ${model_name}  # download pretrained model on ModelScope
+    echo "stage 3: LM Training"
+fi
+
+# ASR Training Stage
+world_size=$gpu_num  # run on one machine
+if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
+    echo "stage 4: ASR Training"
+    python utils/download_model.py  --model_name ${model_name}  # download pretrained model on ModelScope
     mkdir -p ${exp_dir}/exp/${model_dir}
     mkdir -p ${exp_dir}/exp/${model_dir}/log
     INIT_FILE=${exp_dir}/exp/${model_dir}/ddp_init
@@ -127,13 +134,14 @@
                 --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" \
                 --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 \
@@ -149,8 +157,8 @@
 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)"
@@ -182,7 +190,8 @@
                 --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 "${asr_exp}"/config.yaml \
                 --asr_model_file "${asr_exp}"/"${inference_asr_model}" \
@@ -203,4 +212,20 @@
         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 \
+        --nat _nat \
+        --tag $tag
 fi
\ No newline at end of file

--
Gitblit v1.9.1