diff --git a/examples/aishell3_vctk/ernie_sat/README.md b/examples/aishell3_vctk/ernie_sat/README.md
index 57dcd472f..6cc723690 100644
--- a/examples/aishell3_vctk/ernie_sat/README.md
+++ b/examples/aishell3_vctk/ernie_sat/README.md
@@ -15,7 +15,7 @@ In ERNIE-SAT, we propose two innovations:
 Download all datasets and extract it to `~/datasets`:
 - The aishell3 dataset is in the directory `~/datasets/data_aishell3`
 - The vctk dataset is in the directory `~/datasets/VCTK-Corpus-0.92`
- 
+
 ### Get MFA Result and Extract
 We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for the fastspeech2 training.
 You can download from here:
@@ -97,6 +97,8 @@ hifigan_aishell3_ckpt_0.2.0
 ```bash
 CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh ${conf_path} ${train_output_path} ${ckpt_name}
 ```
+synthesize, vocoder is `hifigan`
+
 ##  Speech Synthesis and Speech Editing
 ### Prepare
 
@@ -150,7 +152,7 @@ You can check the text of downloaded wavs in `source/README.md`.
 ```bash
 ./run.sh --stage 3 --stop-stage 3 --gpus 0
 ```
-`stage 3` of `run.sh` calls `local/synthesize_e2e.sh`.
+`stage 3` of `run.sh` calls `local/synthesize_e2e.sh`, `stage 0` of it is **Speech cross language from en to zh** and `stage 1` of it is **Speech cross language from zh to en**.
 
 You can modify  `--wav_path`、`--old_str` and `--new_str` yourself, `--old_str` should be the text corresponding to the audio of  `--wav_path`, `--new_str` should be designed according to `--task_name`, `--source_lang` and `--target_lang` should be different in this example.
 ## Pretrained Model
diff --git a/examples/aishell3_vctk/ernie_sat/run.sh b/examples/aishell3_vctk/ernie_sat/run.sh
index 8cd9d8d1b..d29f0b6e8 100755
--- a/examples/aishell3_vctk/ernie_sat/run.sh
+++ b/examples/aishell3_vctk/ernie_sat/run.sh
@@ -27,10 +27,11 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
 fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
-    # synthesize, vocoder is pwgan
+    # synthesize, vocoder is hifigan
     CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
 fi
 
 if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
-    CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
+    # synthesize_e2e, default speech synthesis from Chinese to English, use stage1 to switch from English to Chinese
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
 fi