From 609b4a384a307ff0fa59937b5eeb4901107004a0 Mon Sep 17 00:00:00 2001
From: rich04lin <152049331+rich04lin@users.noreply.github.com>
Date: Fri, 14 Mar 2025 20:55:22 +0800
Subject: [PATCH] num5

---
 examples/aishell3_vctk/ernie_sat/README.md | 6 +++++-
 examples/aishell3_vctk/ernie_sat/run.sh    | 7 ++++---
 2 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/examples/aishell3_vctk/ernie_sat/README.md b/examples/aishell3_vctk/ernie_sat/README.md
index fbf9244d1..110ce4207 100644
--- a/examples/aishell3_vctk/ernie_sat/README.md
+++ b/examples/aishell3_vctk/ernie_sat/README.md
@@ -95,7 +95,11 @@ hifigan_aishell3_ckpt_0.2.0
 ```
 `./local/synthesize.sh` calls `${BIN_DIR}/../synthesize.py`, which can synthesize waveform from `metadata.jsonl`.
 ```bash
-CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh ${conf_path} ${train_output_path} ${ckpt_name}
+`./local/synthesize.sh` calls `${BIN_DIR}/../synthesize.py`, which can synthesize waveform from `metadata.jsonl`. 
+
+CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name}
+
+`--stage` controls the vocoder model during synthesis, which can be `0` or `1`, use `pwgan` or `hifigan` model as vocoder.
 ```
 ##  Speech Synthesis and Speech Editing
 ### Prepare
diff --git a/examples/aishell3_vctk/ernie_sat/run.sh b/examples/aishell3_vctk/ernie_sat/run.sh
index 8cd9d8d1b..69d0b3fe7 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 ] && [ ${stop_stage} -ge 2 ]; then
-    # synthesize, vocoder is pwgan
-    CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
+    # synthesize, vocoder is pwgan by default stage 0, stage 1 will use hifigan as vocoder
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${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} ${ckpt_name} || exit -1
+    # synthesize_e2e, vocoder is pwgan by default stage 0, stage 1 will use hifigan as vocoder
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
 fi