From f96df00995c8ddddc2f0668f8db307342cc3819e Mon Sep 17 00:00:00 2001
From: rich04lin <152049331+rich04lin@users.noreply.github.com>
Date: Sat, 15 Mar 2025 17:50:36 +0800
Subject: [PATCH] NUM7

---
 examples/csmsc/tts0/README.md | 12 ++++++++++--
 examples/csmsc/tts0/run.sh    |  8 ++++----
 2 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/examples/csmsc/tts0/README.md b/examples/csmsc/tts0/README.md
index ce682495e..a734c644a 100644
--- a/examples/csmsc/tts0/README.md
+++ b/examples/csmsc/tts0/README.md
@@ -99,7 +99,11 @@ pwg_baker_ckpt_0.4
 ```
 `./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} ${ckpt_name}
+
+`--stage` controls the vocoder model during synthesis, which can be `0` or `1`, use `pwgan` or `hifigan` model as vocoder.
 ```
 ```text
 usage: synthesize.py [-h]
@@ -147,7 +151,11 @@ optional arguments:
 ```
 `./local/synthesize_e2e.sh` calls `${BIN_DIR}/../synthesize_e2e.py`, which can synthesize waveform from text file.
 ```bash
-CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.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.
 ```
 ```text
 usage: synthesize_e2e.py [-h]
diff --git a/examples/csmsc/tts0/run.sh b/examples/csmsc/tts0/run.sh
index 8f06e933c..3a4f5a58b 100755
--- a/examples/csmsc/tts0/run.sh
+++ b/examples/csmsc/tts0/run.sh
@@ -27,13 +27,13 @@ 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 ] && [ ${stop_stage} -ge 3 ]; then
-    # synthesize_e2e, vocoder is pwgan
-    CUDA_VISIBLE_DEVICES=${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
 
 if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then