From fae44e7e78e21b9d5386c2e9c1c6b741d47363f6 Mon Sep 17 00:00:00 2001
From: Echo-Nie <157974576+Echo-Nie@users.noreply.github.com>
Date: Mon, 7 Apr 2025 15:15:40 +0800
Subject: [PATCH] =?UTF-8?q?=E3=80=90PaddleSpeech=20No.12=E3=80=91=20(#4037?=
 =?UTF-8?q?)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* fix the svs1

* del stage 0

* 删去中文README中多余的stage 0
---
 examples/opencpop/svs1/README.md    | 6 +++++-
 examples/opencpop/svs1/README_cn.md | 6 +++++-
 examples/opencpop/svs1/run.sh       | 4 ++--
 3 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/examples/opencpop/svs1/README.md b/examples/opencpop/svs1/README.md
index 092f27644..534a741fd 100644
--- a/examples/opencpop/svs1/README.md
+++ b/examples/opencpop/svs1/README.md
@@ -118,6 +118,8 @@ pwgan_opencpop_ckpt_1.4.0.zip
 ```bash
 CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh ${conf_path} ${train_output_path} ${ckpt_name}
 ```
+use `pwgan` model as vocoder.
+
 ```text
 usage: synthesize.py [-h]
                      [--am {diffsinger_opencpop}]
@@ -170,8 +172,10 @@ optional arguments:
 `local/pinyin_to_phone.txt` comes from the readme of the opencpop dataset, indicating the mapping from pinyin to phonemes in opencpop.
 
 ```bash
-CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh ${conf_path} ${train_output_path} ${ckpt_name}
+CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name}
 ```
+`--stage` controls the vocoder model during synthesis, which can be `0` or `1`, use `pwgan` or `hifigan` model as vocoder.
+
 ```text
 usage: synthesize_e2e.py [-h]
                          [--am {speedyspeech_csmsc,speedyspeech_aishell3,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk,tacotron2_csmsc,tacotron2_ljspeech}]
diff --git a/examples/opencpop/svs1/README_cn.md b/examples/opencpop/svs1/README_cn.md
index eac72b5aa..e35967d71 100644
--- a/examples/opencpop/svs1/README_cn.md
+++ b/examples/opencpop/svs1/README_cn.md
@@ -121,6 +121,8 @@ pwgan_opencpop_ckpt_1.4.0.zip
 ```bash
 CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh ${conf_path} ${train_output_path} ${ckpt_name}
 ```
+使用 `pwgan` 模型作为声码器。
+
 ```text
 usage: synthesize.py [-h]
                      [--am {diffsinger_opencpop}]
@@ -173,8 +175,10 @@ optional arguments:
 `local/pinyin_to_phone.txt`来源于opencpop数据集中的README，表示opencpop中拼音到音素的映射。
 
 ```bash
-CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh ${conf_path} ${train_output_path} ${ckpt_name}
+CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name}
 ```
+`--stage` 用于选择合成时使用的声码器模型，取值为 `0` 或 `1`，分别对应使用 `pwgan` 或 `hifigan` 模型作为声码器。
+
 ```text
 usage: synthesize_e2e.py [-h]
                          [--am {speedyspeech_csmsc,speedyspeech_aishell3,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk,tacotron2_csmsc,tacotron2_ljspeech}]
diff --git a/examples/opencpop/svs1/run.sh b/examples/opencpop/svs1/run.sh
index bfe5b6594..6c6688b2f 100755
--- a/examples/opencpop/svs1/run.sh
+++ b/examples/opencpop/svs1/run.sh
@@ -32,6 +32,6 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
 fi
 
 if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
-    # synthesize_e2e, vocoder is pwgan by default
-    CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
+    # synthesize_e2e, vocoder is pwgan by default, stage 1 will use hifigan as vocoder
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
 fi