From bef985c6fc35f6aefbc42e64b7ba3c04b2a4a237 Mon Sep 17 00:00:00 2001
From: nyx-c-language <nyxchaoji123@163.com>
Date: Mon, 24 Mar 2025 19:20:50 +0800
Subject: [PATCH] fix the errors 2025/3/24

---
 examples/csmsc/tts3/README_cn.md  | 8 ++++++--
 examples/csmsc/tts3_rhy/README.md | 1 -
 examples/csmsc/tts3_rhy/run.sh    | 3 ++-
 3 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/examples/csmsc/tts3/README_cn.md b/examples/csmsc/tts3/README_cn.md
index 70d50b90a..c68c64d9b 100644
--- a/examples/csmsc/tts3/README_cn.md
+++ b/examples/csmsc/tts3/README_cn.md
@@ -115,7 +115,7 @@ pwg_baker_ckpt_0.4
 ```bash
 CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name}
 ```
-`--stage` 用于合成过程中控制声码器模型，可取值为 `0` 或 `1`，分别对应使用 `pwgan` 或 `hifigan` 模型作为声码器。
+`--stage` 参数用于控制合成过程中使用的声码器模型。通过设置 `0-4` 阶段值，可以选择以下声码器之一：`pwgan`、`multi band melgan`、`style melgan`、`hifigan` 或 `wavernn`。
 
 ```text
 usage: synthesize.py [-h]
@@ -164,8 +164,12 @@ optional arguments:
 `./local/synthesize_e2e.sh` 调用 `${BIN_DIR}/../synthesize_e2e.py`，即可从文本文件中合成波形。
 
 ```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` 参数用于控制合成过程中使用的声码器模型。通过设置阶段值 `0、1、3、4`，可以选择以下声码器之一：`pwgan`、`multi band melgan`、`hifigan` 或 `wavernn`。
+
+
 ```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/csmsc/tts3_rhy/README.md b/examples/csmsc/tts3_rhy/README.md
index d5f6b71a3..ae250f080 100644
--- a/examples/csmsc/tts3_rhy/README.md
+++ b/examples/csmsc/tts3_rhy/README.md
@@ -20,7 +20,6 @@ Run the command below to
 3. train the model.
 4. synthesize wavs.
     - synthesize waveform from `metadata.jsonl`.
-    - use stage `1,3,4` to select the vocoder to use {`multi band melgan`, `hifigan`, `wavernn`}
     - synthesize waveform from a text file.
 5. inference using the static model.
 ```bash
diff --git a/examples/csmsc/tts3_rhy/run.sh b/examples/csmsc/tts3_rhy/run.sh
index 48dff3038..294ceded5 100755
--- a/examples/csmsc/tts3_rhy/run.sh
+++ b/examples/csmsc/tts3_rhy/run.sh
@@ -28,7 +28,8 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
 fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
-    # synthesize, vocoder is pwgan by default stage 0, stage 1 will use hifigan as vocoder
+    # synthesize, vocoder is pwgan by default stage 0
+    # use stage 1-4 to select the vocoder to use {multi band melgan, style melgan, hifigan, wavernn}
     CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
 fi