From 14191901cdb7e791d8fee1ff31dffe107f9e28fb Mon Sep 17 00:00:00 2001
From: huang yutong <3565724239@qq.com>
Date: Sat, 18 Apr 2026 17:10:56 +0800
Subject: [PATCH] =?UTF-8?q?fix:=20=E4=BF=AE=E5=A4=8D=E5=A4=9A=E4=B8=AA?=
 =?UTF-8?q?=E6=A8=A1=E5=9D=97=E4=B8=AD=E7=9A=84=E7=8B=AC=E7=AB=8B=20bug=20?=
 =?UTF-8?q?(#2755)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

1. 修复 sync_buffer 中除以函数对象而非调用结果（distrib.py）
   - `buffer.data /= world_size` 中 world_size 是函数，缺少 ()，
     导致 TypeError 使分布式训练 buffer 同步失败

2. 修复 istft 函数缺少 return 语句（spec_utils.py）
   - 函数计算了结果但未返回，调用者始终得到 None

3. 修复 cut0 返回字面量 "/n" 而非换行符 "\n"（text_segmentation_method.py）
   - 导致后续 text.split("\n") 无法正确切分，字面 /n 被当作文本内容

4. 修复粤语 ASR 的 vad/punc model_revision 被无条件覆盖（funasr_asr.py）
   - 粤语分支将 vad_model_revision 设为空（因不使用 VAD/标点模型），
     但 if/else 外的赋值将其覆盖为 "v2.0.4"，传入错误的 revision 参数

Made-with: Cursor
---
 GPT_SoVITS/TTS_infer_pack/text_segmentation_method.py | 2 +-
 GPT_SoVITS/module/distrib.py                          | 2 +-
 tools/asr/funasr_asr.py                               | 3 +--
 tools/uvr5/lib/lib_v5/spec_utils.py                   | 2 ++
 4 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/GPT_SoVITS/TTS_infer_pack/text_segmentation_method.py b/GPT_SoVITS/TTS_infer_pack/text_segmentation_method.py
index fda70a49..cf28f3fb 100644
--- a/GPT_SoVITS/TTS_infer_pack/text_segmentation_method.py
+++ b/GPT_SoVITS/TTS_infer_pack/text_segmentation_method.py
@@ -92,7 +92,7 @@ def cut0(inp):
     if not set(inp).issubset(punctuation):
         return inp
     else:
-        return "/n"
+        return "\n"
 
 
 # 凑四句一切
diff --git a/GPT_SoVITS/module/distrib.py b/GPT_SoVITS/module/distrib.py
index cabf8f8a..e96f8e00 100644
--- a/GPT_SoVITS/module/distrib.py
+++ b/GPT_SoVITS/module/distrib.py
@@ -87,7 +87,7 @@ def sync_buffer(buffers, average=True):
     for buffer, handle in handles:
         handle.wait()
         if average:
-            buffer.data /= world_size
+            buffer.data /= world_size()
 
 
 def sync_grad(params):
diff --git a/tools/asr/funasr_asr.py b/tools/asr/funasr_asr.py
index 6a5c9989..b4ddce9e 100644
--- a/tools/asr/funasr_asr.py
+++ b/tools/asr/funasr_asr.py
@@ -39,6 +39,7 @@ def create_model(language="zh"):
             local_dir="tools/asr/models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
         )
         model_revision = "v2.0.4"
+        vad_model_revision = punc_model_revision = "v2.0.4"
     elif language == "yue":
         path_asr = "tools/asr/models/speech_UniASR_asr_2pass-cantonese-CHS-16k-common-vocab1468-tensorflow1-online"
         snapshot_download(
@@ -51,8 +52,6 @@ def create_model(language="zh"):
     else:
         raise ValueError(f"{language} is not supported")
 
-    vad_model_revision = punc_model_revision = "v2.0.4"
-
     if language in funasr_models:
         return funasr_models[language]
     else:
diff --git a/tools/uvr5/lib/lib_v5/spec_utils.py b/tools/uvr5/lib/lib_v5/spec_utils.py
index 4d987cd8..d2d2bf34 100644
--- a/tools/uvr5/lib/lib_v5/spec_utils.py
+++ b/tools/uvr5/lib/lib_v5/spec_utils.py
@@ -485,6 +485,8 @@ def istft(spec, hl):
     wave_right = librosa.istft(spec_right, hop_length=hl)
     wave = np.asfortranarray([wave_left, wave_right])
 
+    return wave
+
 
 if __name__ == "__main__":
     import argparse