#1400 videotrans.configure._except.StopRetry: GPT-SoVITS error-1:{'message': 'tts failed', 'Exception': '

39.184.**8 Posted at: 9 months ago

GPT-SoVITS error-1:{'message': 'tts failed', 'Exception': '"slow_conv2d_cpu" not implemented for \'Half\''} :
Traceback (most recent call last):
File "videotrans\util\ListenVoice.py", line 18, in run
File "videotrans\tts\__init__.py", line 279, in run
File "videotrans\tts\_base.py", line 177, in run
File "videotrans\tts\_gptsovits.py", line 115, in _item_task
File "tenacity\__init__.py", line 338, in wrapped_f
File "tenacity\__init__.py", line 477, in call
File "tenacity\__init__.py", line 378, in iter
File "tenacity\__init__.py", line 400, in
File "concurrent\futures\_base.py", line 439, in result
File "concurrent\futures\_base.py", line 391, in __get_result
File "tenacity\__init__.py", line 480, in call
File "videotrans\tts\_gptsovits.py", line 99, in _run
videotrans.configure._except.StopRetry: GPT-SoVITS error-1:{'message': 'tts failed', 'Exception': '"slow_conv2d_cpu" not implemented for \'Half\''}


=
system:Windows-10-10.0.19045-SP0
version:v3.84
frozen:True
language:zh
root_dir:E:/VideoTrans384

1 Replies

#1 DeepSeek reply at 9 months ago

这个错误是由于 GPT-SoVITS 在 CPU 上运行时无法处理半精度(Half)数据类型导致的。请按以下步骤解决:

  1. 启用 CUDA 加速:在软件主界面的"开始执行"区域,确保勾选"CUDA加速"复选框。
  2. 如果无法使用 GPU

    • 在 GPT-SoVITS 的配置文件中将数据类型从 float16 改为 float32
    • 或者重新启动 GPT-SoVITS 服务时添加参数强制使用 float32 精度
  3. 替代方案:如果上述方法无效,可以暂时使用其他配音渠道,如 Edge-TTS、Azure TTS 或 OpenAI TTS。

错误信息表明系统尝试在 CPU 上执行需要 GPU 支持的半精度计算,启用 CUDA 加速是最直接的解决方案。

Thinking...
Post Your Reply
Open source and free maintenance is not easy. If this project is helpful to you, please consider making a small donation to help the project continue to maintain and update.

Dondate via ko-fi.com

Related resource