安装tts-generation-webui遇CUDA相关错误求助

我是GitHub机器学习工具新手，用一键安装程序装完tts-generation-webui后UI能正常显示，但使用Bark语音克隆、Tortoise-TTS这类自定义功能时会报错。

控制台错误信息 #

启动时的警告（通过start_windows.bat启动） #

- 2023-07-23 18:13:18 | WARNING | xformers | WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
    PyTorch 2.0.1+cu118 with CUDA 1108 (you have 2.0.1+cpu)
    Python  3.10.11 (you have 3.10.12)
  Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)
  Memory-efficient attention, SwiGLU, sparse and more won't be available.
  Set XFORMERS_MORE_DETAILS=1 for more details
- 2023-07-23 18:13:18 | WARNING | xformers | Triton is not available, some optimizations will not be enabled. This is just a warning: No module named 'triton'

使用自定义功能时的报错（除Generation (Bark)外） #

Traceback (most recent call last):
  File "C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\installer_files\env\lib\site-packages\gradio\routes.py", line 437, in run_predict
    output = await app.get_blocks().process_api(
  File "C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\installer_files\env\lib\site-packages\gradio\blocks.py", line 1352, in process_api
    result = await self.call_function(
  File "C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\installer_files\env\lib\site-packages\gradio\blocks.py", line 1077, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\installer_files\env\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
    return await get_asynclib().run_sync_in_worker_thread(
  File "C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\installer_files\env\lib\site-packages\anyio\_backends\_asyncio.py", line 877, in run_sync_in_worker_thread
    return await future
  File "C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\installer_files\env\lib\site-packages\anyio\_backends\_asyncio.py", line 807, in run
    result = context.run(func, *args)
  File "C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\tts-generation-webui\src\bark\clone\tab_voice_clone.py", line 222, in generate_voice
    full_generation = get_prompts(wav_file, use_gpu)
  File "C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\tts-generation-webui\src\bark\clone\tab_voice_clone.py", line 87, in get_prompts
    semantic_prompt = get_semantic_prompt(path_to_wav, device)
  File "C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\tts-generation-webui\src\bark\clone\tab_voice_clone.py", line 81, in get_semantic_prompt
    semantic_vectors = get_semantic_vectors(path_to_wav, device)
  File "C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\tts-generation-webui\src\bark\clone\tab_voice_clone.py", line 46, in get_semantic_vectors
    hubert_model = _load_hubert_model(device)
  File "C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\tts-generation-webui\src\bark\clone\tab_voice_clone.py", line 26, in _load_hubert_model
    hubert_model = CustomHubert(
  File "C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\installer_files\env\lib\site-packages\bark_hubert_quantizer\pre_kmeans_hubert.py", line 65, in __init__
    model[0].to(device)
  File "C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\installer_files\env\lib\site-packages\torch\nn\modules\module.py", line 1145, in to
    return self._apply(convert)
  File "C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\installer_files\env\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply
    module._apply(fn)
  File "C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\installer_files\env\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply
    module._apply(fn)
  File "C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\installer_files\env\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply
    module._apply(fn)
  [Previous line repeated 1 more time]
  File "C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\installer_files\env\lib\site-packages\torch\nn\modules\module.py", line 820, in _apply
    param_applied = fn(param)
  File "C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\installer_files\env\lib\site-packages\torch\nn\modules\module.py", line 1143, in convert
    return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
  File "C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\installer_files\env\lib\site-packages\torch\cuda\__init__.py", line 239, in _lazy_init
    raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled

已尝试的无效方法 #

• 更新至PyTorch 2.0
• 手动安装xformers（不清楚安装路径）
• 重装PyTorch

解决建议 #

1. 确认CUDA环境：如果电脑有NVIDIA显卡，先安装对应版本的CUDA Toolkit（建议11.8版本，匹配报错中的cu118）；若无NVIDIA显卡，需强制程序使用CPU运行。
2. 安装带CUDA的PyTorch：进入项目虚拟环境（路径为C:\Users\[CENSORED]\Downloads\one-click-installers-tts-6.0\one-click-installers-tts-6.0\installer_files\env），激活后执行命令：

   pip3 install torch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 --index-url https://download.pytorch.org/whl/cu118
   

3. 安装匹配版本的xformers：在激活的虚拟环境中执行：

   pip install xformers==0.0.20
   

4. 强制CPU运行：若没有NVIDIA显卡，可在启动脚本start_windows.bat中添加--cpu参数，或在UI设置里将设备改为CPU。

内容的提问来源于stack exchange，提问作者Aholicha