cosyvoice2.0本地部署报错no valid model_type等错误

Question

windows本地部署cosyvoice2.0，按照网上的教程conda下创建环境，并下载模型。运行python webui.py后报错

Sliding Window Attention is enabled but not implemented for `sdpa`; unexpected results may be encountered.
D:\Programs\anaconda3\envs\cosyvoice\lib\site-packages\diffusers\models\lora.py:393: FutureWarning: `LoRACompatibleLinear` is deprecated and will be removed in version 1.0.0. Use of `LoRACompatibleLinear` is deprecated. Please switch to PEFT backend by installing PEFT: `pip install peft`.
  deprecate("LoRACompatibleLinear", "1.0.0", deprecation_message)
2025-10-09 16:37:30,238 INFO input frame rate=25
D:\Programs\anaconda3\envs\cosyvoice\lib\site-packages\torch\nn\utils\weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.
  warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.")
Traceback (most recent call last):
  File "D:\job\AI\CosyVoice\webui.py", line 188, in <module>
    cosyvoice = CosyVoice(args.model_dir)
  File "D:\job\AI\CosyVoice\cosyvoice\cli\cosyvoice.py", line 37, in __init__
    raise ValueError('{} not found!'.format(hyper_yaml_path))
ValueError: pretrained_models/CosyVoice2-0.5B/cosyvoice.yaml not found!

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "D:\job\AI\CosyVoice\webui.py", line 191, in <module>
    cosyvoice = CosyVoice2(args.model_dir)
  File "D:\job\AI\CosyVoice\cosyvoice\cli\cosyvoice.py", line 156, in __init__
    self.frontend = CosyVoiceFrontEnd(configs['get_tokenizer'],
  File "D:\job\AI\CosyVoice\cosyvoice\cli\frontend.py", line 66, in __init__
    self.frd = ttsfrd.TtsFrontendEngine()
AttributeError: module 'ttsfrd' has no attribute 'TtsFrontendEngine'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "D:\job\AI\CosyVoice\webui.py", line 193, in <module>
    raise TypeError('no valid model_type!')
TypeError: no valid model_type!

请问有人部署时遇见过这个问题吗，要怎么解决？

Answer 1

阿里嘎多学长整理AIGC生成，因移动端显示问题导致当前答案未能完全显示，请使用PC端查看更加详细的解答过程

问题分析

根据你的描述，cosyvoice2.0本地部署在Windows系统上，使用conda创建环境并下载模型后，运行python webui.py时报错。错误信息包括no valid model_type和Sliding Window Attention is enabled。

解决方案

1. 检查模型下载: 确保模型下载成功，并且模型类型（model_type）正确。可以尝试重新下载模型或检查模型文件是否完整。
2. 检查环境配置: 确保conda环境配置正确，包括Python版本、依赖包等。可以尝试重新创建环境或检查环境配置文件。
3. 检查代码: 检查webui.py文件是否有任何错误或不兼容的代码。可以尝试重新运行代码或检查代码是否有任何更新。
4. 检查错误信息: 错误信息中提到Sliding Window Attention is enabled，这可能是cosyvoice2.0的特定配置问题。可以尝试禁用此功能或检查配置文件是否正确。

核心代码

如果你需要检查模型下载或环境配置，可以尝试以下代码：

import os
import conda

# 检查模型下载
model_path = 'path/to/model'
if not os.path.exists(model_path):
    print('模型下载失败')
else:
    print('模型下载成功')

# 检查环境配置
env_name = 'env_name'
env = conda.Env.load(env_name)
print(env)

如果你需要检查代码，可以尝试以下代码：

import webui

# 检查代码
try:
    webui.run()
except Exception as e:
    print(e)

请注意，这些代码仅供参考，具体解决方案可能需要根据你的具体情况进行调整。