CosyVoice - 阿里最新开源语音克隆、文本转语音项目 支持情感控制及粤语 本地一键整合包下载

luju***

原来这是第一个版本，终于找到源头了，真不容易

kko***

来下载本体

qj***

有用过的吗  说说感受

hid***

我刚下完，运行后提示：

failed to import ttsfrd, use WeTextProcessing instead
Traceback (most recent call last):
  File "E:\迅雷云盘\CosyVoice-V7\cosyvoice\cli\frontend.py", line 28, in <module>
    import ttsfrd
ModuleNotFoundError: No module named 'ttsfrd'

少了ttsfrd模块，有人遇到同样问题吗

sug***

不支持50系有点难受

49***

大大大大大大

dai***

好资源，试试

pur***

求助楼主老师，我运行CosyVoice-V3和GPT-SoVITS-v3都会显示“系统检测到在一个调用中尝试使用指针参数时的无效指针地址”是怎么回事啊

无言***

pureuu 发表于 2025-6-20 11:46
求助楼主老师，我运行CosyVoice-V3和GPT-SoVITS-v3都会显示“系统检测到在一个调用中尝试使用指针参数时的 ...

贴出详细报错代码

pur***

无言以对 发表于 2025-6-20 11:48
贴出详细报错代码

您帮助看一下，谢谢您
以下我把urlhttp换成了_______
-----------------------------------------------
更多好玩的AI应用，访问 _______
CosyVoice WebUI正在启动中，请稍后
-----------------------------------------------
E:\G\CosyVoice-V3\CosyVoice-V3\cosyvoice\cli\cosyvoice.py:17: UserWarning: torchaudio._backend.set_audio_backend has been deprecated. With dispatcher enabled, this function is no-op. You can remove the function call.
  torchaudio.set_audio_backend('soundfile')
2025-06-20 12:07:53,900 - modelscope - INFO - PyTorch version 2.3.1+cu121 Found.
2025-06-20 12:07:53,903 - modelscope - INFO - Loading ast index from C:\Users\Administrator\.cache\modelscope\ast_indexer
2025-06-20 12:07:54,041 - modelscope - INFO - Loading done! Current index file version is 1.15.0, with md5 d3ff66ded160363978e9d67503f9f177 and a total number of 980 components indexed
E:\G\CosyVoice-V3\CosyVoice-V3\python\Lib\site-packages\torch\_jit_internal.py:739: FutureWarning: ignore(True) has been deprecated. TorchScript will now drop the function call on compilation. Use torch.jit.unused now. {}
  warnings.warn(
E:\G\CosyVoice-V3\CosyVoice-V3\python\Lib\site-packages\torch\cuda\__init__.py:749: UserWarning: CUDA initialization: The NVIDIA driver on your system is too old (found version 11040). Please update your GPU driver by downloading and installing a new version from the _______/Download/index.aspx Alternatively, go to: _______ to install a PyTorch version that has been compiled with your version of the CUDA driver. (Triggered internally at ..\c10\cuda\CUDAFunctions.cpp:108.)
  return torch._C._cuda_getDeviceCount() if nvml_count < 0 else nvml_count
E:\G\CosyVoice-V3\CosyVoice-V3\python\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)
2025-06-20 12:08:02,475 INFO input frame rate=50
E:\G\CosyVoice-V3\CosyVoice-V3\python\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.")
E:\G\CosyVoice-V3\CosyVoice-V3\cosyvoice\dataset\processor.py:24: UserWarning: torchaudio._backend.set_audio_backend has been deprecated. With dispatcher enabled, this function is no-op. You can remove the function call.
  torchaudio.set_audio_backend('soundfile')
2025-06-20 12:08:09,389 DEBUG Using proactor: IocpProactor
E:\G\CosyVoice-V3\CosyVoice-V3\python\Lib\site-packages\gradio\components\base.py:193: UserWarning: 'scale' value should be an integer. Using 0.5 will cause issues.
  warnings.warn(
E:\G\CosyVoice-V3\CosyVoice-V3\python\Lib\site-packages\gradio\components\base.py:193: UserWarning: 'scale' value should be an integer. Using 0.25 will cause issues.
  warnings.warn(
E:\G\CosyVoice-V3\CosyVoice-V3\python\Lib\site-packages\gradio\layouts\column.py:55: UserWarning: 'scale' value should be an integer. Using 0.25 will cause issues.
  warnings.warn(
2025-06-20 12:08:09,592 DEBUG Using proactor: IocpProactor
Running on local _______127.0.0.1:9886
2025-06-20 12:08:09,616 DEBUG load_ssl_context verify=True cert=None trust_env=True http2=False
2025-06-20 12:08:09,617 DEBUG load_verify_locations cafile='E:\\G\\CosyVoice-V3\\CosyVoice-V3\\python\\Lib\\site-packages\\certifi\\cacert.pem'
2025-06-20 12:08:09,799 DEBUG connect_tcp.started host='127.0.0.1' port=9886 local_address=None timeout=None socket_options=None
2025-06-20 12:08:09,799 DEBUG connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x00000269182BD250>
2025-06-20 12:08:09,799 ERROR Accept failed on a socket
socket: <asyncio.TransportSocket fd=4468, family=2, type=1, proto=6, laddr=('127.0.0.1', 9886)>
Traceback (most recent call last):
  File "E:\G\CosyVoice-V3\CosyVoice-V3\python\Lib\asyncio\proactor_events.py", line 843, in loop
    conn, addr = f.result()
                 ^^^^^^^^^^
  File "E:\G\CosyVoice-V3\CosyVoice-V3\python\Lib\asyncio\windows_events.py", line 854, in _poll
    value = callback(transferred, key, ov)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\G\CosyVoice-V3\CosyVoice-V3\python\Lib\asyncio\windows_events.py", line 603, in finish_accept
    return conn, conn.getpeername()
                 ^^^^^^^^^^^^^^^^^^
OSError: [WinError 10014] 系统检测到在一个调用中尝试使用指针参数时的无效指针地址。
2025-06-20 12:08:09,799 DEBUG send_request_headers.started request=<Request [b'GET']>
2025-06-20 12:08:09,801 ERROR Task exception was never retrieved
future: <Task finished name='Task-5' coro=<IocpProactor.accept.<locals>.accept_coro() done, defined at E:\G\CosyVoice-V3\CosyVoice-V3\python\Lib\asyncio\windows_events.py:605> exception=OSError(14, '系统检测到在一个调用中尝试使用指针参数时 的无效指针地址。', None, 10014, None)>
Traceback (most recent call last):
  File "E:\G\CosyVoice-V3\CosyVoice-V3\python\Lib\asyncio\windows_events.py", line 608, in accept_coro
    await future
OSError: [WinError 10014] 系统检测到在一个调用中尝试使用指针参数时的无效指针地址。
2025-06-20 12:08:09,801 DEBUG send_request_headers.complete
2025-06-20 12:08:09,802 DEBUG send_request_body.started request=<Request [b'GET']>
2025-06-20 12:08:09,802 DEBUG send_request_body.complete
2025-06-20 12:08:09,802 DEBUG receive_response_headers.started request=<Request [b'GET']>