常见问题 ❓

字数

589 字

阅读

4 分钟

安装使用过程问题汇总

安装

使用 gpu 显卡

解决方法

nvidia-smi

参考配置

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2024 NVIDIA Corporation
Built on Thu_Jun__6_02:18:23_PDT_2024
Cuda compilation tools, release 12.5, V12.5.82
Build cuda_12.5.r12.5/compiler.34385749_0
Sat Jul 12 14:42:54 2025
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 560.35.03            Driver Version: 560.35.03      CUDA Version: 12.6     |
|---------------------------------------+------------------------+----------------------+
| GPU  Name               Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf        Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                       |                        |               MIG M. |
|=======================================+========================+======================|
|   0  Tesla T4                     Off |   00000000:00:04.0 Off |                    0 |
| N/A   39C    P8            9W /   70W |       1MiB /  15360MiB |      0%      Default |
|                                       |                        |                  N/A |
+---------------------------------------+------------------------+----------------------+
|   1  Tesla T4                     Off |   00000000:00:05.0 Off |                    0 |
| N/A   41C    P8            9W /   70W |       1MiB /  15360MiB |      0%      Default |
|                                       |                        |                  N/A |
+---------------------------------------+------------------------+----------------------+

参考版本

pip install torch==2.6.0+cu124 torchvision==0.21.0+cu124 torchaudio==2.6.0+cu124 --extra-index-url https://download.pytorch.org/whl/cu124

使用

启动报错

使用方式

启动透传报错

解决方法

PyngrokNgrokError:
The ngrok process errored on start: authentication failed:
Your account is limited to 1 simultaneous ngrok agent sessions.
You can run multiple simultaneous tunnels from a single agent session by defining the tunnels in your agent configuration file and starting them with the command `ngrok start --all`.
Read more about the agent configuration file: https://ngrok.com/docs/secure-tunnels/ngrok-agent/reference/config
You can view your current agent sessions in the dashboard:
https://dashboard.ngrok.com/agents ERR_NGROK_108.

启动出现上述错误，则需要 进入 Ngrok DashBoard https://dashboard.ngrok.com/agents

关闭正在运行的代理，重新运行

配音语言配置

使用方式

默认内置 10 种语言，支持自定义添加节点

webapp\data\settings.json

{
    "locales": [
        {
            "name": "中国",
            "locale": "zh-CN",
            "country": "China",
            "enable": true
        }
    ]
    // ...
}

使用 Gemini 异常

解决方法

Retrying 1 time(s), translation_json -> Your location is not supported by google-generativeai at the moment. Try to use ChatVertexAI LLM from langchain_google_vertexai., waiting 5.0 seconds before retrying.

• 出现 Your location is not supported 尝试切换代理地区即可
• 推荐代理，见 《JustMySocks》 章节

模型

模型下载失败

解决方法

An error occured while synchronizing the model Systran/faster-whisper-large-v3 from the Hugging Face Hub:
An error happened while trying to locate the files on the Hub and we cannot find the appropriate snapshot folder for the
specified revision on the local disk. Please check your internet connection and try again.
Trying to load the model directly from the local cache, if it exists.

通过国内镜像下载模型

说话人调用错误

解决方法

2025-04-18 07:29:31.094 | INFO whisper_.py:102 - Loading Speaker model on device cuda
2025-04-18 07:29:31.865 | ERROR whisper_.py:106 - Error: 401 Client Error: Unauthorized for url: https://hf-mirror.com/pyannote/speaker-diarization-3.1/resolve/main/config.yaml (Request ID: Root=1-6801ff5b-0270fbd846adbc761e229ace;fddee4c5-7f49-4739-bba3-42cbc47dca6e)

1. 前往并接受 pyannote/segmentation-3.0 的用户协议
2. 接受 pyannote/speaker-diarization-3.1 的用户协议
3. 前往并获取访问令牌：huggingface.co/settings/tokens