FAQ ❓

Summary of common issues during installation and usage

Installation

Using gpu graphics card

Solution

Reference Configuration

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 |
+---------------------------------------+------------------------+----------------------+

Reference Version

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

Error when installing Cython pynini

Solution

conda install -c conda-forge Cython==3.0.12
conda install -c conda-forge pynini==2.1.5

or

conda config --add channels conda-forge
conda install Cython==3.0.12
conda install pynini==2.1.5

Usage

Startup Error

Solution

• If you see RuntimeError: this license key is expired, try forcing an update:

python cli.py update --force

• If you see RuntimeError: [WinError 10060]...(1:11076), Please try restarting:

python cli.py start

• On Windows systems, simply double-click start.bat to run.

Switching interface language

Currently only Chinese and English are supported. Add the ?lang= parameter. Gradually adapting to English...

Usage

• http://127.0.0.1:8000?lang=zh 中文
• http://127.0.0.1:8000?lang=en English

Configuring dubbing languages

10 languages are built in by default, and custom nodes can be added.

Usage

webapp\data\settings.json

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

Model

Model Download Failure

Solution

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.

Download models via domestic mirror

Speaker Invocation Error

Solution

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. Go to and accept the user agreement for pyannote/segmentation-3.0
2. Accept the user agreement for pyannote/speaker-diarization-3.1
3. Go to and obtain an access token: huggingface.co/settings/tokens