常见问题
字数
1414 字
阅读
8 分钟
安装使用问题汇总
目录
项目目录 new
说明 CreatorBox 文件夹下的 目录 和 文件
- webapp 应用目录
- cache 缓存
- data 数据
- download 下载
- dubb 配音
- test 视频目录
- _v1 输出目录
- draft 草稿目录
- stems 音轨分离
- voices 人声处理
- test.mp4 来源视频
- test.png 来源封面
- test.srt 来源字幕
- test.wav 来源音频
- test 视频目录
- extensions 扩展
- logs 日志
- sample 示例
- spk 音色样例
- temp 临时
- tts 合成试听
- upload 上传
模型目录 new
说明 目录
- models
- creatorbox
- huggingface
- modelscope
- torch
首次运行会检测下载模型,自动下载到
models目录下自定义下载位置,可以通过
CREATORBOX_MODEL环境变量指定,或者在/settings页指定,重启后生效
安装
显卡使用 new
目前仅支持 N卡,官方下载 | 镜像下载
参考版本
2.6.0+cu126
bash
uv pip install torch==2.6.0+cu126 torchvision==0.21.0+cu126 torchaudio==2.6.0+cu126 --extra-index-url https://download.pytorch.org/whl/cu126
uv pip install torch==2.6.0+cu126 torchvision==0.21.0+cu126 torchaudio==2.6.0+cu126 --extra-index-url https://mirrors.nju.edu.cn/pytorch/whl/cu126参考配置
bash
nvidia-smilogs
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 |
+---------------------------------------+------------------------+----------------------+启动
启动报错
解决方法
- 启动报错
RuntimeError: this license key is expired,请尝试更新
bash
# git reset --hard
# git clean -fd
git pullWindows直接双击start.bat或桌面快捷方式运行,请根据实际配置调整环境
bash
REM Execute script
set SCRIPT_CMD=uv run --extra gpu
set SCRIPT_PATH=cli.py
set SCRIPT_ARGS=start -h 0.0.0.0 -p 8000
if "%~1"=="--debug" (
set SCRIPT_ARGS=%SCRIPT_ARGS% --debug
) - 默认使用
cpu运行,使用gpu需添加--extra gpu参数
启动环境
解决方法
某些场景下,需要进行环境激活,以 D:\Program Files\CreatorBox 为例
- 主环境
bash
D:; cd "D:\Program Files\CreatorBox\creatorbox"; .\.venv\Scripts\activate.ps1- 扩展环境
bash
# iopaint
D:; & cd "D:\Program Files\CreatorBox\creatorbox\extensions\iopaint"; .\.venv\Scripts\activate.ps1
# voxcpm
D:; & cd "D:\Program Files\CreatorBox\creatorbox\extensions\voxcpm"; .\.venv\Scripts\activate.ps1
# index_tts
D:; & cd "D:\Program Files\CreatorBox\creatorbox\extensions\index_tts"; .\.venv\Scripts\activate.ps1
# cosyvoice
D:; & cd "D:\Program Files\CreatorBox\creatorbox\extensions\cosyvoice"; .\.venv\Scripts\activate.ps1
# gpt_sovits
D:; & cd "D:\Program Files\CreatorBox\creatorbox\extensions\gpt_sovits"; .\.venv\Scripts\activate.ps1正常结果返回
log
(creatorbox) PS D:\Program Files\CreatorBox\creatorbox>
(iopaint) PS D:\Program Files\CreatorBox\creatorbox\extensions\voxcpm
(index_tts) PS D:\Program Files\CreatorBox\creatorbox\extensions\index_tts>
(cosyvoice) PS D:\Program Files\CreatorBox\creatorbox\extensions\cosyvoice>
(gpt_sovits) PS D:\Program Files\CreatorBox\creatorbox\extensions\gpt_sovits>- 主环境与扩展环境隔离,如果环境依赖不兼容,可以在对应环境下安装依赖,不会影响其他环境
- (xxx) 括号内为当前环境,后面为当前路径
- 以
>结尾表示当前路径为环境所在路径,输入命令后会在当前环境下执行 - 推荐使用 Windows Terminal 终端
使用
请求已过期 new
解决方法
log
在登录/注册出现时,点击 '忘记密码',收到邮件后重新设置密码后进行登录设备未就绪
解决方法
log
PermissionError: [WinError 21] 设备未就绪如果安装在系统盘,需要以管理员身份运行,不建议
多语言配置
使用方式
默认内置 10 种语言,支持自定义添加节点
json
{
"locales": [
{
"name": "中国",
"locale": "zh-CN",
"country": "China",
"enable": true
}
]
// ...
} VPN 异常
解决方法
log
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等类似描述,说明 IP 被封,尝试切换代理地区 - 推荐代理,见 《JustMySocks》 章节
Ngrok 报错
解决方法
log
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
模型
模型下载失败
解决方法
log
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.说话人调用错误
解决方法
log
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)- 前往并接受
pyannote/segmentation-3.0的用户协议 - 接受
pyannote/speaker-diarization-3.1的用户协议 - 前往并获取访问令牌:
huggingface.co/settings/tokens
