Linly-Talker

Linly-Talker copied to clipboard

webui中的问题

1

作者很感谢你做出这个非常棒的项目，但是我想问的是为什么webui中的智能多轮对话系统，文本对话都不行，视频也生成不了，全部报错

MikeAiJF

比如：运行系统最低配要求是，GPU型号？内存大小？显存大小？cpu型号？硬盘大小？操作系统？等等

JerryDaHeLian

Traceback (most recent call last): File "/root/miniconda3/lib/python3.8/site-packages/gradio/queueing.py", line 495, in call_prediction output = await route_utils.call_process_api( File "/root/miniconda3/lib/python3.8/site-packages/gradio/route_utils.py", line 232, in call_process_api output = await app.get_blocks().process_api( File "/root/miniconda3/lib/python3.8/site-packages/gradio/blocks.py", line 1570, in...

xuquankun

QAnything As LLM Method

4

Integrate QAnything API as a way to obtain LLM response to input question. Assumes QAnything is set up and running in the same machine (localhost) thus did not include support...

SanBingYouYong

api的问题

3

有没有api接入到其他系统 webui.py app.py 启动的是界面 有没有接口传入图片 文本生成视频回来的那种

lxb0425

请问一下，速度怎么样，会很慢吗？相对于每个原始的项目，速度怎么样？

1

hjj-lmx

kkkwjr

使用MuseTalk的example时出现以下错误 Traceback (most recent call last): File "/root/miniconda3/lib/python3.8/site-packages/gradio/queueing.py", line 495, in call_prediction output = await route_utils.call_process_api( File "/root/miniconda3/lib/python3.8/site-packages/gradio/route_utils.py", line 232, in call_process_api output = await app.get_blocks().process_api( File "/root/miniconda3/lib/python3.8/site-packages/gradio/blocks.py", line 1561,...

545089467

使用的是GPT-SoVITS V2，加载模型报错如下，求指导，谢谢！ ``` 模型加载中... /root/Linly-Talker/GPT_SoVITS/pretrained_models/zhiqiang2-e15.ckpt /root/Linly-Talker/GPT_SoVITS/pretrained_models/zhiqiang2_e8_s72.pth Number of parameter: 77.61M Traceback (most recent call last): File "/root/miniconda3/lib/python3.8/site-packages/gradio/queueing.py", line 495, in call_prediction output = await route_utils.call_process_api( File "/root/miniconda3/lib/python3.8/site-packages/gradio/route_utils.py", line 232, in...

levin-go

CG客户端运行webui.py报错

2

通过CG客户端拉取的v4镜像，在jupyterlab里运行webui.py报错 网上说这种报错一般因为cuda pytorch等版本对不上，但是镜像里会出现这种问题吗 win11就装了显卡驱动和docker desktop，wsl-ubuntu根据CG客户端教程装了cg-client和nvidia-docker 镜像里nvcc报告cuda版本为11.8.89 ``` PaddleTTS Error: No module named 'paddlespeech' 如果使用PaddleTTS，请先安装PaddleTTS环境 pip install -r requirements_paddle.txt 默认不使用LLM模型，直接回复问题，同时减少显存占用！ GPT_SoVITS导入失败，原因： Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions...

Heaverno