wxzz0151

编译raymarching.cu的时候出现错误：fatal error C1189: #error: You need C++17 to compile PyTorch

6

C:\Users\WXZZ\Desktop\metahuman-stream-main>python app.py Traceback (most recent call last): File "C:\Users\WXZZ\Desktop\metahuman-stream-main\ernerf\raymarching\raymarching.py", line 10, in import _raymarching_face as _backend ModuleNotFoundError: No module named '_raymarching_face' During handling of the above exception, another exception occurred:...

Error: Cannot connect to host localhost:1985 ssl:default [远程计算机拒绝网络连接。请问windows下如何启动srs???

3

Error: Cannot connect to host localhost:1985 ssl:default [远程计算机拒绝网络连接。] Traceback (most recent call last): File "C:\Users\WXZZ\Desktop\metahuman-stream-main\app.py", line 429, in run_server(web.AppRunner(appasync)) File "C:\Users\WXZZ\Desktop\metahuman-stream-main\app.py", line 426, in run_server loop.run_until_complete(run(opt.push_url)) File "D:\Anaconda3\Lib\asyncio\base_events.py", line 653,...

基于LLM模型实现与metahuman克隆数字人对话，过程总结

7

前面文章参考：克隆人像和声音，metahuman与GPT-SoVITS接口打通，过程汇总（https://github.com/lipku/metahuman-stream/issues/210） 1.流程概要：前台语音及上传到后台->asr语音识别->LLM对话模型->metahuman呈现 2.增加asr语音识别库 下载模型：https://openaipublic.azureedge.net/main/whisper/models/9ecf779972d90ba49c06d968637d720dd632c55bbf19d441fb42bf17a411e794/small.pt 把模型名称改为：whisper_small.pt，在metahuman工程根目录新建目录“sound”,并把模型文件复制到“sound”目录下。  在“sound”目录下新建：speech2text.py 程序文件，代码实现如下： import os import whisper os.environ["HF_ENDPOINT"] = "https://hf-mirror.com" os.environ["CUDA_VISIBLE_DEVICES"] = "2" os.environ["TF_ENABLE_ONEDNN_OPTS"] = "0" model = whisper.load_model("sound/whisper_small.pt") #['tiny.en', 'tiny', 'base.en', 'base', 'small.en', 'small',...

run：pyspur init，error：No module named 'CommandNotFound'

1


LoadSRT和PreViewAudio出现Conflict问题，无法增加到工作流中 ，请问什么原因。如何解决？ 显示错误： Error message occurred while importing the 'ComfyUI-GPT_SoVITS' module. Traceback (most recent call last): File "D:\AISoftware\ComfyUI\resources\ComfyUI\nodes.py", line 2131, in load_custom_node module_spec.loader.exec_module(module) File "", line 999, in exec_module File...