jinqinn

经过千辛万苦的修改部分Pytorch-On-Angel master分支源码，使其python代码能够运行起来，但是angel的代码却出现ArrayIndexOutOfBoundsException，帮忙看看是哪里出错啦:( 1. 使用脚本生成pt文件： ./gen_pt_model.sh python/recommendation/deepfm.py --input_dim 148 --n_fields 13 --embedding_dim 10 --fc_dims 10 5 1 2. 上传项目中的census_148d_train.libsvm.tmp到hdfs 3. 报错(公司无法链接外网，只能截图)：  4. 提交命令： 

how can i use port 9300 to connect elasticsearch cluster?

3

i want to use transportclient api to connect es, but it doesnot work. help me :(

CMake error: add_subdirectory given source "pytorch_scatter-2.0.5" which is not an existing directory

1

hey, guys, I got a error at make stage -- The C compiler identification is GNU 6.3.0 -- The CXX compiler identification is GNU 6.3.0 -- Check for working C...

support silence mode

3

如何支持静音闭嘴功能

实时推理支持音频数据流

5

whisper_feature = audio_processor.audio2feat(stream) whisper_chunks = audio_processor.feature2chunks(feature_array=whisper_feature, fps=fps) 目前realtime_inference代码中的音频是基于音频文件来操作的，如何支持GPT-SOVits等实时音频流来进行实时推理呢？

bad inference result

2

prompt: a close-up shot of a woman standing in a dimly lit room. she is wearing a traditional chinese outfit, which includes a red and gold dress with intricate designs...