MCPcopy Index your code
hub / github.com/Holasyb918/HeyGem-Linux-Python-Hack

github.com/Holasyb918/HeyGem-Linux-Python-Hack @main

Chat with this repo
repository ↗ · DeepWiki ↗ · + Follow
88 symbols 287 edges 29 files 21 documented · 24%
What it actually does AI analysis from the code graph — generated when you open this
loading…
README

License Python Linux

中文 | English


HeyGem-Linux-Python-Hack

Introduction

[HeyGem-Linux-Python-Hack] is a Python-based digital human project extracted from HeyGem.ai. It is designed to run directly on Linux systems, eliminating the need for Docker and Windows. Our goal is to provide a easier-to-deploy, and user-friendly digital human solution.

Feel free to Star us if you find this project useful!
Please submit an Issue if you run into any problems!

Key Features

  • No Docker Required: Runs directly on Linux systems, simplifying the deployment process.
  • No Windows Required: Fully developed and tested on Linux.
  • Python Powered: Developed using the Python language, making it easy to understand and extend.
  • Developer-Friendly: Easy to use, and easy to extend.

Getting Started

Installation

Please ensure that Python 3.8 is installed on your Linux system. Then, you can install the project dependencies using pip:

pip install -r requirements.txt

Usage

Clone this repository to your local machine:

git clone https://github.com/Holasyb918/HeyGem-Linux-Python-Hack
cd HeyGem-Linux-Python-Hack
bash download.sh

Getting Started

  • Audio and video examples that can be used for the demo are already provided in the repo, and the code can be run directly.

Command:

python run.py
  • If you want to use your own data, you can pass parameters externally. Please note that the path is a local file and only supports relative paths.

command:

python run.py --audio_path example/audio.wav --video_path example/video.mp4

gradio:

python app.py
# Please wait until processor init done.

Contributing

Contributions are welcome!

License

This project is licensed under the HeyGem.ai License.

Core symbols most depended-on inside this repo

spectrogram
called by 7
wenet/tools/_extract_feats.py
preempahsis
called by 3
wenet/tools/_extract_feats.py
power_spec2mel
called by 3
wenet/tools/_extract_feats.py
shuffle
called by 2
landmark2face_wy/data/l2faceaudio_dataset.py
shuffle
called by 2
landmark2face_wy/data/l2faceaudio512_dataset.py
find_dataset_using_name
called by 2
landmark2face_wy/data/__init__.py
shuffle
called by 2
landmark2face_wy/data/Facereala3dmmexpwenet512_dataset.py
shuffle
called by 2
landmark2face_wy/data/Facereala3dmmexp512_dataset.py

Shape

Function 53
Method 28
Class 7

Languages

Python100%

Modules by API surface

wenet/tools/_extract_feats.py31 symbols
landmark2face_wy/data/Facereala3dmmexpwenet512_dataset.py9 symbols
landmark2face_wy/data/Facereala3dmmexp512_dataset.py9 symbols
landmark2face_wy/data/__init__.py8 symbols
landmark2face_wy/data/l2faceaudio_dataset.py7 symbols
landmark2face_wy/data/l2faceaudio512_dataset.py7 symbols
app.py5 symbols
wenet/utils/cmvn.py3 symbols
run.py3 symbols
landmark2face_wy/models/__init__.py3 symbols
model_lib/model_base.py2 symbols
check_env/check_onnx_cuda.py1 symbols

For agents

$ claude mcp add HeyGem-Linux-Python-Hack \
  -- python -m otcore.mcp_server <graph>

⬇ download graph artifact