zhouwg's Projects
Suno AI's Bark model in C/C++ for fast text-to-speech
This is source code of DeepSpeech(customized DeepSpeech for project KanTV), derived from original Mozilla's DeepSpeech. intend to used as ASR engine for PoC in project KanTV
On-device AI across mobile, embedded and edge for PyTorch
This is source code of my customized FFmpeg, used as multimedia engine for project KanTV. moved into project KanTV since 03-21-2024 and this project is no longer maintained accordingly
This is originial source code of upstream ggml from GGML(Georgi Gerganov Machine Learning).used as Machine Learning engine for project KanTV.
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
workbench for learing&practising AI tech in real scenario on Android device, powered by GGML(Georgi Gerganov Machine Learning) and NCNN(Tencent NCNN) and FFmpeg
a forked llama.cpp of upstream llama.cpp equipped by Georgi Gerganov Machine Learning
customized toolchain for x86-ia32,learning and studying how Linaro create their various toolchain from scratch source code
ncnn is a high-performance neural network inference framework optimized for the mobile platform, used as the second edge-AI inference framework for project KanTV
The minimal opencv for Android, iOS, ARM Linux, Windows, Linux, MacOS, WebAssembly
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
Tensors and Dynamic neural networks in Python with strong GPU acceleration
A media packaging and development framework for VOD and Live DASH and HLS applications, supporting Common Encryption for Widevine and other DRM Systems.
Stable Diffusion in pure C/C++
This is originial source code of upstream whisper.cpp,based on GGML(Georgi Gerganov Machine Learning).used as ASR and realtime AI subtitle engine for project KanTV