Michael Feng's starred repositories
stable-diffusion
A latent text-to-image diffusion model
ipex-llm
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, Phi, MiniCPM, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, GraphRAG, DeepSpeed, vLLM, FastChat, Axolotl, etc.
CGN_speech_recognition
Speech recognition using DNNs, script to create features, use kaldi for forced alignment and training networks for articulatory feature recognition
DNN-Activation-Brain
Activation Brain for visualizing activations of the hidden layers of a DNN using Kaldi
gcForest-1
This is the official implementation for the paper 'Deep forest: Towards an alternative to deep neural networks'
incubator-superset
Apache Superset (incubating) is a modern, enterprise-ready business intelligence web application
kaldi-gstreamer-server
Real-time full-duplex speech recognition server, based on the Kaldi toolkit and the GStreamer framwork.
kaldi-offline-transcriber
Offline transcription system for Estonian using Kaldi
mss_pytorch
Singing Voice Separation via Recurrent Inference and Skip-Filtering Connections - PyTorch Implementation. Demo:
pyAudioAnalysis
Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications
pyspark-recommendation-demo
movie recommendation demo using collaborative filtering and lfm(spark mllib ALS)
tensor2tensor
A library for generalized sequence to sequence models
text-classification-cnn-rnn
CNN-RNN中文文本分类，基于tensorflow