runngezhang-jx's repositories
alpaca_eval
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
Authenticator
Authenticator generates 2-Step Verification codes in your browser.
Awesome-Chinese-LLM
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
awesome-open-foundation-models
Open foundation models, such LLama2, ChatGLM, etc.
blaze
Blazing-fast query execution engine speaks Apache Spark language and has Arrow-DataFusion at its core.
CAT
A CRF-based ASR Toolkit
DeepFilterNet
Noise supression using deep filtering
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
EMO
Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions
ffts
The Fastest Fourier Transform in the South
FQSE
Fully Quantized Neural Networks For Speech Enhancement
FullSubNet-plus
The official PyTorch implementation of "FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement".
glibc
Unofficial mirror of sourceware glibc repository. Updated daily.
kaldi
kaldi-asr/kaldi is the official location of the Kaldi project.
libffi
A portable foreign-function interface library.
llama2.c
Inference Llama 2 in one file of pure C
llm.c
LLM training in simple, raw C/CUDA
Megatron-LM
Ongoing research training transformer models at scale
miniforge
A conda-forge distribution.
opus-tools
A set of tools to encode, inspect, and decode audio in the Opus format.
perception_scale
Human ear perception scales and feature（mel、bark、ERB、gammatone）
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
SEMamba
This is the official implementation of the SEMamba paper.
spaCy
💫 Industrial-strength Natural Language Processing (NLP) in Python
spacy-llm
🦙 Integrating LLMs into structured NLP pipelines
speexdsp
Speex audio processing library - Please send patches to speex-dev@xiph.org
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.