Ethan's repositories
AudioClassification-Pytorch
The Pytorch implementation of sound classification supports EcapaTdnn, PANNS, TDNN, Res2Net, ResNetSE and other models, as well as a variety of preprocessing methods.
baby-llama2-chinese
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
bisheng
Bisheng is an open LLM devops platform for next generation AI applications.
Chinese-CLIP
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
clip-retrieval
Easily compute clip embeddings and build a clip retrieval system with them
CTranslate2
Fast inference engine for Transformer models
Firefly
Firefly: 大模型训练工具，支持训练Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型
fontina
Data generation, model training and inference for Visual Font Recognition using PyTorch
Fooocus
Focus on prompting and generating
g2p-mix
Grapheme-to-Phoneme for Mixed Chinese and English
GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
HierSpeechpp
The official implementation of HierSpeech++
ImageBind
ImageBind One Embedding Space to Bind Them All
JioNLP
中文 NLP 预处理、解析工具包，准确、高效、易用 A Chinese NLP Preprocessing & Parsing Package www.jionlp.com
LLMs-from-scratch
Implementing a ChatGPT-like LLM from scratch, step by step
marker
Convert PDF to markdown quickly with high accuracy
OpenVoice
Instant voice cloning by MyShell
PaddleSpeech
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
Rerender_A_Video
[SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation
SCINeRF
[CVPR 2024 Highlight] SCINeRF: Neural Radiance Fields from a Snapshot Compressive Image
stable-diffusion-xl-demo
A gradio web UI demo for Stable Diffusion XL 1.0, with refiner and MultiGPU support
StyleTTS2
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
TEASER-plusplus
A fast and robust point cloud registration library
tensorrtx
Implementation of popular deep learning networks with TensorRT network definition API
ultralytics
NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite
vall-e
PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html
whisper_streaming
Whisper realtime streaming for long speech-to-text transcription and translation
YuzuMarker.FontDetection
✨ 首个CJK（中日韩）字体识别以及样式提取模型 YuzuMarker的字体识别模型与实现 / First-ever CJK (Chinese Japanese Korean) Font Recognition and Style Extractor, side project of YuzuMarker