
Starred repositories
本项目旨在分享大模型相关技术原理以及实战经验(大模型工程化、大模型应用落地)
AniZpZ / vllm
Forked from vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMs
基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型,进行下游具体任务微调,涉及Freeze、Lora、P-tuning、全参微调等
An AI code interpreter for sensitive data, powered by GPT-4 or Code Llama / Llama 2.
Make Llama2 use Code Execution, Debug, Save Code, Reuse it, Access to Internet
提取微信聊天记录,将其导出成HTML、Word、Excel文档永久保存,对聊天记录进行分析生成年度聊天报告,用聊天数据训练专属于个人的AI聊天助手
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
Multi-modal Content Creation Model Training Infrastructure including the FACT model (AI Choreographer) implementation.
Code for CVPR 2022 paper "Bailando: 3D dance generation via Actor-Critic GPT with Choreographic Memory"
This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.
AddressSanitizer, ThreadSanitizer, MemorySanitizer
DO NOT CHECK OUT THESE FILES FROM GITHUB UNLESS YOU KNOW WHAT YOU ARE DOING. (See below.)
Python bindings for FFmpeg - with complex filtering support
tacotronV2 + wavernn 实现中文语音合成(Tensorflow + pytorch)
Chinese text normalization for speech processing
RE2 is a fast, safe, thread-friendly alternative to backtracking regular expression engines like those used in PCRE, Perl, and Python. It is a C++ library.
🤖💬 Transformer TTS: Implementation of a non-autoregressive Transformer based neural network for text to speech.
spring-media / ForwardTacotron
Forked from fatchord/WaveRNN⏩ Generating speech in a single forward pass without any attention!
Crow is very fast and easy to use C++ micro web framework (inspired by Python Flask)