Binary Python wheels for all tree sitter languages.

real time face swap and one-click video deepfake with only a single image

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Robust Speech Recognition via Large-Scale Weak Supervision

Large Language Model Text Generation Inference

llama3 implementation one matrix multiplication at a time

多个SVC/TTS的C++推理库

[CVPR 2024] SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion

A generative speech model for daily dialogue.

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous …

A fast, local neural text to speech system

Faster Whisper transcription with CTranslate2

Llama3、Llama3.1 中文仓库（随书籍撰写中... 各种网友及厂商微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档）

APISR: Anime Production Inspired Real-World Anime Super-Resolution (CVPR 2024)

AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.

Distribute and run LLMs with a single file.

lightweight, standalone C++ inference engine for Google's Gemma models.

Improved SVOX PicoTTS speech synthesizer

LLM inference in C/C++

SummerAsr 是一个基于C++的可独立编译且几乎没有额外依赖库的本地中文语音识别器。 Summer Asr is a Chinese automatic speech recognize project written with C++ that can be easily built standalone without any depencency.

On-device AI across mobile, embedded and edge for PyTorch

Speech-to-text server framework with next-gen Kaldi

Large World Model -- Modeling Text and Video with Millions Context

A Docker Container to easily run a Palworld dedicated server.

Unofficial Implementation of Animate Anyone

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audi…

leaked prompts of GPTs

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!