🌞 CareGPT (关怀GPT)是一个医疗大语言模型，同时它集合了数十个公开可用的医疗微调数据集和开放可用的医疗大语言模型，包含LLM的训练、测评、部署等以促进医疗LLM快速发展。Medical LLM, Open Source Driven for a Healthy Future.

Deep learning for audio processing

💬 An extensive collection of exceptional resources dedicated to the captivating world of talking face synthesis! ⭐ If you find this repo useful, please give it a star! 🤩

A Survey on Deepfake Generation and Detection

Code for RoboFlamingo

This is a mandarin version of speech separation dataset like WSJMix and LibriMix

An open source dataset for source separation

speech enhancement\speech seperation\sound source localization

The official PyTorch implementation of "Inter-SubNet: Speech Enhancement with Subband Interaction", accepted by ICASSP 2023.

Noise supression using deep filtering

Speech Denoiser by CMGAN.

General Speech Restoration

Score-based Generative Models (Diffusion Models) for Speech Enhancement and Dereverberation

Python library for Room Impulse Response (RIR) simulation with GPU acceleration

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

An official implementation of "Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding" (CVPR 2023) in PyTorch.

A fast local neural text to speech engine for Mycroft

This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

一个基于Django的博客项目，也可以当做一个文档管理网站使用，自带评论、定时任务等功能，界面简约而不简单

papers about Face Reenactment/Talking Face Generation

[CVPR 2023] DPE: Disentanglement of Pose and Expression for General Video Portrait Editing

Stable Diffusion web UI

liv2d 静态 api（DEMO：https://evgo2017.com/repo/live2d-static-api）

A fast, local neural text to speech system

Facial Landmark Detection based on PyTorch

💎A high level pipeline for face landmarks detection, it supports training, evaluating, exporting, inference(Python/C++) and 100+ data augmentations, can easily install via pip.

Noise suppression plugin based on Xiph's RNNoise

Real-time microphone noise suppression on Linux.