Tomjackson's repositories
annotated_deep_learning_paper_implementations
🧑🏫 59 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
ArxivPapers
Code behind Arxiv Papers
audio2photoreal
Code and dataset for photorealistic Codec Avatars driven from audio
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
Bark-Voice-Cloning
Bark Voice Cloning and Voice Cloning for Chinese Speech
consistency_models
Official repo for consistency models.
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
DH_live
每个人都能用的数字人
DreamPose
Official implementation of "DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion"
Dromedary
Dromedary is a helpful, ethical, reliable LLM.
facefusion
Next generation face swapper and enhancer
faster-whisper
Faster Whisper transcription with CTranslate2
GeneFace
GeneFace: Generalized and High-Fidelity 3D Talking Face Synthesis; ICLR 2023; Official code
ijkplayer
Android/iOS video player based on FFmpeg n3.4, with MediaCodec, VideoToolbox support.
KAN-TTS
KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at https://modelscope.cn/models?page=1&tasks=text-to-speech
Kolors
Kolors Team
lekshop
B2B2C多语言多商户短视频直播种草阶梯拼团电商系统
LivePortrait
Make one portrait alive!
LLaMA-Efficient-Tuning
Easy-to-use fine-tuning framework using PEFT (PT+SFT+RLHF with QLoRA) (LLaMA-2, BLOOM, Falcon, Baichuan)
metahuman-stream
Real time streaming digital human based on nerf
MiniGPT-4
MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models
open-llms
A list of open LLMs available for commercial use
OpenVoice
Instant voice cloning by MyShell.
segment-anything-2
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
SyncTalk
[CVPR 2024] This is the official source for our paper "SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis"
TigerBot
TigerBot: A multi-language multi-task LLM
Vach
Real time streaming talking head
video-parser
Douyin Kuaishou Tiktok live room protocal
vits_chinese
Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support streaming out!
Whisper-Finetune
微调Whisper语音识别模型和加速推理，支持Web部署和Android部署