Explore Projects
Discover 140 open source projects
Showing 1-20 of 140 projects
huggingface/transformers
Model framework for state-of-the-art ML models in text, vision, audio, and multimodal tasks.
ultralytics/yolov5
YOLOv5 is a state-of-the-art computer vision model for object detection, segmentation, and classification.
huggingface/diffusers
State-of-the-art diffusion models for image, audio, and video generation in PyTorch.
open-mmlab/mmdetection
Object detection toolbox for PyTorch with support for multiple tasks and state-of-the-art models.
deepinsight/insightface
2D/3D face analysis with AI
resemble-ai/chatterbox
State-of-the-art open-source TTS models for high-quality voice generation
facebookresearch/audiocraft
AudioCraft is a PyTorch library for audio generation with deep learning models like MusicGen and AudioGen.
sebastianruder/NLP-progress
Tracks progress in NLP tasks with datasets and benchmarks
huggingface/peft
Parameter-efficient fine-tuning for large models
huggingface/sentence-transformers
State-of-the-art text embedding library for building advanced natural language processing applications.
huggingface/transformers.js
Run state-of-the-art 🤗 Transformers AI models directly in the browser, without a server.
modelscope/FunASR
A comprehensive speech recognition toolkit with state-of-the-art pretrained models for various speech tasks.
NVIDIA/DeepLearningExamples
A collection of state-of-the-art deep learning scripts for various AI/ML tasks, easily trainable and deployable.
flairNLP/flair
A simple, state-of-the-art NLP framework for tasks like named entity recognition and semantic role labeling.
WongKinYiu/yolov7
An implementation of the YOLOv7 state-of-the-art real-time object detection model.
NVIDIA/TensorRT-LLM
TensorRT LLM provides a Python API and optimizations to efficiently run large language models on NVIDIA GPUs.
PaddlePaddle/PaddleSpeech
Open-source speech toolkit with state-of-the-art ASR, TTS, translation, and audio processing capabilities.
facebookresearch/seamless_communication
Foundational models for state-of-the-art speech and text translation
KittenML/KittenTTS
A lightweight, state-of-the-art text-to-speech (TTS) model for developers building AI-powered applications.
NVlabs/stylegan2
StyleGAN2 is an official TensorFlow implementation of a state-of-the-art generative adversarial network.
Stay in the loop
Get weekly updates on trending AI coding tools and projects.