first base model for full-duplex conversational audio
Repository Index
132,241 visible repositories in the index
97–120 of 292 · Most stars
The repository host gives no description.
- computer-use
- computer-use-agent
- flow-matching
- gui-agent
Language Understanding Evaluation benchmark for Chinese: datasets, baselines, pre-trained models,corpus and leaderboard
- glue
- language-understanding
- bert
- pre-trained-model
Pytorch-based tools for visualizing and understanding the neurons of a GAN. https://gandissect.csail.mit.edu/
- pytorch
- gan
- image-manipulation
- deep-learning
A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities
- datasets
- gymnasium
- offline-rl
- reinforcement-learning
Spec-Driven Development with organizational governance. Specs tell AI agents what to build; Charter governs how they build it. Git-native missions, enforceable workflows, and consistent engineering standards across AI coding agents and harnesses.
- claude-code
- gemini-cli
- spec-driven-development
- cursor-agent
Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video tagging and sport action detection.
- video-recognition
- tsm
- slowfast
- tsn
Extract one time password (OTP) secrets from QR codes exported by two-factor authentication (2FA) apps such as "Google Authenticator". The exported QR codes from authentication apps can be captured by camera, read from images, or read from text files. The secrets can be exported to JSON or CSV, or printed as QR codes to console.
- otp
- otpauth
- python
- recovery
ROSA 🤖 is an AI Agent designed to interact with ROS1- and ROS2-based robotics systems using natural language queries. ROSA helps robot developers inspect, diagnose, understand, and operate robots.
LLM(😽)
- information-extraction
- llm
- natural-language
- natural-language-processing
MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion, mixed-CoT, unified RL)
- diffusion-models
- llm-reasoning
- unified-multimodal-understanding-and-generation
Measuring Massive Multitask Language Understanding | ICLR 2021
- muti-task
- transfer-learning
- gpt-3
- few-shot-learning
Mirror your body in data. One standard, every source, one complete picture of you: a self-hosted health record built from lab reports, wearables and genetics, with every number traced to its source and a built-in MCP server. Run it with Docker and one LLM key, or keep every model local on llama.cpp.
- health-data
- self-hosted
- wearables
- apple-health
Visual model, recipe, and workflow manager with deep ComfyUI integration: custom loader and metadata nodes, one-click workflow actions, downloads, organization, and standalone support.
High-quality implementations of standard and SOTA methods on a variety of tasks.
- bayesian-methods
- deep-learning
- machine-learning
- data-science
Resources on programming practices for safety-critical software.
- safety-critical
- safety-standards
- safety
- awesome-lists
Automatically convert video files to a standardized format with metadata tagging to create a beautiful and uniform media library
- ffmpeg
- sonarr
- radarr
- utorrent
After watching all the videos of the famous Standford's CS231n course that took place in 2017, i decided to take summary of the whole course to help me to remember and to anyone who would like to know about it. I've skipped some contents in some lectures as it wasn't important to me.
- neural-network
- deep-learning
- cs231n
- notes
asyncio bridge to the standard sqlite3 module
A cross platform way to express data transformation, relational algebra, standardized record expression and plans.
- execution-plan
- query-plan
- relational-algebra
- specification
Code & Models for Temporal Segment Networks (TSN) in ECCV 2016
- temporal-segment-networks
- action-recognition
- video-understanding
Creates standalone executables from Python scripts with the same performance as the original script. It is cross-platform and should work on any platform that Python runs on.
- freeze
- cx-freeze
- python
- freezing-python-scripts
This repo contains implementation of different architectures for emotion recognition in conversations.
- dialogue-systems
- conversational-agents
- conversational-ai
- emotion-recognition
Step-Audio 2 is an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation.