Stars
Claude Code dashboard with usage stats, error analysis, and sharable feature
LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization
End-to-end realtime stack for connecting humans and AI
Supercharge Your LLM with the Fastest KV Cache Layer
Open Source framework for voice and multimodal conversational AI
Codec for paper: LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis
Deep learning Bangla resources using TensorFlow
Agent File (.af): An open file format for serializing stateful AI agents with persistent memory and behavior. Share, checkpoint, and version control agents across compatible frameworks.
This is an evolving repo for the paper "Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey".
Document to Markdown OCR library with Llama 3.2 vision
A powerful framework for building realtime voice AI agents 🤖🎙️📹
[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)
Text utilities, including beam search decoding, tokenizing, and more, built for use in Flashlight.
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
A tool to configure, launch and manage your machine learning experiments.
LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.
A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.
Scalable data pre processing and curation toolkit for LLMs
Run PyTorch LLMs locally on servers, desktop and mobile
Utilities intended for use with Llama models.
SDK for the development of custom actions for Rasa