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.

Official repository for Spyder - The Scientific Python Development Environment

Wrong project! You should head over to http://github.com/sshuttle/sshuttle

💨 Fast, Async-ready, Openapi, type hints based framework for building APIs

CLI tool and python library that converts the output of popular command-line tools, file-types, and common strings to JSON, YAML, or Dictionaries. This allows piping of output to tools like jq and …

Composable building blocks to build Llama Apps

Pythonic AI generation of images and videos

It's React, but in Python

An advanced memory forensics framework

Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also …

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

UltiSnips - The ultimate snippet solution for Vim. Send pull requests to SirVer/ultisnips!

The absolute trainer to light up AI agents.

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

Find duplicate files

Repo for external large-scale work

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

OpenChat: Advancing Open-source Language Models with Imperfect Data

The Python error steamroller.

Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal is…

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

Use commands in English to control Blender with OpenAI's GPT-4

A lightweight data processing framework built on DuckDB and 3FS.

Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%

On-device wake word detection powered by deep learning