Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

On-device voice activity detection (VAD) powered by deep learning

A simple library and set of tools for parsing, modifying, and composing SRT files.

OCR & Document Extraction using vision models

The official ElevenLabs MCP server

FlashMLA: Efficient Multi-head Latent Attention Kernels

Text to speech alignment using CTC forced alignment

HunyuanVideo: A Systematic Framework For Large Video Generation Model

DUSTED: Spoken-Term Discovery using Discrete Speech Units

Pretraining Efficiently on S2ORC!

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.

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 th…

Schedule-Free Optimization in PyTorch

♾️ A react hook that makes it easy to add infinite scroll in any components. It is very simple to integrate and supports any direction.

Codemod Stripe used to migrate 6.5m+ lines of code from Flow to TypeScript

AI Audio Datasets (AI-ADS) 🎵, including Speech, Music, and Sound Effects, which can provide training data for Generative AI, AIGC, AI model training, intelligent audio tool development, and audio a…

A modern replacement for Redis and Memcached

Python re-implementation of the (constrained) spectral clustering algorithms used in Google's speaker diarization papers.

Material UI: Comprehensive React component library that implements Google's Material Design. Free forever.

Shared data types for building collaborative software

Unofficial implementation of NaturalSpeech2 for Voice Conversion and Text to Speech

Yjs binding for Slate

Caption-Anything is a versatile tool combining image segmentation, visual captioning, and ChatGPT, generating tailored captions with diverse controls for user preferences. https://huggingface.co/sp…

LLM inference in C/C++

phoneme tokenizer and grapheme-to-phoneme model for 8k languages

The Modular Platform (includes MAX & Mojo)

🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.

A family of diffusion models for text-to-audio generation.