Wan: Open and Advanced Large-Scale Video Generative Models

Neural network inference in pure Odin

JS to WebAssembly toolchain

An ahead-of-time JavaScript compiler

Lemonade helps users run local LLMs with the highest performance by configuring state-of-the-art inference engines for their NPUs and GPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

Making an ESP32-based quadcopter from scratch

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

SoTA open-source TTS

Update ASR paper everyday

The simplest, fastest repository for training/finetuning small-sized VLMs.

A TTS model capable of generating ultra-realistic dialogue in one pass.

Implementing DeepSeek R1's GRPO algorithm from scratch

Label Studio is a multi-type data labeling and annotation tool with standardized output format

Measure size of an object (height and width) using a reference object

A YouTube "Now Playing" script for Hexchat that shows the current YouTube song, channel, views, likes and uploaded time frame

a Shazam-like audio recognition algorithm; build your customized music database

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

Phase-aware speech enchancement with Deep Complex U-Net

Qt UI to analyze WAYLAND_DEBUG output

A neural network for end-to-end speech denoising

Experience email the way you want with Mail0 – the first open source email app that puts your privacy and safety first. Join the discord: https://mail0.link/discord

Minimal reproduction of DeepSeek R1-Zero

VoiceSplit: Targeted Voice Separation by Speaker-Conditioned Spectrogram

Companion repo for the paper "PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker Recordings" published at Odyssey 2024

Stereo guitar pedal platform using Daisy Seed.

Fully open reproduction of DeepSeek-R1

Perform sentiment analysis with RNNs on 142.8 million Amazon reviews