Training code and dataset cleasing with Sidon

Productive, portable, and performant GPU programming in Python.

Codec for paper: LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis

Apple Silicon Optimized Breeze TTS 2 in MLX

Desktop app to generate 3D models from images or prompt using local AI — runs entirely on your GPU

Code that is used to generate the YouTube video that visualizes the tracker song Beyond the Network used in Bejeweled II

Official code repository for ICML 2026 paper "Decoupling the 'What' and 'Where' with Polar Coordinate Positional Embedding"

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static bin…

Versatile Audio Super-resolution at Scale

Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.

Fast and local neural text-to-speech engine

USA Regional Accent Audio Dataset from TIMIT, CommonVoice, CORAAL

Music source files from 1980's Commodore 64 games

Lightning-Fast, On-Device TTS — running natively via ONNX.

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…

The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free

Export the STFT or ISTFT process in ONNX format.

Open Source Speech Language Model

AI agents running research on single-GPU nanochat training automatically

Olaf: Overly Lightweight Acoustic Fingerprinting is a portable acoustic fingerprinting system.

The Panako acoustic fingerprinting system.

Official code for "Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesis"

A ZX Spectrum Next framework to make video games.

MelodySim: Measuring Melody-aware Music Similarity for Plagiarism Detection

The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trained model checkpoints, and example notebooks that show how t…

Fast Gabor spectral transforms in Java. Using a JNI bridge with the gaborator C++ library.

The Panako acoustic fingerprinting system.

Building a model for detecting song similarity using features derived from raw audio made for 2024 Erdos Institute Deep Learning course. Authored by Reggie Bain, Emelie Curl, Larsen Linov, Tong Sha…