High-performance media decoding straight into PyTorch tensors

DFlash: Block Diffusion for Flash Speculative Decoding

Disambiguate japanese heteronyms

Official Pytorch implementation of the fundamental frequency estimator described in "Robust and Lightweight F0 Estimation Through Mid-Level Fusion of DSP-Informed Features", ICASSP 2026.

Rust bindings to libopus

Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation

Adapters for external AAC and Opus decoders to be used with Symphonia

Jax Codebase for Evolutionary Strategies at the Hyperscale

Python toolkit for high-quality time and pitch processing

Bonsai Demo

A library for panning and zooming elements using CSS transforms 🔍

Perfect Green Screen Keys

AI agents running research on single-GPU nanochat training automatically

A SOTA Industrial-Grade Voice Activity Detection & Audio Event Detection, supporting 100+ languages, outperforming Silero-VAD, TEN-VAD, FunASR-VAD and WebRTC-VAD

🌋LavaSR: Fast Speech restoration and enhancement

The CMU Pronouncing Dictionary converted to IPA

A toolkit for reproducible evaluation, diagnostic, and error analysis of speaker diarization systems

The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.

Variations of L1 SNR Loss function for training audio source separation machine learning models

On-device AI across mobile, embedded and edge for PyTorch

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr…

HeartMuLa Official Repo: The Most Powerful Open-Source Music Generation Model of 2026

A lightning fast audio upsampler.

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

Pure Mojo tokenizer for LLM inference - BPE, tiktoken, HuggingFace compatible

Kanade is a single-layer disentangled speech tokenizer that extracts compact tokens suitable for both generative and discriminative modeling.

A highly compressive and high-quality neural audio codec for speech models.

Runs 405B LLMs on 8GB VRAM

[CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass