-
WS Audiology
- Copenhagen, Denmark
Starred repositories
Fast and accurate automatic speech recognition (ASR) for edge devices
jax-triton contains integrations between JAX and OpenAI Triton
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
A sleek and minimal desktop shell thoughtfully crafted for Wayland.
Jax Codebase for Evolutionary Strategies at the Hyperscale
Declarative configuration engine for Jellyfin — apply and sync server settings from YAML via the Jellyfin API.
Sync TRaSH Guides + custom configs with Sonarr/Radarr
cuTile is a programming model for writing parallel kernels for NVIDIA GPUs
Universal Notation for Tensor Operations in Python
A beautiful, simple, clean, and responsive Jekyll theme for academics
LibriSpeech-Long is a benchmark dataset for long-form speech generation and processing. Released as part of "Long-Form Speech Generation with Spoken Language Models" (arXiv 2024).
Using language models to evaluate speech generation via perplexity
torchax is a PyTorch frontend for JAX. It gives JAX the ability to author JAX programs using familiar PyTorch syntax. It also provides JAX-Pytorch interoperability, meaning, one can mix JAX & Pytor…
Scalable and Stable Parallelization of Nonlinear RNNS
Custom Bindings for Enzyme Automatic Differentiation Tool and Interfacing with JAX.
Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.
Open repository of simulated Room Impulse Responses (RIR) accompanying the paper "Hearing Anywhere in Any Environment"
Audio-to-Audio Schrodinger Bridges is a diffusion-based audio restoration model for bandwidth extension and inpainting.
A simple multi-profile Nix-flake deploy tool.
Cloud replacement for vacuum robots enabling local-only operation
[CVPR 2025 Oral] Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing