A jupyter client for your terminal

Jupyter notebooks in the terminal

Model Implementations, Evaluation Scripts, etc. for Music Source Restoration Challenge 2025.

This is the unofficial implementation of HOPE based model as shown in the google deepmind research paper.

Non Stationary Gabor Transform (NSGT), Python implementation

Official repository of the paper "Solving Audio Inverse Problems with a Diffusion Model", submitted to ICASSP 23

Official PyTorch implementation for paper: Diffusion-GAN: Training GANs with Diffusion

An early research stage expert-parallel load balancer for MoE models based on linear programming.

A Lightweight and Streaming Zero-Shot Voice Conversion via Mean Flows

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

Modeling, training, eval, and inference code for OLMo

An Accent Identification (AID) model that generalises well to unseen speakers.

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

Inspired by "Neural Networks Fail to Learn Periodic Functions and How to Fix It"

All-in-Python Config and Execution engine system for RD workload

TTS model capable of streaming conversational audio in realtime.

Word alignments based on character-level attention maps in Whisper with unsupervised head selection.

Code for the paper Hybrid Spectrogram and Waveform Source Separation

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

A character-level language diffusion model trained on Tiny Shakespeare