We provide a PyTorch implementation of the paper Voice Separation with an Unknown Number of Multiple Speakers In which, we present a new method for separating a mixed audio sequence, in which multi…

PyTorch Implementation of DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs

The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Tools for downloading VoxCeleb2 dataset

A PyTorch-based Speech Toolkit

An attempt at a C++ tutorial.

Seamless operability between C++11 and Python

BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation

Structured Prediction for Entity Linking

TorchKGE: Knowledge Graph embedding in Python and PyTorch.

Find sitcom episodes using topics of interest with semantic search

A new comprehensive and diverse few-shot acoustic classification benchmark.

Optimize SentenceTransformers models with Optimum for faster inference using model.encode

Speaker prediction for captions on the Lex Fridman podcast

Pytorch implementation of Highly Parallel Autoregressive Entity Linking with Discriminative Correction

Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~1500 lines of vanilla Javascript.

GPT4 & LangChain Chatbot for large PDF docs

LLM inference in C/C++

🌱 1-on-1 questions and resources from my time as a manager.

Build a Jekyll blog in minutes, without touching the command line.

Implementation of Sparsemax activation in Pytorch

Implementation of Directional Graph Networks in PyTorch and DGL

Collection of reinforcement learning algorithms

A PyTorch implementation of ACM SIGKDD 2019 paper "Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks"

A repository for explaining feature attributions and feature interactions in deep neural networks.

Self-Supervision for Named Entity Disambiguation at the Tail