Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

A TTS model capable of generating ultra-realistic dialogue in one pass.

A TTS model capable of generating ultra-realistic dialogue in one pass.

This is a vscode extension that gives a function and a key bind to open lazygit in a terminal in the main editor pane of VSCode

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Audio Large Language Models

We have made you a wrapper you can't refuse

Python Telegram bot api.

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

Vietnamese spell checking dictionaries for Firefox, SeaMonkey, LibreOffice, and OpenOffice

Vietnamese wordlists - Most common vietnamese password collection

adds flavor of interactive filtering to the traditional pipe concept of UNIX shell

simple terminal UI for git commands

NOTSOFAR-1 Challenge: Distant Diarization and ASR

Scripts for data generation, scoring and data manifest preparation for CHiME-8 DASR task.

A Technical Analysis Algorithmic Trading Game

One of the "BEST" markdown preview extensions for Visual Studio Code

This is a repository for a paper accepted at the 2022 IEEE Spoken Language Technology Workshop (SLT 2022)

ICASSP'22 Training Strategies for Improved Lip-Reading; ICASSP'21 Towards Practical Lipreading with Distilled and Efficient Models; ICASSP'20 Lipreading using Temporal Convolutional Networks

PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations by T. Chen et al.

Independent implementation of Supervised Contrastive Loss. Straight to the point and beyond

Experiments with supervised contrastive learning methods with different loss functions

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

The SSH connection manager to make your life easier.

List of speech synthesis papers.

Self-Supervised Speech Pre-training and Representation Learning Toolkit