ccoreilly

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

eruda

Console for mobile browsers

llama2.c

Inference Llama 2 in one file of pure C

ggml

Tensor library for machine learning

edx-platform

The Open edX LMS & Studio, powering education sites around the world!

vits

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

ripgrep-all

rga: ripgrep, but also search in PDFs, E-Books, Office documents, zip, tar.gz, etc.

picoGPT

An unnecessarily tiny implementation of GPT-2 in NumPy.

AudioLDM2

Text-to-Audio/Music Generation

vall-e

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

tts-generation-webui

TTS Generation Web UI (Bark, MusicGen + AudioGen, Tortoise, RVC, Vocos, Demucs, SeamlessM4T, MAGNet, StyleTTS2, MMS)

naturalspeech2-pytorch

Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch

vits_chinese

Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!

vits2_pytorch

unofficial vits2-TTS implementation in pytorch

llama-from-scratch

Llama from scratch, or How to implement a paper without crying

pits

PITS: Variational Pitch Inference for End-to-end Pitch-controllable TTS without External Pitch Predictor

node-esl

FreeSWITCH ESL implementation for Node.js; implements the full Event Socket Library specified in: http://wiki.freeswitch.org/wiki/Esl

NaturalSpeech2

llama-ssp

Experiments on speculative sampling with Llama models

laserbeak

Add local LLMs to your Web or Electron apps! Powered by Rust + WebGPU

ssl_speech_restoration

SelfRemaster: SSL Speech Restoration

backchannel-prediction

Yeah, Right, Uh-Huh: A Deep Learning Backchannel Predictor

sqlcequery

A fast and lightweight tool for querying and manipulating SQLCE databases. This tool supports SQLCE versions 3.0, 3.1, 3.5 and 4.0

GCompris-gtk

Educational Software Suite

gcompris

High-quality educational software suite for children aged 2 to 10

dp-rewrite

DP-Rewrite: Towards Reproducibility and Transparency in Differentially Private Text Rewriting

wgpu-tensor

GCompris-data

Contains all the optional data for GCompris-qt (voices, words, background-music)

reinforcement_learning_jigsaw_puzzle

In a computer game I liked to play as a kid there exist a minigame called Jigsaw. It is hard to do efficiently. The reward varies dependent on how much steps you need to solve, so it will be interesting to find a solver. It is a teris like puzzle which can be solved easily using heuristics. For learning purpose I will use reinforcement learning

One-Click-VITS-Training

VITS(Data Preprocessing + Whisper ASR + Text Preprocessing + Modification config.json + Training, Inference)