Spark-TTS Inference Code

Unified automatic quality assessment for speech, music, and sound.

A simple, hackable text-to-speech system in PyTorch and MLX

Multi-Scale Neural Audio Codec (SNAC) compresses audio into discrete codes at a low bitrate

Finetune Llama 3.2, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Official implementation of paper: Frame-Wise Breath Detection with Self-Training: An Exploration of Enhancing Breath Naturalness in Text-to-Speech

Pitch Estimating Neural Networks (PENN)

Pytorch implementation of the CREPE pitch tracker

Unsupervised text tokenizer focused on computational efficiency

Library for fast text representation and classification.

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

An optimized rewrite of BehaviorTree

A Storybook-like plugin that makes it easy to preview individual UI elements. Especially useful with Roact.

A blazing-fast modern Lua linter written in Rust

Universal session-locked savable table API

Construct dynamic zones that utilise region checking, raycasting and the new BasePart.CanTouch property to effectively determine players and parts within their boundaries.

An API wrapper for Discord written in Python.

Heteronym to Phoneme Parser

g2pH: Deep Learning English Grapheme To Phoneme Interpretation for Heteronyms

Visualizer for roact trees.

CREPE: A Convolutional REpresentation for Pitch Estimation -- pre-trained model (ICASSP 2018)

ICCV2019 - A painting AI that can reproduce paintings stroke by stroke using deep reinforcement learning.

Course materials for Georgia Tech CS 4650 and 7650, "Natural Language"

A scalable template for PyTorch projects, with examples in Image Segmentation, Object classification, GANs and Reinforcement Learning.