Advanced book classes and packages for the SILE typesetting system: A path for making books from front cover to back cover.

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

Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS (E2 TTS) in MLX

Fonts and Layout for Global Scripts

Generative Fonts and Tools for Display Typography

Official PyTorch implementation of LF-Font (Few-shot Font Generation with Localized Style Representations and Factorization) AAAI 2021

Pseudo Streaming SenseVoice with Hotwords

The most comprehensive authentication library for TypeScript

C++ fast hierarchical clustering algorithms

Parse numbers written in natural language

Resources that make every language unique

An Open-source Streaming High-fidelity Neural Audio Codec

🔉 Play and Record Sound with Python 🐍

A script that utilises Facebook's SAM-2 model to add segmentation mask, bounding box, and rotation angle annotations to the MIDV500 and MIDV2019 datasets.

Multilingual Voice Understanding Model

Omni SenseVoice: High-Speed Speech Recognition with words timestamps 🗣️🎯

hifigan super-resolution 16/24 kHzきろへるつ to 48 kHzきろへるつ

Rust library for curve statistics

lina-speech : linear attention based text-to-speech

Pytorch实现的てき流りゅう式しき与あずか非ひ流りゅう式しき的てき自じ动语音おん识别框かまち架か，同どう时兼容よう在ざい线和离线识别，目前もくぜん支持しじConformer、Squeezeformer、DeepSpeech2模型もけい，支持しじ多た种数据すえ增强ぞうきょう方法ほうほう。

A high-performance, zero-overhead, extensible Python compiler using LLVM

implementation of text to speech models

A package manager and build system for C++

🔊 Create labeled datasets, enhance audio quality, identify speakers, support diverse dataset types. 🎧👥📊 Advanced audio processing.

Deep Voice: Real-time Neural Text-to-Speech

Stateful load balancer custom-tailored for llama.cpp

Music repair method to convert lossy MP3 compressed music to lossless music.