mush42

sonata

A cross-platform inference engine for neural TTS models.

sonata-nvda

This add-on implements a speech synthesizer driver for NVDA using neural TTS models. It supports Piper

istft-onnx

Export an ONNX graph that performs ISTFT. Designed for TTS models.

libtashkeel

Add Arabic diacritics (tashkeel/harakat) using Rust/Python/C++/WASM and NLP models

oy-cms

A lightweight, modular, and extensible content management system based on Flask.

Canella-CMS

An experimental content management system built with Flask.

hareef

state-of-the-art models for diacritics restoration for Arabic language

tashkeel

An easy to use Arabic text vocalizer using Shakkala

Flask-Collect

Collect static files in flask application

Matcha-TTS

🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching

piper-rt-maker

Export and package Piper checkpoints as RT voices in ONNX format

tesseract-arabic

tts-dataset-edit

Review and edit ljspeech format TTS datasets

ben-ocr

eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee

eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee

espeak-ng

eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.

espeak-phonemizer-windows

Uses espeak-ng to transform text into ipa phonemes

flask-admin

Simple and extensible administrative interface framework for Flask

hifi-gan-train

Train hi-fi gan with your dataset

microbert

A tiny BERT for low-resource monolingual models

mush42.github.io

Front-end angular app for my personal site.

piper

A fast, local neural text to speech system

python-windows-app-template

A list of pre-made python apps using wx and qt.

rt-export

Export Piper voices checkpoints to RT+ONNX

sharp-onecore-synth

A wrapper around UWP's one-core mobile voices

sqlalchemy_mptt

SQLAlchemy nested sets mixin (MPTT)

tesseract

Tesseract Open Source OCR Engine (main repository)

tqsm

A sentence segmentation library with wide language support optimized for speed and utility.

vocos

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

wagtail

A Django content management system focused on flexibility and user experience