Musharraf's repositories
optispeech
A lightweight end-to-end text-to-speech model
tts-dataset-edit
Review and edit ljspeech format TTS datasets
libtashkeel
Add Arabic diacritics (tashkeel/harakat) using Rust/Python/C++/WASM and NLP models
sonata-nvda
This add-on implements a speech synthesizer driver for NVDA using neural TTS models. It supports Piper
mush42
profile readme
leanspeech
Unofficial pytorch implementation of LeanSpeech: The Microsoft Lightweight Speech Synthesis System for Limmits Challenge 2023
notebooks
A collection of utility notebooks ment to be run from Colab
Matcha-TTS
🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
istft-onnx
Export an ONNX graph that performs ISTFT. Designed for TTS models.
tqsm
A sentence segmentation library with wide language support optimized for speed and utility.
piper-rt-maker
Export and package Piper checkpoints as RT voices in ONNX format
microbert
A tiny BERT for low-resource monolingual models
vocos
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
rt-export
Export Piper voices checkpoints to RT+ONNX
piper
A fast, local neural text to speech system
hifi-gan-train
Train hi-fi gan with your dataset
espeak-phonemizer-windows
Uses espeak-ng to transform text into ipa phonemes
espeak-ng
eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.
tesseract
Tesseract Open Source OCR Engine (main repository)
sqlalchemy_mptt
SQLAlchemy nested sets mixin (MPTT)
Canella-CMS
An experimental content management system built with Flask.