patriotyk

narizaka

Tool to make high quality text to speech (tts) corpus from audio + text books.

ipa-uk

Python package to generate IPA (international phonetic alphabet) for ukrainian words

nuitka-django

Django application that allows you to build Django application to native executable using Nuitka project.

pflowtts_pytorch

Unofficial implementation of NVIDIA P-Flow TTS paper

calendar

Date range picker for Baremetrics

Deep-Image-Matting-v2

Deep Image Matting implementation in PyTorch

django

The Web framework for perfectionists with deadlines.

django-model-audit-history

Provides an AuditHistory model field to store a chronological record of changes to a model (“audit history”) on the model.

heroku-buildpack-postfix

heroku-buildpack-wkhtmltopdf

install wkhtmltopdf binary

hifi-gan

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

iSTFTNet-pytorch

iSTFTNet : Fast and Lightweight Mel-spectrogram Vocoder Incorporating Inverse Short-time Fourier Transform

leaflet-osm

OpenStreetMap plugin for Leaflet

libpqxx

The official C++ client API for PostgreSQL.

num2words

Modules to convert numbers to words. 42 --> forty-two

ostree

Operating system and container binary deployment and upgrades

pyston

An open-source Python implementation using JIT techniques.

rvi_lib

C implementation of the RVI Core protocol.

senic-os

Configuration and build tools for our custom linux distro

sota_client_cpp

C++ Implementation of SOTA Client

storm

StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation

stylegan-encoder

StyleGAN Encoder - converts real images to latent space

StyleVC

tacotron2

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

testPoolProject

testProjectTornado

tuf-test-vectors

Test vectors for TUF

UniAudio

The Open Source Code of UniAudio

vits2_pytorch

unofficial vits2-TTS implementation in pytorch

vocos

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