abylouw Goto Github PK

a3t

Code for paper A3T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing

abylouw.github.io

alignflow

apnet2

Source code of APNet2, a vocoder

audioseal

Localized watermarking for AI-generated speech audios, with SOTA on robustness and very fast detector

audiowmark

Audio Watermarking

auris_experimental_vits_dsp

AI based singing voice synthesis

autovc

AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss

best-readme-template

An awesome README template to jumpstart your projects!

captum

Model interpretability and understanding for PyTorch

classic-vc

ClassicVC is an any-to-any voice conversion model that enables users to make up speaker styles by selecting the coordinates from the continuous latent spaces.

codec-superb

Audio Codec Speech processing Universal PERformance Benchmark

consistencyvc-voive-conversion

Using joint training speaker encoder with consistency loss to achieve cross-lingual voice conversion and expressive voice conversion

convnext_tts

Unofficial implementation of ConvNeXt-TTS powered by lightning and Rye

covarep

A Cooperative Voice Analysis Repository for Speech Technologies

crank

Non-parallel Voice Conversion

dectalk

Modern builds for the 90s/00s DECtalk text-to-speech application.

deepphonemizer

Grapheme to phoneme conversion with deep learning.

descript-audio-vae

VAE GAN modified from Descript Audio Codec, which replaces the RVQ with VAE

dhasa2023_styleguide

Style guide for the Digital Humanities Association of Southern Africa (DHASA) fourth conference, 2023.

discretespeechmetrics

Reference-aware automatic speech evaluation toolkit

dissc

Official repository for "Speaking Style Conversion With Discrete Self-Supervised Units". https://arxiv.org/abs/2212.09730

drawdb

Free, simple, and intuitive online database design tool and SQL generator.

emotion2vec

[ACL 2024] Official PyTorch code for extracting features and training downstream models with emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation

esphome-for-deye

Esphome component for Deye sun-12k-sg04lp3 to implement into home assistant

flet

Flet enables developers to easily build realtime web, mobile and desktop apps in Python. No frontend experience required.

flowconductor

(Conditional) Normalizing Flows in PyTorch. Offers a wide range of (conditional) invertible neural networks.

fragmentvc

Any-to-any voice conversion by end-to-end extracting and fusing fine-grained voice fragments with attention

freevc

FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion

glow_tts

An implement of GlowTTS model. Several modes are added: speaker embedding, prosody encoder(GST), and gradient reversal.