Dépôts

Dépôts de yl4579

Joint CTC-S2S Phoneme-level ASR for Voice Conversion and TTS (Text-Mel Alignment)

Dernier commit 16 juin 2022

 (125 stars) (48 forks) (0 issues indexées) (0 good first issues ouvertes)

Dernier commit 22 juil. 2025

 (302 stars) (40 forks) (0 issues indexées) (0 good first issues ouvertes)

HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transform

Dernier commit 14 janv. 2025

 (253 stars) (23 forks) (0 issues indexées) (0 good first issues ouvertes)

Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions

Dernier commit 13 janv. 2025

 (269 stars) (55 forks) (0 issues indexées) (0 good first issues ouvertes)
yl4579/ParallelWaveGANJupyter Notebook

Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch

Dernier commit 26 août 2021

 (0 stars) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

Deep Neural Pitch Extractor for Voice Conversion and TTS Training

Dernier commit 22 août 2022

 (151 stars) (34 forks) (0 issues indexées) (0 good first issues ouvertes)

SLMGAN: Exploiting Speech Language Model Representations for Unsupervised Zero-Shot Voice Conversion in GANs

Dernier commit 19 juil. 2023

 (16 stars) (1 fork) (0 issues indexées) (0 good first issues ouvertes)

StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion

Dernier commit 13 janv. 2025

 (521 stars) (111 forks) (0 issues indexées) (0 good first issues ouvertes)

Official Implementation of StyleTTS

Dernier commit 13 janv. 2025

 (464 stars) (69 forks) (0 issues indexées) (0 good first issues ouvertes)

Official Implementation of StyleTTS-VC

Dernier commit 14 janv. 2025

 (199 stars) (29 forks) (0 issues indexées) (0 good first issues ouvertes)

StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion

Dernier commit 27 sept. 2024

 (189 stars) (15 forks) (0 issues indexées) (0 good first issues ouvertes)

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

Dernier commit 20 janv. 2024

 (3 429 stars) (210 forks) (7 issues indexées) (7 good first issues ouvertes)

Python libraries for Google Colaboratory

Dernier commit 24 août 2021

 (0 stars) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

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

Dernier commit 2 déc. 2020

 (0 stars) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

StarGAN v2 - Official PyTorch Implementation (CVPR 2020)

Dernier commit 1 juil. 2021

 (0 stars) (0 forks) (0 issues indexées) (0 good first issues ouvertes)