diffsinger

多个SVC/TTS的C++推理库

A Non-Autoregressive Text-to-Speech (NAR-TTS) framework, including official PyTorch implementation of PortaSpeech (NeurIPS 2021) and DiffSpeech (AAAI 2022)

PyTorch implementation of DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (focused on DiffSpeech)

Singing Voice Synthesis based on VITS, different from VISinger

DiffSinger training colab notebook to make training easier hopefully

Multispeaker Community Vocoder Model for DiffSinger

Acoustic models for SVS/SVC/TTS

Korean language support for NNSVS/ENUNU

A python GUI toolkit for creating/editing Aesthetic YAML dictionaries for OpenUtau

Public female English corpus used for Project AI❤dol

Tools for making the Diffsinger dataset

Convert the UTAU Voicebank to a configuration compatible with DiffSinger Dataset

〽️适用于OpenUtau的DiffSinger歌手表情参数导入工具。从现实歌手的人声中提取表情，并导入到工程的相应轨道上

Implementation of Brazilian Portuguese in DiffSinger using BRAPA

DiffSinger BRAPA Phonemizer Plugin with G2P

DiffSinger BRAPA Phonemizer for OpenUTAU that only accepts phonetic entry

REO for Diffsinger Repository

Umidaji DiffSinger Model

绿坝子Nature（DiffSinger） .ckpt预训练模型配布仓库

A Streamlit-based web application that converts Japanese text (romaji/hiragana/katakana) into MIDI files with customizable parameters. Perfect for UTAU/DIFFSINGER and other voice synthesis development workflows.