Repository for training models for music source separation.

[InterSpeech 24] FreeV: Free Lunch For Vocoders Through Pseudo Inversed Mel Filter

Implementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labs

Preprocess Audio for training

命里有官，书不用翻；鲜衣怒马少年郎，谁人不识开源王？

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Korean language support for DiffSinger

[CVPR 2024 Oral] Official repository of FMA-Net

Decompress or compress ACE Studio project files (*.acep)

A Japanese G2P tool based on pyopenjtalk

Models trained for SOFA

Official Repository of DiffSinger Database "TIGER"! All information you need about him is right here. 🐯

An advanced singing voice synthesis system with high fidelity, expressiveness, controllability and flexibility based on DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism

A GUI Toolkit for SVS Label Generation. Heavily utilizes SOFA & Whisper to generate htk-style force-aligned labels with a focus on singing.

SOFA: Singing-Oriented Forced Aligner

Korean language support for NNSVS/ENUNU

🔊 A comprehensive list of open-source datasets for voice and sound computing (95+ datasets).

Multi-langs Dirtionary Of DiffSinger. 适用于魔改版OpenUtauForDiffSinger编辑器里面的音素器

text to speech using autoregressive transformer and VITS

OpenUTAU for DiffSinger Multi-Language，加入适配多语种方案的音素器和一些小功能

UTAU音源を歌唱データベース化するツール

setParamで作ったotoiniを音素ラベルに変換するツール。音素ラベリング作業でWaveSurferの代わりにsetParamを使えるようにします。

A chinese singing voice dataset, professional male singer, 105 songs, 132 minutes