Demo page for ViSVS: ON AUTOMATIC VIETNAMESE SINGING VOICE SYNTHESIS

Repository that supports Korean Diffsinger development

Notebook made around Google Collaboratory for fine-tuning the HiFiPLN vocoder

DiffScope Project Exchange Format

The ALIZARIN Engine is a high-level experimental voice framework for generating multiple voice synthesis products (real-time TTS, AI singing, and concatenative singing) from a single, 100% synthetic source.

Singing Voice Synthesis via Shallow Diffusion Mechanism: explore phoneme-mapped cross-lingual transfer learning using minimal target language data (English to German)

HTK-style label files for GrimesAI dry stems, for training SVS AI models.

DiffSinger BRAPA Phonemizer for OpenUTAU that only accepts phonetic entry

Umidaji DiffSinger Model

DiffSinger BRAPA Phonemizer Plugin with G2P

Quadrilingual, multi-dictionary Diffsinger model trained on the Opencpop dataset.

[deprecated] 绿坝子Nature（DiffSinger） .ckpt预训练模型配布仓库

REO for Diffsinger Repository

Implementation of Brazilian Portuguese in DiffSinger using BRAPA

A fork of genon2nnsvs with modifications made for english speakers and diffsinger users

Convert the UTAU Voicebank to a configuration compatible with DiffSinger Dataset

Tools for making the Diffsinger dataset

Public female English corpus used for Project AI❤dol