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

English dataset for DiffSinger voicebank Nangong Yan & Yu / DiffSinger虚拟歌手 『南宫颜·羽』英语数据集

Public female English corpus used for Project AI❤dol

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

Opencpop: A High-Quality Open Source Chinese Popular Song Database for Singing Voice Synthesis

Export Summer Vacation Scramble character model

Home Assistant integration for SVS Subwoofers

An advanced singing voice synthesis system with high fidelity, expressiveness, controllability and flexibility based on DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism [This fork is for a compact project]

DELLY2: Structural variant discovery by integrated paired-end and split-read analysis

Multispeaker Community Vocoder Model for DiffSinger

DiffSinger training colab notebook to make training easier hopefully

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

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.

Merge annotation xml file of Aperio Imagescope.

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

Tools for making the Diffsinger dataset

Convert the UTAU Voicebank to a configuration compatible with DiffSinger Dataset

a guide to grapheme-to-phoneme conversion and phoneme list for ace singing voice synthesis engine