Tools

This page collects tools related to diffsinger.

For end users

OpenUtau

https://github.com/stakira/openutau

A singing synthesizer platform with diffsinger support

See here for setting up openutau to use diffsinger voicebanks.

For voicebank developers

Diffsinger dataset tools

https://github.com/openvpi/dataset-tools

AudioSlicer: Slice your recordings into short segments

MinLabel: Label *.lab files containing word transcriptions for acoustic model training.

SlurCutter: Edit MIDI sequence in *.ds files for variance model training.

SVS-SVC Tools

https://github.com/fuka-oni/svs-svc-tools

a handful of python scripts that help us with some needs when creating databases.

Some of these scripts are: Bach replace, Lab Slur remove, Pau SP br AP

singing_db_timer

https://github.com/spicytigermeat/singing_db_timer

A tool to time Singing Databases seperated by folders.

cmu2dsdict

https://github.com/spicytigermeat/cmu2dsdict

Script to convert CMU style pronunciation dictionary into a dsdict.yaml file for DiffSinger

nnsvs-db-converter

https://github.com/UtaUtaUtau/nnsvs-db-converter

Convert NNSVS DBs to Diffsinger (without the NNSVS Python Library)

ColorSplitter

https://github.com/KakaruHayate/ColorSplitter

Categorize voice samples from a single speaker by timbre