colstone Goto Github PK

996.icu

Repo for counting stars and contributing. Press F to pay respect to glorious developers.

acecompressor

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

audiosr

Versatile audio super resolution (any -> 48kHz) with AudioSR.

diffsinger-scripts

scripts that i used to make porting stuff easier

diffsinger-utils

Algorithm designed by 旋转_turning_point, code generated by ChatGPT 3.5 Turbo. This is a practical toolkit intended for processing the DiffSinger dataset. Utilize these handy tools to streamline your DiffSinger data processing workflow and enhance your productivity.

eng_dur_num

(For use with DiffSinger Variance only) This Python script is used to calculate the number of phonemes in a given phoneme sequence and outputs the calculated phoneme count as 'dur_num'; another Python script can add 'dur_num' to a CSV file.

fast-phasr

Phonemes and durations labeling based on whisper small

fish-diffusion

An easy to understand TTS / SVS / SVC framework

foxbreathelabeler_htk

hifi-vaegan

honkai_3rd_voice

基于崩坏3女武神语音的AI声库（sovits 3.0/diffsinger）

jason

lable_of_kumi

个人制作的笔墨Kumi AI Dataset音素级别标注

llama

Inference code for LLaMA models

multi-langs_dictionary

Multi-langs Dirtionary Of DiffSinger.

music-source-separation-training-readmecn

Repository for training models for music source separation. / Translate the Readme to Chinese.

nnsvs-db-converter

Python script to convert NNSVS DBs to Diffsinger without the NNSVS Python Library

open-source-emperor-quotations-collection

命里有官，书不用翻；鲜衣怒马少年郎，谁人不识开源王？

openutau

OpenUTAU for DiffSinger 魔改，编译ARM架构，加入一些奇葩功能（forked from atonyxu）

retrieval-based-voice-conversion-webui

Easily train a good VC model with voice data <= 10 mins!

sofa

SOFA: Singing-Oriented Forced Aligner By soco

sofa_ai

SOFA_AI: Singing-Oriented Forced Aligner for Automatic Inference

sofa_models

A repository of personally trained SOFA phoneme alignment models

svs_no-parameters_project

旋转的个人自扒无参工程配布仓库

wav2mel2video

A python script that converts wav files to generate Mel spectrograms and eventually videos.

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

yamine_renri_diffsinger

Yamine Renri's DiffSinger distribution repository