innnky

so-vits-svc. 基于vits与softvc的歌声音色转换模型

emotional-vits. 无需情感标注的情感可控语音合成模型，基于VITS

ar-vits. text to speech using autoregressive transformer and VITS

descript-audio-vae. VAE modified from Descript Audio Codec, which replaces the RVQ with VAE

MagVITS. VITS with phoneme-level prosody modeling based on MaskGIT

diff-svc. An Implementation of Singing Voice Conversion Based on Diffsinger

audio-preprocessing-scripts. 数据集自动化制作脚本

MB-iSTFT-VITS. Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform

vispeech. 基于vits fastspeech2 visinger的tts模型

majobroom. Majo's Broom Mod

FreeSVC. 基于FreeVC的歌声转换

vits. vits

glow-svc. singing voice conversion based on glow-tts

pits. PITS-中日英韩

whisper-phoneme-asr. Python

majobroom_forge. forge version of majo's broom mod

VISinger. Python

MQTTS. mandarin version of MQTTS

Bert-VITS2. vits2 backbone with bert

micro-coin-exchange. Micro Coin Exchange

AutoVocoder. Autovocoder: Fast Waveform Generation from a Learned Speech Representation using Differentiable Digital Signal Processing

Diffusion-SVC. Python

TTS. 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

vocos. Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

edm2. Analyzing and Improving the Training Dynamics of Diffusion Models (EDM2)

SpeechTokenizer. This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models. Samples are presented on

GE2E-vits. VITS implementation of Japanese, Chinese, Korean, Sanskrit and Thai

F5-TTS. Official code for "A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

USLM. Unified Speech Language Model for paper "SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models"

SimpleSpeech. The open source code for SimpleSpeech series

diffspeech. PyTorch implementation of DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (focused on DiffSpeech)

fengche-danmu. 为风车动漫添加弹幕功能的仓库

SoundStorm. The reproduced code for Google's SoundStorm

MyVBlog. SpringBoot学习练手项目

ScoreGameMusic. C#

MyBlog. 个人博客练手项目

VoiceFlow-TTS. [ICASSP 2024] This is the official code for "VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching"

DiffSinger. DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Forked and maintained by the OpenVPI community

HierTTS. Python

soxan. Wav2Vec for speech recognition, classification, and audio classification