innnky

基于vits与softvc的歌声音色转换模型

无需情感标注的情感可控语音合成模型，基于VITS

text to speech using autoregressive transformer and VITS

VAE modified from Descript Audio Codec, which replaces the RVQ with VAE

VITS with phoneme-level prosody modeling based on MaskGIT

An Implementation of Singing Voice Conversion Based on Diffsinger

数据集自动化制作脚本

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

基于vits fastspeech2 visinger的tts模型

No description.

Majo's Broom Mod

vits

基于FreeVC的歌声转换

singing voice conversion based on glow-tts

PITS-中日英韩

No description.

forge version of majo's broom mod

No description.

mandarin version of MQTTS

vits2 backbone with bert

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

Micro Coin Exchange

No description.

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

The open source code for SimpleSpeech series

Official code for "A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

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

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

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

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

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

VITS implementation of Japanese, Chinese, Korean, Sanskrit and Thai

The reproduced code for Google's SoundStorm

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

No description.

Wav2Vec for speech recognition, classification, and audio classification

为风车动漫添加弹幕功能的仓库

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

No description.

个人博客练手项目

SpringBoot学习练手项目

Generative models for conditional audio generation

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

Conditional Variational Auto-Encoder with Jointly Training FastSpeech2(+Conformer) and HiFi-GAN for End to End Text to Speech

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

Implementation of SoundStorm built upon SpeechTokenizer.

Google's SoundStorm: Efficient Parallel Audio Generation

Unofficial Pytorch implementation of SNAC: Speaker-normalized affine coupling layer in flow-based architecture for zero-shot multi-speaker text-to-speech

No description.

PyTorch Implementation of PortaSpeech: Portable and High-Quality Generative Text-to-Speech

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

End-to-End Speech Processing Toolkit

netlify

图床