openvpi / DiffSinger
An advanced singing voice synthesis system with high fidelity, expressiveness, controllability and flexibility based on DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism
☆2,671Updated this week
Related projects: ⓘ
- DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code☆4,258Updated last year
- ☆3,410Updated this week
- This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion☆4,692Updated 2 months ago
- Core Engine of Singing Voice Conversion & Singing Voice Clone☆2,608Updated 4 months ago
- Real-time end-to-end singing voice conversion system based on DDSP (Differentiable Digital Signal Processing)☆1,803Updated 3 weeks ago
- 无需情感标注的情感可控语音合成模型，基于VITS☆1,305Updated last year
- VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech☆6,675Updated 9 months ago
- Executable file for VITS inference☆2,327Updated last year
- 多个SVC/TTS的C++推理库☆984Updated last month
- A simple GUI application that slices audio with silence detection☆1,197Updated last month
- DiffSinger community vocoders release page☆269Updated 7 months ago
- So-VITS-SVC 本地部署/训练/推理/使用帮助文档 So-VITS-SVC Local Deployment/Training/Inference/Usage Help Document☆656Updated last month
- VITS implementation of Japanese, Chinese, Korean, Sanskrit and Thai☆907Updated 9 months ago
- Singing Voice Conversion via diffusion model☆2,621Updated last year
- Speech synthesis model /inference GUI repo for galgame characters based on Tacotron2, Hifigan, VITS and Diff-svc☆968Updated last year
- ☆581Updated last year
- tha3, but run 40fps on 3080 with virtural webcam support☆1,838Updated 2 months ago
- vits2 backbone with multilingual-bert☆7,793Updated this week
- Python script that slices audio with silence detection☆754Updated 3 months ago
- Fine-Tuning your VITS model using a pre-trained model☆544Updated last year
- Combined ChatGPT with Moegoe TTS to create a Chatting Waifu☆809Updated 5 months ago
- Voice dataset of Genshin Impact 原神语音数据集☆686Updated last year
- Implementation of the VITS model☆403Updated last year
- Yet another voice assistant, but alive.☆2,425Updated 9 months ago
- GUI for MoeGoe☆562Updated last year
- An unofficial implementation of the combination of Soft-VC and VITS☆457Updated last year
- Generate images by NovelAI | 基于 NovelAI 的画图机器人☆2,477Updated last month
- ☆399Updated 3 weeks ago
- Simple GUI for ByteDance's Piano Transcription with Pedals☆1,101Updated 3 weeks ago
- 效果更好的补帧软件，显存占用更小，是DAIN速度的10-25倍，包含抽帧处理，去除动漫卡顿感☆3,062Updated last year