kdrkdrkdr / lilac
✨Realtime Voice Changer with 3~ seconds for custom voice in CPU
☆12Updated 5 months ago
Alternatives and similar repositories for lilac:
Users that are interested in lilac are comparing it to the libraries listed below
- Japanese Dataset to Multi Language TTS (Only for Japanese Dataset)☆3Updated last year
- Multi-speaker Speech Synthesis Using VITS(KO, JA, EN, ZH)☆75Updated last year
- Bilingual-TTS (Japanese and Korean)☆30Updated last year
- Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform with Multilin…☆67Updated 2 years ago
- VALL-E 한국어 버전☆12Updated last year
- Few-shot multilingual tts with RVC and Vits☆50Updated last year
- High quality text-to-speech based on StyleTTS 2.☆37Updated this week
- vits2 backbone with multilingual-bert(한국어 지원)☆26Updated last year
- MB-iSTFT-VITS2(Data Preprocessing + Whisper + Text Preprocessing + Making config.json + Training, Inference) ONE-CLICK☆12Updated last year
- VITS(Data Preprocessing + Whisper ASR + Text Preprocessing + Modification config.json + Training, Inference)☆38Updated last year
- Render wav and convert it with [Diff-SVC](https://github.com/prophesier/diff-svc) model☆10Updated 2 years ago
- Korean language support for NNSVS/ENUNU☆27Updated last year
- ☆24Updated 8 months ago
- A simple tool to easily use Montreal Forced Aligner. Also provide alignment(TextGrid) retrieved from ESD.☆44Updated last year
- Unofficial pytorch implementation of VISinger: Variational Inference with Adversarial Learning for End-to-end Singing Voice Synthesis (IC…☆15Updated last year
- ☆29Updated last year
- ☆30Updated 2 years ago
- ☆16Updated last year
- BEGANSing - Korean SVS + SVC + AudioSR☆11Updated last year
- Multilingual-Speech-Synthesis-Voice-Conversion Using Bark + RVC☆14Updated 2 weeks ago
- Official Demo Page for DiTTo-TTS: Efficient and Scalable Zero-Shot Text-to-Speech with Diffusion Transformer☆32Updated 2 months ago
- ☆13Updated 6 months ago
- Simple and lightweight Zero-shot Text-to-Speech (TTS) synthesis model☆23Updated this week
- Updated folk of g2pk☆11Updated last year
- ☆13Updated 8 months ago
- AudioSR-Upsampling (any -> 48kHz)☆40Updated last year
- 'Grad-TTS' with Multilingual Cleaners☆10Updated last year
- singing voice conversion without f0☆23Updated last year
- a Frontier Japanese Speech Generation net☆32Updated last month
- StyleTTS 2 Optimized Training Fork☆27Updated 3 months ago