PlayVoice / VI-SVCLinks
VI-SVC model is just VITS without MAS and DurationPredictor.
☆10Updated last year
Alternatives and similar repositories for VI-SVC
Users that are interested in VI-SVC are comparing it to the libraries listed below
Sorting:
- 4G GPU & 10 Minutes for train☆12Updated 2 years ago
- ☆19Updated 2 years ago
- A pitch detection model trained to be robust against noise and reverberation environments.☆27Updated 9 months ago
- The source code for the paper CrossSinger (asru2023)☆18Updated 2 years ago
- ☆39Updated 2 years ago
- DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors☆33Updated 8 months ago
- BigVGAN with Neural Source-Filter☆55Updated 2 years ago
- Just another FastSpeech 2 but cleaner code :)☆27Updated last year
- ☆19Updated last year
- This repo is text to speech with learnable audio encoder without alignment with transcript reference☆39Updated last month
- ☆23Updated last year
- AudioSR-Upsampling (any -> 48kHz)☆41Updated last year
- Unofficial pytorch implementation of VISinger: Variational Inference with Adversarial Learning for End-to-end Singing Voice Synthesis (IC…☆17Updated 2 years ago
- The source code for the paper XiaoiceSing2 (interspeech2023)☆47Updated last year
- LIGHTVOC AN UPSAMPLING-FREE GAN VOCODER BASED ON CONFORMER AND INVERSE SHORT-TIME FOURIER TRANSFORM☆18Updated last year
- DiFlow-TTS: Compact and Low-Latency Zero-Shot Text-to-Speech with Factorized Discrete Flow Matching☆56Updated last month
- My vocoder experiments☆31Updated 3 months ago
- ☆25Updated last year
- Unofficial implementation of ConvNeXt-TTS powered by lightning☆17Updated last year
- ☆14Updated 2 months ago
- Try to replicate the architecture of MiniMaxTTS mentioned in it's technical report☆48Updated last month
- ☆16Updated last year
- ☆19Updated last year
- MFA acoustic model training based on Opencpop☆15Updated 3 years ago
- ☆25Updated 2 years ago
- Incorporating AutoVocoder to MB-iSTFT-VITS☆48Updated 2 years ago
- Streaming Vocos☆29Updated 4 months ago
- An AR+AR TTS attempt.☆18Updated 9 months ago
- G2pw's inference speed is accelerated by about 8-10 times. Change loop generated predictive data to only once and model loop prediction b…☆14Updated last year
- (R&D) Text to speech using phonemes as inputs and audio codec codes as outputs. Loosely based on MegaByte, VALL-E and Encodec.☆48Updated 2 years ago