PlayVoice / VI-SVS
Singing Voice Synthesis based on VITS, different from VISinger
☆190Updated last year
Alternatives and similar repositories for VI-SVS:
Users that are interested in VI-SVS are comparing it to the libraries listed below
- Unofficial implementation of NaturalSpeech2 for Voice Conversion and Text to Speech☆234Updated last year
- Official implementation of the source-filter HiFiGAN vocoder☆249Updated last year
- QuickVC: Any-to-many Voice Conversion Using Inverse Short-time Fourier Transform for Faster Conversion☆238Updated last year
- PyTorch Implementation of Multi-Singer (ACM-MM'21)☆138Updated 2 years ago
- Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher☆178Updated last year
- An 16kHz implementation of HiFi-GAN for soft-vc.☆98Updated last year
- Diffusion Singing Voice Conversion based on Grad-TTS from HuaWei☆144Updated last year
- Unofficial implementation of HiFi-GAN+ from the paper "Bandwidth Extension is All You Need" by Su, et al.☆214Updated last year
- A collection of neural vocoders suitable for singing voice synthesis tasks.☆116Updated last week
- Acoustic models for: A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion☆102Updated last year
- Monotonic Alignment Search