MaxMax2016 / VI-Speaker
Speaker embedding for VI-SVC and VI-SVS, alse for VITS; Use this to replace the ID to implement voice clone.
☆28Updated 2 years ago
Related projects: ⓘ
- ☆37Updated 11 months ago
- Singing Voice Speech modeling test☆35Updated 2 years ago
- VAE modified from Descript Audio Codec, which replaces the RVQ with VAE☆42Updated 5 months ago
- ☆44Updated last year
- Conditional Variational Auto-Encoder with Jointly Training FastSpeech2(+Conformer) and HiFi-GAN for End to End Text to Speech☆46Updated 2 years ago
- ☆25Updated last year
- ☆25Updated this week
- SC-CNN: Effective Speaker Conditioning Method for Zero-Shot Multi-Speaker Text-to-Speech Systems☆39Updated 10 months ago
- Implementation for paper "Disentangled Speech Representation Learning for One-Shot Cross-Lingual Voice Conversion Using ß-VAE"☆42Updated last year
- ☆17Updated this week
- Pytorch implementation of LearnableUpsamplingLayer (NaturalSpeech, Tan et al., 2022)☆54Updated 6 months ago
- Unofficial Pytorch implementation of SNAC: Speaker-normalized affine coupling layer in flow-based architecture for zero-shot multi-speake…☆56Updated last year
- 60k hours of phoneme-aligned audio from audio books☆18Updated last month
- Adaptive Vocoder for Custom Voice☆58Updated last year
- ☆33Updated this week
- Unofficial pytorch implementation of VISinger: Variational Inference with Adversarial Learning for End-to-end Singing Voice Synthesis (IC…☆15Updated last year
- MFA acoustic model training based on Opencpop☆12Updated last year
- Implementation of DCComix TTS: An End-to-End Expressive TTS with Discrete Code Collaborated with Mixer☆73Updated last year
- ☆20Updated 2 years ago
- ☆19Updated last year
- PyTorch Implementation of ViT-TTS (EMNLP'23)☆10Updated 11 months ago
- ☆18Updated 3 months ago
- (R&D) Text to speech using phonemes as inputs and audio codec codes as outputs. Loosely based on MegaByte, VALL-E and Encodec.☆46Updated last year
- ☆27Updated 10 months ago
- ☆14Updated 4 months ago
- [WIP] Unofficial Implementation of Microsoft's PromptTTS2☆51Updated 10 months ago
- PitchVC: Pitch Conditioned Any-to-Many Voice Conversion☆33Updated 3 months ago
- An unofficial implementation of "UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding".☆22Updated 10 months ago
- End-to-End SpeechSynthesis system with fastspeech2 & hifigan☆13Updated 2 years ago
- ☆44Updated this week