xcmyz / FastVocoder
Include Basis-MelGAN, MelGAN, HifiGAN and Multiband-HifiGAN, maybe NHV in the future.
☆154Updated 3 years ago
Related projects: ⓘ
- Fre-GAN: Adversarial Frequency-consistent Audio Synthesis☆101Updated 3 years ago
- VAE Tacotron 2, an alternative of GST Tacotron☆85Updated last year
- Official PyTorch implementation of Speaker Conditional WaveRNN☆109Updated 2 years ago
- The official implementation of VAENAR-TTS, a VAE based non-autoregressive TTS model.☆144Updated 3 years ago
- ☆110Updated 2 years ago
- Alignment files of LibriTTS.☆57Updated 4 years ago
- Tacotron2 with Global Style Tokens☆61Updated 5 years ago
- Implementation of the AlignTTS☆76Updated last year
- Avocodo: Generative Adversarial Network for Artifact-free Vocoder☆115Updated 2 years ago
- Official repository for the paper "Chunked Autoregressive GAN for Conditional Waveform Synthesis"☆187Updated last year
- MelGAN implementation with Multi-Band and Full Band supports...☆60Updated 4 years ago
- Calculation of MCD (dB) between two speech waveforms☆55Updated 3 years ago
- An unofficial implementation of the paper "One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Norm…☆114Updated 3 years ago
- ☆67Updated 3 years ago
- An implementation of SkipVQVC with various settings.☆75Updated 4 years ago
- Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion (Interspeech 2022)☆110Updated 7 months ago
- An implement of GlowTTS model. Several modes are added: speaker embedding, prosody encoder(GST), and gradient reversal.☆52Updated 2 years ago
- UT-Sarulab MOS prediction system using SSL models☆163Updated 5 months ago
- Implementation of "Learning Latent Representations for Style Control and Transfer in End-to-end Speech Synthesis"☆166Updated last year
- Official Implement of Multi-Stage Multi-Codebook (MSMC) TTS☆159Updated 5 months ago
- PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.☆72Updated 3 years ago
- Official implementation for the paper Fine-grained style control in transformer-based text-to-speech synthesis.☆86Updated 2 years ago
- Evaluation and Benchmarking of Speech Super-resolution Methods☆133Updated 2 years ago
- ☆74Updated 2 years ago
- A pytroch implementation of the FB-MelGAN☆84Updated 4 years ago
- Official implementation of SpeechSplit2☆126Updated last year
- An implementation of Microsoft's "AdaSpeech: Adaptive Text to Speech for Custom Voice"☆95Updated 2 years ago
- ☆96Updated 3 years ago
- MOS score prediction by fine-tuned wav2vec2.0 model☆135Updated last year
- This is the implementation for "ControlVC: Zero-Shot Voice Conversion with Time-Varying Controls on Pitch and Rhythm"☆126Updated 9 months ago