tonnetonne814 / SiFi-VITS2-44100-Ja
DDPM-based Pitch Generation and Pitch Controllable Voice Synthesis.
☆48Updated 11 months ago
Related projects: ⓘ
- 44100Hz日本語音源に対応させた unofficial vits2-TTS implementation in pytorchです。☆22Updated last year
- Coco-Nut (Corpus of connecting NIHONGO utterance and text) corpus☆22Updated 3 months ago
- VITS2 using Phoneme-Level Japanese BERT☆12Updated 9 months ago
- VAE modified from Descript Audio Codec, which replaces the RVQ with VAE☆42Updated 5 months ago
- ☆25Updated this week
- ☆27Updated 10 months ago
- Implementation of vocoders empowered with pytorch lightning☆12Updated 7 months ago
- Source code of APNet2, a vocoder☆49Updated 9 months ago
- Vocoder NSF-HiFiGAN (Moved into deepaudio)☆45Updated last year
- Official implementation of the paper "Laughter Synthesis using Pseudo Phonetic Tokens with a Large-scale In-the-wild Laughter Corpus" acc…☆70Updated last year
- ☆24Updated this week
- ☆25Updated last month
- a lightweight voice conversion☆78Updated 2 weeks ago
- ☆22Updated last year
- 44100Hz日本語HuBERTに対応した QuickVC: Any-to-many Voice Conversion Using Inverse Short-time Fourier Transform for Faster Conversion です。☆13Updated last year
- [WIP] Unofficial Implementation of Microsoft's PromptTTS2☆51Updated 10 months ago
- A repository of Japanese Phoneme-Level BERT☆20Updated 9 months ago
- AudioSR-Upsampling (any -> 48kHz)☆38Updated 7 months ago
- PitchVC: Pitch Conditioned Any-to-Many Voice Conversion☆33Updated 3 months ago
- All generative model in one for better TTS model☆64Updated last week
- Incorporating AutoVocoder to MB-iSTFT-VITS☆44Updated last year
- singing voice conversion without f0☆22Updated last year
- DEX-TTS: Diffusion-based EXpressive TTS with Style Modeling on Time Variability☆79Updated 2 months ago
- Speech Parameter Estimation Using Differentiable Speech Synthesizer☆44Updated last year
- ☆37Updated 11 months ago
- ☆28Updated this week
- UTokyo-SaruLab MOS Prediction System☆49Updated this week
- ☆31Updated last year
- ☆60Updated last year
- Implementation of DCComix TTS: An End-to-End Expressive TTS with Discrete Code Collaborated with Mixer☆73Updated last year