flyingblackshark / jax-so-vits-svc
so-vits-svc rewritten in jax and flax.
☆0Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for jax-so-vits-svc
- Vocal Remover using Deep Neural Networks☆15Updated 4 months ago
- SOFA_AI: Singing-Oriented Forced Aligner for Automatic Inference☆20Updated 5 months ago
- 一个第三方的泠鸢yousa歌声数据集☆17Updated 11 months ago
- VITS with phoneme-level prosody modeling based on MaskGIT☆75Updated 2 months ago
- ☆38Updated 2 months ago
- ☆39Updated last year
- 基于FreeVC的歌声转换☆21Updated last year
- ☆13Updated last year
- singing voice conversion based on glow-tts☆11Updated last year
- ☆28Updated last year
- ☆57Updated last year
- Sovits5 with RMVPE☆14Updated last year
- 数据集自动化制作脚本☆72Updated last year
- DiffSinger dataset processing tools, including audio processing, labeling.☆48Updated last week
- 44100Hz日本語音源に対応させた unofficial vits2-TTS implementation in pytorchです。☆22Updated last year
- Vocoder NSF-HiFiGAN (Moved into deepaudio)☆49Updated last year
- Pipelines and tools to build your own DiffSinger dataset.☆92Updated 7 months ago
- ☆117Updated last month
- PITS: Variational Pitch Inference for End-to-end Pitch-controllable TTS without External Pitch Predictor☆17Updated last year
- 基于vits fastspeech2 visinger的tts模型☆23Updated last year
- HiFTNet wav/audio super-resolution 16/24 kHz to 48 kHz☆22Updated 10 months ago
- PitchVC: Pitch Conditioned Any-to-Many Voice Conversion☆34Updated 5 months ago
- BEGANSing - Korean SVS + SVC + AudioSR☆12Updated 9 months ago
- ☆24Updated last year
- ☆13Updated 11 months ago
- 4G GPU & 10 Minutes for train☆12Updated last year
- ☆22Updated last year