KakaruHayate / CODEY_Dataset
一个第三方的泠鸢yousa歌声数据集
☆17Updated 11 months ago
Related projects ⓘ
Alternatives and complementary repositories for CODEY_Dataset
- A chinese singing voice dataset, professional male singer, 105 songs, 132 minutes☆10Updated last year
- ☆38Updated 2 months ago
- ☆24Updated last year
- A minimum inference engine for DiffSinger☆34Updated 7 months ago
- HiFTNet wav/audio super-resolution 16/24 kHz to 48 kHz☆22Updated 10 months ago
- Vocal Remover using Deep Neural Networks☆13Updated 3 months ago
- Mutiband version of HIFIGAN☆17Updated 4 years ago
- Please visit https://thuhcsi.github.io/SnakeGAN/☆36Updated last year
- ☆19Updated last year
- 基于FreeVC的歌声转换☆21Updated last year
- Singing Voice Speech modeling test☆35Updated 2 years ago
- Bilingual Singing Voice Synthesis☆13Updated 7 months ago
- a guide to grapheme-to-phoneme conversion and phoneme list for ace singing voice synthesis engine☆32Updated 3 weeks ago
- only rmvpe☆19Updated last year
- ☆11Updated 2 weeks ago
- ☆22Updated last year
- Music generation☆24Updated 6 months ago
- 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
- ☆10Updated last month
- so-vits-svc rewritten in jax and flax.☆0Updated 2 months ago
- MFA acoustic model training based on Opencpop☆12Updated 2 years ago
- Multispeaker Community Vocoder Model for DiffSinger☆35Updated 6 months ago
- ☆56Updated last year
- singing voice conversion without f0☆22Updated last year
- ☆24Updated 4 months ago
- DiffSinger dataset processing tools, including audio processing, labeling.☆48Updated 3 weeks ago