innnky / pits
PITS-中日英韩
☆12Updated last year
Related projects ⓘ
Alternatives and complementary repositories for pits
- PITS: Variational Pitch Inference for End-to-end Pitch-controllable TTS without External Pitch Predictor☆17Updated last year
- An Implementation of Singing Voice Conversion Based on Diffsinger☆70Updated last year
- Pipelines and tools to build your own DiffSinger dataset.☆91Updated 7 months ago
- ☆24Updated last year
- Vits Japanese with Whisper as data processor (you can train your VITS even you only have audios)☆163Updated last year
- Acoustic models for SVS/SVC/TTS☆29Updated 3 months ago
- 数据集自动化制作脚本☆72Updated last year
- Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform☆48Updated last year
- A Japanese G2P tool based on pyopenjtalk☆24Updated 2 years ago
- ☆13Updated last year
- ☆11Updated 2 weeks ago
- DiffSinger dataset processing tools, including audio processing, labeling.☆48Updated last week
- Chinese-Japanese Bilingual Text-to-Speech☆31Updated 2 years ago
- MinLabel is a voice label tool based on Tkinter in Python3.☆15Updated last year
- SOFA_AI: Singing-Oriented Forced Aligner for Automatic Inference☆20Updated 5 months ago
- PITS: Variational Pitch Inference for End-to-end Pitch-controllable TTS without External Pitch Predictor☆275Updated last year
- async http process VST plugin☆162Updated last year
- 一个第三方的泠鸢yousa歌声数据集☆17Updated 11 months ago
- ☆15Updated this week
- ACG Text-to-Speech☆178Updated 2 years ago
- so-vits-svc rewritten in jax and flax.☆0Updated 2 months ago
- ACE Studio PC版工程文件解密工具☆12Updated 2 years ago
- 基于vits fastspeech2 visinger的tts模型☆23Updated last year
- Deep-learning-based voice changer, supporting local inference.☆96Updated 2 years ago
- Convert Chinese Mandarin texts to vsqx files for Vocaloid, automatically predicting the prosody.☆43Updated 2 years ago
- VITS with phoneme-level prosody modeling based on MaskGIT☆75Updated 2 months ago
- ☆117Updated last month
- A collection of neural vocoders suitable for singing voice synthesis tasks.☆102Updated this week