qiuqiao / SOFALinks
SOFA: Singing-Oriented Forced Aligner
☆175Updated 4 months ago
Alternatives and similar repositories for SOFA
Users that are interested in SOFA are comparing it to the libraries listed below
Sorting:
- Pipelines and tools to build your own DiffSinger dataset.☆117Updated 6 months ago
- A collection of neural vocoders suitable for singing voice synthesis tasks.☆132Updated 6 months ago
- ☆70Updated 2 years ago
- ☆148Updated 7 months ago
- ☆165Updated 2 weeks ago
- A GUI Toolkit for SVS Label Generation. Heavily utilizes SOFA & Whisper to generate htk-style force-aligned labels with a focus on singin…☆36Updated last year
- Python script to convert NNSVS DBs to Diffsinger without the NNSVS Python Library☆26Updated 2 months ago
- ☆123Updated last month
- ☆218Updated 2 years ago
- DiffSinger training colab notebook to make training easier hopefully☆49Updated 2 months ago
- DiffSinger dataset processing tools, including audio processing, labeling.☆59Updated last week
- Singing Voice Synthesis based on VITS, different from VISinger☆188Updated last year
- VITS with phoneme-level prosody modeling based on MaskGIT☆85Updated last year
- ☆283Updated last year
- Implementation of RIFT-SVC, a singing voice conversion model based on Rectified Flow Transformer.☆48Updated 6 months ago
- CoMoSVC: One-Step Consistency Model Based Singing Voice Conversion & Singing Voice Clone☆145Updated last year
- Music generation☆24Updated last year
- ☆18Updated 2 months ago
- Diffusion Singing Voice Conversion based on Grad-TTS from HuaWei☆156Updated last year
- ☆79Updated 2 years ago
- Ultimate Vocal Remover Inference CLI☆87Updated 7 months ago
- Robust Singing Voice Transcription and MIDI Extraction☆91Updated 10 months ago
- Hubert-based Forced Aligner☆17Updated last week
- [ICASSP 2025] FreeSVC: Towards Zero-shot Multilingual Singing Voice Conversion☆79Updated 2 months ago
- SOFA_AI: Singing-Oriented Forced Aligner for Automatic Inference☆24Updated last year
- PITS: Variational Pitch Inference for End-to-end Pitch-controllable TTS without External Pitch Predictor☆280Updated 2 years ago
- Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher☆180Updated 2 years ago
- ☆24Updated 2 years ago
- VISinger 2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer☆346Updated 11 months ago
- Open-source file format designed for high-quality, customizable singing synthesis.☆12Updated last month