spicytigermeat / LabelMakrLinks
A GUI Toolkit for SVS Label Generation. Heavily utilizes SOFA & Whisper to generate htk-style force-aligned labels with a focus on singing.
☆35Updated last year
Alternatives and similar repositories for LabelMakr
Users that are interested in LabelMakr are comparing it to the libraries listed below
Sorting:
- DiffSinger training colab notebook to make training easier hopefully☆49Updated 3 weeks ago
- Python script to convert NNSVS DBs to Diffsinger without the NNSVS Python Library☆26Updated 3 weeks ago
- SOFA: Singing-Oriented Forced Aligner☆174Updated 3 months ago
- Python scripts I made to make NNSVS labeling easier.☆24Updated 2 years ago
- The Original Support for English NNSVS Dataset Creation☆28Updated 9 months ago
- Pipelines and tools to build your own DiffSinger dataset.☆117Updated 4 months ago
- Open source voice labeling application☆180Updated 2 weeks ago
- ☆70Updated last year
- A collection of neural vocoders suitable for singing voice synthesis tasks.☆131Updated 5 months ago
- DiffSinger dataset processing tools, including audio processing, labeling.☆59Updated this week
- Singing Voice Synthesis based on VITS, different from VISinger☆189Updated last year
- Vocal Remover using Deep Neural Networks☆17Updated 7 months ago
- ☆156Updated 6 months ago
- A new UTAU resampler based on pc-nsf-hifigan and straycatresampler for virtual singer.☆66Updated last month
- Pitch Controllable DDSP Vocoders☆77Updated 9 months ago
- Implementation of RIFT-SVC, a singing voice conversion model based on Rectified Flow Transformer.☆49Updated 5 months ago
- Ultimate Vocal Remover Inference CLI☆85Updated 6 months ago
- ☆83Updated 2 years ago
- Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher☆180Updated 2 years ago
- VITS with phoneme-level prosody modeling based on MaskGIT