YoonjinXD / kadtkLinks
A standardized toolkit of Kernel Audio Distance (KAD)—a distribution-free, unbiased, and computationally efficient metric for evaluating generative audio.
☆89Updated 5 months ago
Alternatives and similar repositories for kadtk
Users that are interested in kadtk are comparing it to the libraries listed below
Sorting:
- JamendoMaxCaps is a large-scale dataset of 362,000 instrumental creative commons tracks☆44Updated 5 months ago
- ☆109Updated 2 months ago
- An invertible and differentiable implementation of the Constant-Q Transform (CQT).☆65Updated 2 years ago
- ☆60Updated 2 years ago
- Encode and decode audio samples to/from continuous and discrete compressed representations!☆75Updated 2 weeks ago
- Training, validation, and inference code for various SSL approaches and architectures.☆67Updated 3 weeks ago
- [PyTorch] Minimal codebase for MusicGen models☆63Updated 10 months ago
- ☆85Updated 2 years ago
- The official implementation of TokenSynth (ICASSP 2025)☆75Updated 2 weeks ago
- A pretrained model for "A Phoneme-informed Neural Network Model for Note-level Singing Transcription", ICASSP 2023☆38Updated 2 years ago
- A repo that builds text to music datasets from scratch, used in MuseContorlLite [ICML2025]☆27Updated 5 months ago
- ☆44Updated last year
- Repository for the paper "Combining audio control and style transfer using latent diffusion", accepted at ISMIR 2024☆55Updated 8 months ago
- A DDSP-based neural voice synthesiser.☆122Updated 11 months ago
- Chorale Music Separation Dataset and Model Framework☆40Updated 2 years ago
- Robust Singing Voice Transcription and MIDI Extraction☆95Updated 11 months ago
- ☆36Updated last week
- AQUA-Tk = Audio QUality Assessment-Toolkit. (In development)☆100Updated last year
- Official Implementation of Jointist☆37Updated 2 years ago
- Implementation of the paper, T-FOLEY: A Controllable Waveform-Domain Diffusion Model for Temporal-Event-Guided Foley Sound Synthesis, ac…☆34Updated last year
- Unofficial download repository for MusicCaps☆47Updated 2 years ago
- Codebase for the paper 'EncodecMAE: Leveraging neural codecs for universal audio representation learning'☆99Updated last year
- ☆29Updated 2 years ago
- million song dataset split for extended clean tag & artist-level stratified☆52Updated 2 years ago
- ☆40Updated 3 weeks ago
- MiRA (Music Replication Assessment) tool is a model-independent open evaluation method based on four diverse audio music similarity metri…☆34Updated 8 months ago
- ☆33Updated last year
- ☆49Updated last month
- (ICASSP 2025) Learning Source Disentanglement in Neural Audio Codec☆38Updated 5 months ago
- Codes for ICASSP 2024 paper: BEAST: Online Joint Beat and Downbeat Tracking Based on Streaming Transformer. An online beat tracking syste…☆40Updated last year