SonyCSLParis / pesto-fullLinks
Full models and training code for PESTO
☆68Updated last year
Alternatives and similar repositories for pesto-full
Users that are interested in pesto-full are comparing it to the libraries listed below
Sorting:
- Code for the "NoiseBandNet: Controllable Time-Varying Neural Synthesis of Sound Effects Using Filterbanks" paper.☆37Updated last year
- Differentiable dynamic range controller in PyTorch.☆50Updated 8 months ago
- Source Separation training codebase for the Sound Demixing Challenge 2023.☆43Updated 2 years ago
- Synthesis of percussion sounds using sinusoidal modelling, DDSP noise synthesis, and a neural source filter approach.☆30Updated 7 months ago
- ☆84Updated 2 years ago
- Frechet Audio Distance evaluation in PyTorch☆36Updated 2 years ago
- The ArtificialSongGenerator automatically composes and compiles the Artifical Audio Multitrack dataset (AAM).☆21Updated 6 months ago
- PyTorch version of Spotify's Basic Pitch☆40Updated last year
- Audio production style transfer with inference-time optimization☆42Updated 9 months ago
- The official implementation of TokenSynth (ICASSP 2025)☆73Updated 3 months ago
- ☆28Updated 2 years ago
- Repository for the paper "Combining audio control and style transfer using latent diffusion", accepted at ISMIR 2024☆51Updated 6 months ago
- A project to synthesize massive amounts of multitrack audio data from MIDI.☆62Updated 5 years ago
- Multitrack music mixing style transfer given a reference song using differentiable mixing console.☆50Updated last month
- ☆57Updated 2 years ago
- Banquet: A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems☆71Updated 3 weeks ago
- Unsupervised Music Source Separation Using Differentiable Parametric Source Models☆63Updated 2 years ago
- Repository for Semi-supervised Synthesizer Sound Matching with Differentiable DSP☆23Updated 3 years ago
- MR-MT3: Memory Retaining Multi-Track Music Transcription to Mitigate Instrument Leakage☆44Updated 2 months ago
- list of MIR dataset papers presented at ISMIR 2022☆61Updated 2 years ago
- ☆58Updated 2 months ago
- Code for the paper "Timbre-Trap: A Low-Resource Framework for Instrument-Agnostic Music Transcription"☆39Updated last year
- A DDSP-based neural voice synthesiser.☆120Updated 9 months ago
- Code for ISMIR 2020 paper: "Multiple F0 Estimation in Vocal Ensembles using Convolutional Neural Networks"☆55Updated 9 months ago
- Code for the paper "Toward Fully Self-Supervised Multi-Pitch Estimation".☆23Updated 6 months ago
- Repository for ISMIR 2022 tutorial T3(M): Designing Controllable Synthesis System for Musical Signals☆28Updated 2 years ago
- Demucs Lightning: A PyTorch lightning version of Demucs with Hydra and Tensorboard features☆85Updated 2 years ago
- ☆39Updated 2 years ago
- An invertible and differentiable implementation of the Constant-Q Transform (CQT).☆62Updated 2 years ago
- ☆34Updated last month