crlandsc / torch-log-wmse
logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source separation systems.
☆39Updated last week
Alternatives and similar repositories for torch-log-wmse:
Users that are interested in torch-log-wmse are comparing it to the libraries listed below
- Unofficial PyTorch implementation of "SCNet: Sparse Compression Network for Music Source Separation"☆54Updated last year
- [ICASSP 2025] "FLowHigh: Towards efficient and high-quality audio super-resolution with single-step flow matching"☆61Updated 3 months ago
- ☆43Updated 10 months ago
- A standardized toolkit of Kernel Audio Distance (KAD)—a distribution-free, unbiased, and computationally efficient metric for evaluating …☆67Updated last month
- An invertible and differentiable implementation of the Constant-Q Transform (CQT).☆60Updated 2 years ago
- Source code for training models and using the hyperbolic interface proposed in our ICASSP 2023 paper, “Hyperbolic Audio Source Separation…☆65Updated 2 years ago
- ☆76Updated last week
- ☆25Updated last year
- Open implementation of UNIVERSE and UNIVERSE++ diffusion-based speech enhancement models.☆94Updated 8 months ago
- Official implementation of "AEROMamba: An efficient architecture for audio super-resolution using generative adversarial networks and sta…☆40Updated 5 months ago
- Bandwidth Extension of Historical Recordings using Generative Adversarial Networks☆35Updated last year
- Source Separation training codebase for the Sound Demixing Challenge 2023.☆42Updated last year
- Landing Page for All Things Source Separation☆27Updated 5 months ago
- (ICASSP 2025) Learning Source Disentanglement in Neural Audio Codec☆32Updated last week
- ☆38Updated 3 months ago
- Unsupervised Music Source Separation Using Differentiable Parametric Source Models☆63Updated 2 years ago
- Unofficial implementation of NANSY++ in Pytorch Lightning☆50Updated last year
- Official repo for DisCoder: High-Fidelity Music Vocoder using Neural Audio Codecs presented at ICASSP 2025☆28Updated 2 months ago
- ☆96Updated 4 months ago
- An official implementation of the ICASSP 2024 paper: Dual-Path TFC-TDF UNet for Music Source Separation☆87Updated last year
- Source code and demo for INTERSPEECH 2024 paper: Noise-robust Speech Separation with Fast Generative Correction☆37Updated 5 months ago
- PAM is a no-reference audio quality metric for audio generation tasks☆60Updated 9 months ago
- ☆81Updated 2 years ago
- TAPE: An End-to-End Timbre-Aware Pitch Estimator☆22Updated last year
- Codebase for the paper 'EncodecMAE: Leveraging neural codecs for universal audio representation learning'☆96Updated 9 months ago
- A DDSP-based neural voice synthesiser.☆116Updated 5 months ago
- [PyTorch] Minimal codebase for MusicGen models☆60Updated 3 months ago
- A fast python library for aligning similar audio snippets passed in as NumPy arrays☆47Updated last month
- Differentiable dynamic range controller in PyTorch.☆48Updated 5 months ago
- Repo for source code of EBEN: Extreme Bandwidth Extension Network☆73Updated 3 months ago