google-research / leaf-audioLinks
LEAF is a learnable alternative to audio features such as mel-filterbanks, that can be initialized as an approximation of mel-filterbanks, and then be trained for the task at hand, while using a very small number of parameters.
☆509Updated 3 years ago
Alternatives and similar repositories for leaf-audio
Users that are interested in leaf-audio are comparing it to the libraries listed below
Sorting:
- Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.☆1,046Updated 4 months ago
- Audio processing by using pytorch 1D convolution network☆1,069Updated 3 weeks ago
- Audio transformations library for PyTorch☆232Updated 3 years ago
- A library for speech data augmentation in time-domain☆661Updated 3 years ago
- An open source dataset for source separation☆423Updated last year
- ☆493Updated 11 months ago
- Collection of audio-focused loss functions in PyTorch☆783Updated 10 months ago
- Code for the AAAI 2022 paper "SSAST: Self-Supervised Audio Spectrogram Transformer".☆385Updated 2 years ago
- Efficient Training of Audio Transformers with Patchout☆335Updated last year
- Fast PyTorch based DSP for audio and 1D signals☆442Updated 3 months ago
- Code for SuDoRm-Rf networks for efficient audio source separation. SuDoRm-Rf stands for SUccessive DOwnsampling and Resampling of Multi-R…☆324Updated last year
- BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation☆211Updated 2 years ago
- The official code repo of "HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection"☆412Updated 9 months ago
- Perceptual Metrics of Audio - perceptually relevant loss function. DPAM and CDPAM☆362Updated 2 years ago
- This repository aims at providing efficient CNNs for Audio Tagging. We provide AudioSet pre-trained models ready for downstream training …☆285Updated 6 months ago
- ☆224Updated last year
- A PyTorch implementation of DNN-based source separation.☆301Updated 3 years ago
- The official code repo for "Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data", in AAAI 2022☆199Updated 2 years ago
- Improved Wave-U-Net implemented in Pytorch☆343Updated 10 months ago
- 🔦 A Pytorch implementation of GoogleBrain's SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition☆494Updated 3 years ago
- spafe: Simplified Python Audio Features Extraction☆474Updated 2 months ago
- Implementation of WaveGrad high-fidelity vocoder from Google Brain in PyTorch.☆403Updated 3 years ago
- Official PyTorch Implementation of CleanUNet (ICASSP 2022)☆322Updated last year
- Repo associated to the DESED dataset, download and creation of data☆139Updated 10 months ago
- Python library for downloading, loading & working with sound datasets☆340Updated 2 weeks ago
- Speaker embedding (d-vector) trained with GE2E loss☆282Updated last year
- Official PyTorch implementation of Contrastive Learning of Musical Representations☆326Updated 10 months ago
- A didactic toolkit to rapidly prototype audio classifiers with pre-trained Tensorflow models and Scikit-learn☆143Updated 2 years ago
- Problem Agnostic Speech Encoder☆441Updated last year
- An implementation of the Contrast Predictive Coding (CPC) method to train audio features in an unsupervised fashion.☆358Updated 3 years ago