YuanGongND / ast
Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".
☆1,162Updated last year
Related projects ⓘ
Alternatives and complementary repositories for ast
- Code for the AAAI 2022 paper "SSAST: Self-Supervised Audio Spectrogram Transformer".☆364Updated 2 years ago
- Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.☆963Updated last week
- The official code repo of "HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection"☆366Updated 3 months ago
- Efficient Training of Audio Transformers with Patchout☆305Updated 10 months ago
- ☆1,356Updated 3 months ago
- A Python library for audio data augmentation. Inspired by albumentations. Useful for machine learning.☆1,875Updated last week
- This repo hosts the code and models of "Masked Autoencoders that Listen".☆544Updated 7 months ago
- ☆471Updated 4 months ago
- Audio processing by using pytorch 1D convolution network☆1,032Updated 9 months ago
- [Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)☆959Updated 10 months ago
- LEAF is a learnable alternative to audio features such as mel-filterbanks, that can be initialized as an approximation of mel-filterbanks…☆501Updated 2 years ago
- This repository aims at providing efficient CNNs for Audio Tagging. We provide AudioSet pre-trained models ready for downstream training …☆233Updated 6 months ago
- Learning audio concepts from natural language supervision☆487Updated 2 months ago
- Pytorch port of Google Research's VGGish model used for extracting audio features.☆377Updated 3 years ago
- Contrastive Language-Audio Pretraining☆1,422Updated 4 months ago
- A library for speech data augmentation in time-domain☆647Updated 3 years ago
- OpenL3: Open-source deep audio and image embeddings☆467Updated last year
- In defence of metric learning for speaker recognition☆1,058Updated 7 months ago
- Unofficial reimplementation of ECAPA-TDNN for speaker recognition (EER=0.86 for Vox1_O when train only in Vox2)☆610Updated 7 months ago
- SincNet is a neural architecture for efficiently processing raw audio samples.☆1,139Updated 3 years ago
- VGGSound: A Large-scale Audio-Visual Dataset☆291Updated 3 years ago
- Collection of audio-focused loss functions in PyTorch☆744Updated 3 months ago
- Code, Dataset, and Pretrained Models for Audio and Speech Large Language Model "Listen, Think, and Understand".☆386Updated 6 months ago
- List of speech synthesis papers.☆1,003Updated last year
- Improved Wave-U-Net implemented in Pytorch☆312Updated 3 months ago
- A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain☆641Updated 2 years ago
- Self-Supervised Speech Pre-training and Representation Learning Toolkit☆2,271Updated this week
- INTERSPEECH 2023-2024 Papers: A complete collection of influential and exciting research papers from the INTERSPEECH 2023-24 conference. …☆642Updated 3 months ago
- 🔦 A Pytorch implementation of GoogleBrain's SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition☆490Updated 3 years ago
- Audio Dataset for training CLAP and other models☆637Updated 9 months ago