LudovicTuncay / Audio-JEPALinks
Audio-JEPA is an adaptation of the Joint-Embedding Predictive Architecture (JEPA) for self-supervised audio representation learning. Built upon the I-JEPA paradigm, it uses a Vision Transformer (ViT) backbone to predict latent representations of masked spectrogram patches.
☆29Updated 4 months ago
Alternatives and similar repositories for Audio-JEPA
Users that are interested in Audio-JEPA are comparing it to the libraries listed below
Sorting:
- Descript Audio Codec - VAE Variant (.dac-vae): High-Fidelity Audio Compression with Variational Autoencoder☆27Updated 2 months ago
- Implementation of the paper "Variable Bitrate Residual Vector Quantization for Audio Coding"☆11Updated 6 months ago
- ☆13Updated 7 months ago
- Speech Resynthesis and Language Modeling☆27Updated 4 months ago
- Code for ICASSP 2024 Paper: RECAP: Retrieval-Augmented Audio Captioning☆14Updated last year
- Inference code for Interspeech 2025 paper, "LSCodec: Low-Bitrate and Speaker-Decoupled Discrete Speech Codec"☆30Updated 2 weeks ago
- LIGHTVOC AN UPSAMPLING-FREE GAN VOCODER BASED ON CONFORMER AND INVERSE SHORT-TIME FOURIER TRANSFORM☆18Updated last year
- Tidy Tunes is an easy-to-use pipeline for mining high-quality audio data for speech generation models. To do so, it chains multiple open …☆21Updated last week
- Simple tool for speech dataset augmentation for modeling various prosodies.☆14Updated 4 years ago
- Official repository for NAST: Noise Aware Speech Tokenization for Speech Language Models (Interspeech 2024) https://arxiv.org/abs/2406.11…☆46Updated last year
- A spoken version of the textual story cloze benchmark☆19Updated 2 years ago
- Automatic speech annotator processing speech with voice activaty detection, overlapping speech detection, speaker diarization and automat…☆33Updated last year
- ☆19Updated last year
- Forced alignment decoder for Whisper.☆14Updated last year
- ☆33Updated 2 months ago
- Onset-and-Offset-Aware Sound Event Detection☆19Updated 8 months ago
- ESLTTS dataset☆16Updated 9 months ago
- This is the repository for the work "BridgeVoC: Revitalizing Neural Vocoder from a Restoration Perspective".☆28Updated this week
- ☆36Updated last year
- FREECODEC: A DISENTANGLED NEURAL SPEECH CODEC WITH FEWER TOKENS☆23Updated last year
- Collection of scripts from mHuBERT-147.☆32Updated 11 months ago
- Pushing the Limits of Zero-shot End-to-End Speech Translation☆26Updated 10 months ago
- A toolkit dedicate for speech evaluation.☆24Updated last year
- ☆38Updated last year
- ☆56Updated 3 weeks ago
- Streaming Vocos☆29Updated 4 months ago
- DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors☆33Updated 8 months ago
- DiFlow-TTS: Compact and Low-Latency Zero-Shot Text-to-Speech with Factorized Discrete Flow Matching☆57Updated last month
- Extract phoneme-level timestamps from speeh audio.☆89Updated last week
- PyTorch implementation of Miipher-2 [2025] which is a speech restoration model by Google DeepMind☆56Updated last month