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.
☆39Updated 6 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:
- ☆13Updated 10 months ago
- OpenFLAM: Frame-Wise Language-Audio Model☆31Updated this week
- Speech Resynthesis and Language Modeling☆27Updated 7 months ago
- Event Relation in Text-to-Audio (TTA) Generation☆20Updated 10 months ago
- The open source code of ALMTokenizer2: Towards Low bit-rate and Semantic-rich Audio Tokenizer with Flow-based Scalar Diffusion Transforme…☆42Updated 4 months ago
- PyTorch implementation of the ICASSP-24 paper: "Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Superv…☆38Updated 2 years ago
- Official Repository for "Efficient Vocal Source Separation Through Windowed RoFormer"☆42Updated 2 months ago
- PyTorch Implementation of [WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for Authenticity Verification](https://arxiv.or…☆16Updated 5 months ago
- ProsodyLM: Uncovering the Emerging Prosody Processing Capabilities in Speech Language Models☆33Updated last month
- This is the official train-dev-test release of the Interspeech2024 Discrete Speech Representation Challenge.☆32Updated 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 …☆22Updated 2 months ago
- Evaluation tool used in the BigVSAN paper☆14Updated last year
- (ICASSP 2025) Learning Source Disentanglement in Neural Audio Codec☆45Updated 7 months ago
- 5Hz Deep-Compression Speech VAE for AR-Diffusion and CALMs☆56Updated last month
- The open-source code of UniAudio2.0☆74Updated 4 months ago
- ☆52Updated 6 months ago
- Bilingual Singing Voice Synthesis☆18Updated last year
- FREECODEC: A DISENTANGLED NEURAL SPEECH CODEC WITH FEWER TOKENS☆24Updated last year
- Baseline for DCASE 2024 Task 9: "Language-Queried Audio Source Separation"☆26Updated last year
- This repository contains the code for the paper "voc2vec: A Foundation Model for Non-Verbal Vocalization", accepted at ICASSP 2025.☆46Updated 9 months ago
- Official Code for SyllableLM: Learning Coarse Semantic Units for Speech Language Models☆58Updated 6 months ago
- A repo that builds text to music datasets from scratch, used in MuseContorlLite [ICML2025]☆27Updated 7 months ago
- T5Voice is a lightweight PyTorch implementation of T5-based text-to-speech synthesis, supporting both streaming and non-streaming speech …☆28Updated 2 months ago
- ☆15Updated 9 months ago
- ☆21Updated last year
- Source code for the EMNLP 2025 paper “DM-Codec: Distilling Multimodal Representations for Speech Tokenization”☆56Updated 7 months ago
- A complete cross-modal RAG system for end-to-end speech-to-speech large models, including ASR-based Retrieval and E2E Retrieval.☆27Updated 6 months ago
- Kanade is a speech tokenizer that encodes speech into compact content tokens and global embeddings and decodes them back to mel spectrogr…☆32Updated this week
- Variable Bitrate Residual Vector Quantization for Audio Coding☆50Updated 8 months ago
- Task Vector in TTS: Toward Emotionally Expressive Dialectal Speech Synthesis☆33Updated 3 weeks ago