ituvisionlab / EdVAELinks
Official PyTorch implementation of "EdVAE: Mitigating Codebook Collapse with Evidential Discrete Variational Autoencoders"
☆12Updated last year
Alternatives and similar repositories for EdVAE
Users that are interested in EdVAE are comparing it to the libraries listed below
Sorting:
- A neural speech codec based on discrete WavLM representations☆24Updated last year
- The demo page for ALMTokenizer☆55Updated 8 months ago
- Source code for the EMNLP 2025 paper “DM-Codec: Distilling Multimodal Representations for Speech Tokenization”☆54Updated 6 months ago
- Audio-JEPA is an adaptation of the Joint-Embedding Predictive Architecture (JEPA) for self-supervised audio representation learning. Buil…☆38Updated 5 months ago
- An ODE-based generative neural vocoder using Rectified Flow☆59Updated 2 years ago
- [ICASSP 2025] AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder☆12Updated 9 months ago
- ☆13Updated 9 months ago
- The open source code of ALMTokenizer2: Towards Low bit-rate and Semantic-rich Audio Tokenizer with Flow-based Scalar Diffusion Transforme…☆42Updated 3 months ago
- This is the official train-dev-test release of the Interspeech2024 Discrete Speech Representation Challenge.☆32Updated last year
- A toolkit for researchers in the multimodal sound separation.☆16Updated 2 years ago
- A lightweight audio codec based on a single quantizer☆65Updated 4 months ago
- (ICASSP 2025) Learning Source Disentanglement in Neural Audio Codec☆42Updated 7 months ago
- Please visit https://thuhcsi.github.io/SnakeGAN/☆37Updated 2 years ago
- ICASSP 2024 - Generative De-Quantization for Neural Speech Codec via Latent Diffusion.☆55Updated last month
- Inference code for Interspeech 2025 paper, "LSCodec: Low-Bitrate and Speaker-Decoupled Discrete Speech Codec"☆34Updated last month
- [ICASSP2025] Official code for VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesis☆39Updated 8 months ago
- A spoken version of the textual story cloze benchmark☆20Updated 2 years ago
- Variable Bitrate Residual Vector Quantization for Audio Coding☆50Updated 7 months ago
- Inference codebase for "Cacophony: An Improved Contrastive Audio-Text Model". Preprint: https://arxiv.org/abs/2402.06986☆48Updated last year
- Baseline for DCASE 2024 Task 9: "Language-Queried Audio Source Separation"☆26Updated last year
- [SpeechCom Journal] Learning and controlling the source-filter representation of speech with a variational autoencoder☆45Updated 2 years ago
- FREECODEC: A DISENTANGLED NEURAL SPEECH CODEC WITH FEWER TOKENS☆24Updated last year
- Bilingual Singing Voice Synthesis☆18Updated last year
- PyTorch implementation of the ICASSP-24 paper: "Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Superv…☆38Updated last year
- ☆51Updated 5 months ago
- 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 last month
- Speech Resynthesis and Language Modeling☆27Updated 6 months ago
- Streaming Vocos☆29Updated 6 months ago
- Code for INTERSPEECH 2023 paper "mdctGAN: Taming transformer-based GAN for speech super-resolution with Modified DCT spectra"☆62Updated 2 years ago
- ☆21Updated last year