Ceaglex / LoVALinks
The code and weight for LoVA. LoVA is a novel model for Long-form Video-to-Audio generation. Based on the Diffusion Transformer (DiT) architecture, LoVA proves to be more effective at generating long-form audio compared to existing autoregressive models and UNet-based diffusion models.
☆15Updated 7 months ago
Alternatives and similar repositories for LoVA
Users that are interested in LoVA are comparing it to the libraries listed below
Sorting:
- ☆113Updated last month
- A project for tri-modal LLM benchmarking and instruction tuning.☆48Updated 6 months ago
- a fully open-source implementation of a GPT-4o-like speech-to-speech video understanding model.☆27Updated 6 months ago
- AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension☆122Updated 10 months ago
- Make-An-Audio-3: Transforming Text/Video into Audio via Flow-based Large Diffusion Transformers☆111Updated 5 months ago
- An easy-to-use, fast, and easily integrable tool for evaluating audio LLM☆150Updated last week
- EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learning [🔥The Exploration of R1 for General Audio-Vi…☆58Updated 5 months ago
- Official Repository of IJCAI 2024 Paper: "BATON: Aligning Text-to-Audio Model with Human Preference Feedback"☆29Updated 7 months ago
- A curated list of Video to Audio Generation☆77Updated 3 months ago
- [NeurIPS 2025] Benchmark data and code for MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix☆169Updated 4 months ago
- LUCY: Linguistic Understanding and Control Yielding Early Stage of Her☆55Updated 6 months ago
- (NIPS 2025) OpenOmni: Official implementation of Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Align…☆102Updated 3 weeks ago
- The dataset and baseline code for Text-to-Audio Grounding (TAG)☆46Updated 3 months ago
- A unified tokenizer that is capable of both extracting semantic information and enabling high-fidelity audio reconstruction.☆101Updated last month
- dLLM: Training Diffusion Large Language Models Made Simple☆116Updated last week
- ☆66Updated 3 weeks ago
- BLSP-Emo: Towards Empathetic Large Speech-Language Models☆49Updated last year
- ☆41Updated last year
- ☆19Updated 3 months ago
- Official PyTorch implementation of EMOVA in CVPR 2025 (https://arxiv.org/abs/2409.18042)☆73Updated 7 months ago
- Towards Fine-grained Audio Captioning with Multimodal Contextual Cues☆81Updated 3 weeks ago
- OpenS2S : Advancing Fully Open-Source End-to-End Empathetic Large Speech Language Model☆84Updated 3 months ago
- This reporsitory contains metadata of WavCaps dataset and codes for downstream tasks.☆248Updated last year
- SpeechAgents: Human-Communication Simulation with Multi-Modal Multi-Agent Systems☆84Updated last year
- [ACL 2025 Main] SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition☆232Updated 4 months ago
- Chinese-Mimi 是对 Moshi 模型的声码器进行了中文语料上的适配。☆31Updated 7 months ago
- BLSP: Bootstrapping Langauge-Speech Pre-training via Behavior Alignment of Continuation Writing☆55Updated last year
- Code for NeurIPS 2023 paper "DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation".☆63Updated last year
- MOSS-Speech is a true speech-to-speech large language model without text guidance.☆55Updated 2 weeks ago
- 🤗 R1-AQA Model: mispeech/r1-aqa☆300Updated 6 months ago