ColorfulAI/LLaVA-NeXT-Speech

Dataset

we randomly select 300k visual instructions from LLaVA-NeXT, and convert the user queries into audio using CosyVoice with randomly selected audio prompts from VoiceAssistant-400K.

3 commits

5 linked in READMEs

updated Apr 1, 2025

See the code

README

we randomly select 300k visual instructions from LLaVA-NeXT, and convert the user queries into audio using CosyVoice with randomly selected audio prompts from VoiceAssistant-400K.

Similar repos

kaiyuyue/llava-1.5-665k-genqa-500k-instructions

Dataset

LLaVA-1.5-665K-GenQA-Random-500K

lmms-lab/LLaVA-NeXT-Data

Dataset

Dataset Card for LLaVA-NeXT

X2FD/LVIS-Instruct4V

Dataset

**LVIS-Instruct4V**:

liuhuadai/AudioCoT

Dataset

AudioCoT

fnlp/AnyInstruct

Dataset

Dataset details

MatthewCYM/VoiceBench

[TACL'26] VoiceBench: Benchmarking LLM-Based Voice Assistants

400

ColorfulAI/M4-IT

Dataset

This dataset, M4-IT, is a synthetic instruction finetuning dataset used in the development of the…

LLaVA-VL/llava-plus-data

Dataset

LLaVA-Plus Instructed Dataset Card

Linked in READMEs

FunAudioLLM/CosyVoice

Multi-lingual large voice generation model, providing inference, training and deployment full-stack…

23,820

README badge

LLaVA-VL/LLaVA-NeXT

4,727

README badge

OmniMMI/OpenOmniNexus

a fully open-source implementation of a GPT-4o-like speech-to-speech video understanding model.

README badge

patrick-tssn/Open-Omni-Nexus

a fully open-source implementation of a GPT-4o-like speech-to-speech video understanding model.

README badge

patrick-tssn/M4

[CVPR 2025] OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts

README badge

ColorfulAI/LLaVA-NeXT-Speech

Dataset

we randomly select 300k visual instructions from LLaVA-NeXT, and convert the user queries into audio using CosyVoice with randomly selected audio prompts from VoiceAssistant-400K.

3 commits

5 linked in READMEs

updated Apr 1, 2025

See the code

README

we randomly select 300k visual instructions from LLaVA-NeXT, and convert the user queries into audio using CosyVoice with randomly selected audio prompts from VoiceAssistant-400K.