GitHub - hari-huynh/viVQA-voice-assistant: Voice assistant using Multimodal LLMs - LLaVA-NeXT (Mistral 7B) finetuned & PhoWhisper

hari-huynh / viVQA-voice-assistant Public

Notifications You must be signed in to change notification settings
Fork 4
Star 3

Voice assistant using Multimodal LLMs - LLaVA-NeXT (Mistral 7B) finetuned & PhoWhisper

Apache-2.0 license

3 stars 4 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 14 Commits
llava		llava
moellava		moellava
LICENSE.txt		LICENSE.txt
README.md		README.md
builder.py		builder.py
dataset.py		dataset.py
finetune.py		finetune.py
utils.py		utils.py

Repository files navigation

Voice assistant using Multimodal LLMs

Contributors

Yixin

Bailey

_{QuangTruong-Nguyen}

Casper/

About

Voice assistant using Multimodal LLMs - LLaVA-NeXT (Mistral 7B) finetuned & PhoWhisper

text-to-speech lora visual-question-answering llava multimodal-large-language-models audio-speech-recognition mistral-7b

Apache-2.0 license

Report repository

Releases

No releases published

Packages

No packages published

Contributors 3

Languages