metadata
license: mit
base_model: llava-hf/LLaVA-NeXT-Video-7B-hf
pipeline_tag: video-text-to-text
library_name: transformers
tags:
- llava
- video
- sign-language
- multimodal
Sign Language Translation Model (LLaVA Fine-tuned)
This is a fine-tuned version of LLaVA-NeXT-Video-7B for sign language translation.
Usage
from transformers import LlavaNextVideoForConditionalGeneration, AutoProcessor
import torch
model = LlavaNextVideoForConditionalGeneration.from_pretrained("Remostart/sign-language")
processor = AutoProcessor.from_pretrained("Remostart/sign-language")