Video-Text-to-Text
Transformers
Safetensors
qwen2_5_omni
text-to-audio
multimodal
video-captioning
audio-visual
ugc
Instructions to use openinterx/UGC-VideoCaptioner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openinterx/UGC-VideoCaptioner with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("openinterx/UGC-VideoCaptioner") model = AutoModelForMultimodalLM.from_pretrained("openinterx/UGC-VideoCaptioner", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tiktok_qa_sample.png from openinterx/UGC-VideoCaptioner: direct link, hf CLI and curl.
- Browser
- Download file 857 kB
-
https://huggingface.co/openinterx/UGC-VideoCaptioner/resolve/main/tiktok_qa_sample.png
- Command line
-
hf download hf://openinterx/UGC-VideoCaptioner/tiktok_qa_sample.png
-
curl -L -o tiktok_qa_sample.png https://huggingface.co/openinterx/UGC-VideoCaptioner/resolve/main/tiktok_qa_sample.png
857 kB

- Xet hash:
- 49ce72813231c3e3d223227f94f05ae0dc3eee7822ac5dd371efcc91dadab6de
- Size of remote file:
- 857 kB
- SHA256:
- fca026f60429b76fb286e91fb8a33bc40ebf4e5c9257e3559e44801bad79c7d1
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.