From the model card
Fields below are copied from the tags and counters on the HuggingFace repository omni-research/Tarsier2-Recap-7b at our last fetch. They are set by the uploader, not verified by us; rows with no tag are omitted. How this page is made.
- Publisher (HF namespace)
- omni-research
- Weight formats
- safetensors
- License tag
apache-2.0— read the license file in the repo before relying on it- Papers cited
- arXiv:2501.07888
- Downloads (HF counter at last fetch)
- 572,329
- Likes (HF counter at last fetch)
- 39
- Model card
- https://huggingface.co/omni-research/Tarsier2-Recap-7b
Use cases
- Automated video description for training data curation pipelines
- Dense captioning for video accessibility and descriptive audio tracks
- Generating text representations of video for downstream retrieval systems
- Synthetic training data generation for video-language model research
Pros
- Produces temporally detailed captions beyond simple scene-level labels
- Apache 2.0 license enables commercial use in data processing pipelines
- 7B scale runs on a single 24GB GPU for batch captioning workloads
Cons
- No official pipeline_tag reduces HuggingFace tooling auto-routing support
- Inference requires custom loading code rather than a standard transformers pipeline
- Not suitable for real-time or streaming video captioning at low latency
Tags
safetensorsvideo LLMarxiv:2501.07888license:apache-2.0region:us