tencent/Youtu-Parsing-Omni
image-text-to-text model by tencent
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
One model that parses documents, images, charts, geometry, audio and video into structured JSON Youtu-Parsing-Omni is a compact (5B) omni-modal parsing model. Given a single input — a document page, a natural image, a chart / flowchart, a geometry figure, an audio clip or an audio-visual video — it produces one structured JSON envelope that covers both perception (layout elements, text, tables, formulas, bounding boxes, timestamps, ASR, OCR, acoustic events, camera motion) and cognition (captions, narratives, reports). The output family is selected by the task prompt (--task in the examples, keys of prompts/youtuparsingomni.json). Highlights (see the technical report for details): Existing omni-modal parsers (a) encode pixels and audio with two separately pre-trained towers whose streams first meet inside the language model. Youtu-Parsing-Omni (b) replaces both towers with a single Youtu-Omni-Encoder, initialized from a pre-trained text language model to strengthen text reading. Thin modality-specific stems map pixels and log-mel frames to…
Read the full model card ↗ · Preview checked 2026-10-30T17:14:57.074Z
Inside the original model card — Document outline
- News
- Introduction
- Method
- One encoder for every modality
- Audio-visual fusion inside perception
- One schema for every task: OmniSchema-Aware On-Policy Distillation (OSAD)
- Model Zoo
- Results
- OmniDocBench v1.6
- OmniParsingBench
- ChemOCR & PDMX-Synth
- Quick Start
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
tencent/Youtu-Parsing-Omni is a image-text-to-text model repository published by tencent on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 1,552
- Cumulative likes
- 107
- Hugging Face trending score
- 57
- Reported safetensors parameters
- 5,334,472,192
- Architecture
- YoutuVITAForCausalLM
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-10-09T06:42:18.000Z
- Last modified
- 2026-10-10T17:04:14.000Z
Compatibility and lineage
Language coverage was not reported.
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-17T06:41:56.108Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.