AudioRubrics

umd-zhou-lab/AudioRubrics

Audio Text To Text12.2B parametersLicense: other

Tracked by OpenModelStats since September 12, 2026View on Hugging Face ↗

Downloads 30D: 51
Total downloads: 160
Gained 7D: +16(increase)
Gained 30D: —
Likes: 3; +0 in 7D
Rank · tracked models: —; –this week
Parameters: 12.2B
Last source update: Aug 5, 2026

AudioRubrics gained 16 downloads during the last seven tracked days.

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-09-12. Charts appear as daily observations accumulate.

Overview

AudioRubrics is a audio text to text model published by umd-zhou-lab. OpenModelStats has tracked the model since Sep 12, 2026, most recently observing it Oct 11, 2026.

Published: Jul 11, 2026
Last updated: Aug 5, 2026
Library: —
License: other
Task: Audio Text To Text
Parameters: 12,180,092,832
Spaces: 1
Derivative models: —
Velocity 7D/day: 2

safetensorsqwen2_5_omniaudioaudio-reasoningreinforcement-learningaudio-text-to-textenarxiv:2608.02831base_model:Qwen/Qwen2.5-Omni-7Bbase_model:finetune:Qwen/Qwen2.5-Omni-7Blicense:otherregion:us

Publisher

umd-zhou-labView publisher statistics →

Model family

Based on base-model relationships reported by the source's metadata.

Base model

Qwen2.5-Omni-7B295K

Sibling models

Similar models

Models similar to AudioRubrics
Model	Task	DL 30D	Likes	Params
acestep-transcriberACE-Step	Audio Text To Text	3,073	65	10.7B
MOSS-Music-8B-InstructOpenMOSS-Team	Audio Text To Text	3,022	43	9.1B
MOSS-Audio-8B-InstructOpenMOSS-Team	Audio Text To Text	2,311	50	9.1B
MOSS-Music-8B-ThinkingOpenMOSS-Team	Audio Text To Text	1,021	42	9.1B
MOSS-Audio-8B-ThinkingOpenMOSS-Team	Audio Text To Text	651	84	9.1B
MOSS-Music-8B-Thinking-8bitmlx-community	Audio Text To Text	449	8	9.1B