Unified_Audio_Schema

tencent/Unified_Audio_Schema

Audio Text To Text8.3B parametersLicense: other
Tracked by OpenModelStats since October 23, 2026View on Hugging Face ↗
Downloads 30D
102
Total downloads
407
Gained 7D
—
Gained 30D
—
Likes
12
Rank · tracked models
#75,448
444(down 444 places)this week
Parameters
8.3B
Last source update
Apr 16, 2026
  • It moved from #82 to #83 among tracked Audio Text To Text models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Unified_Audio_Schema is a audio text to text model published by tencent. OpenModelStats has tracked the model since Oct 23, 2026, most recently observing it Oct 30, 2026.

Published
Apr 3, 2026
Last updated
Apr 16, 2026
Library
—
License
other
Task
Audio Text To Text
Parameters
8,332,630,656
Spaces
—
Derivative models
—
Velocity 7D/day
—
safetensorsuas_audioaudiospeechsoundmusicaudio-understandingASRaudio-captioningTTSaudio-language-modelaudio-llm

Publisher

tencentView publisher statistics →

Derived from Qwen/Qwen2.5-7B (reported by the source; parent not yet tracked).

Similar models

Models similar to Unified_Audio_Schema
ModelDL 30D
VibeVoice-ASR-HFmicrosoft15.1K
midashenglm-spatialmispeech437
midashenglm-7b-0804-fp32mispeech5,375
midashenglm-7b-1021-bf16mispeech1,875
Qwen2-Audio-7B-InstructQwen120.5K
Qwen2-Audio-7BQwen7,037
tencent/Unified_Audio_Schema — Downloads, Growth & Stats | OpenModelStats