Unified_Audio_Schema
tencent/Unified_Audio_Schema
Tracked by OpenModelStats since November 10, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 102
- Total downloadsCumulative all-time download counter reported by the source platform.
- 407
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- —
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 12
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #83 among tracked Audio Text To Text 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 OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
Unified_Audio_Schema is a audio text to text model published by tencent. OpenModelStats has tracked the model since Nov 10, 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
| Model | DL 30D |
|---|---|
| VibeVoice-ASR-HFmicrosoft | 15.1K |
| midashenglm-spatialmispeech | 437 |
| midashenglm-7b-0804-fp32mispeech | 5,375 |
| midashenglm-7b-1021-bf16mispeech | 1,875 |
| Qwen2-Audio-7B-InstructQwen | 120.5K |
| Qwen2-Audio-7BQwen | 7,037 |