Qwen3-ASR-Refiner-4B
Aye10032/Qwen3-ASR-Refiner-4B
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 158
- Total downloadsCumulative all-time download counter reported by the source platform.
- 518
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +28(increase)
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 0
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #10933 among tracked Text Generation models.
- #38,423
- –this week
- Parameters
- 4B
- Last source update
- Aug 23, 2026
- MomentumOpenModelStats' composite rising-model signal (0–100): a percentile blend of absolute 7-day download gains, capped percentage growth, and likes gained. See Methodology.
- 14.4
- Qwen3-ASR-Refiner-4B gained 28 downloads during the last seven tracked days.
- It moved from #10992 to #10933 among tracked Text Generation models this week.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
Qwen3-ASR-Refiner-4B is a text generation model published by Aye10032. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Sep 26, 2026.
- Published
- Aug 23, 2026
- Last updated
- Aug 23, 2026
- Library
- transformers
- License
- apache-2.0
- Task
- Text Generation
- Parameters
- 4,022,468,096
- Spaces
- 0
- Derivative models
- —
- Velocity 7D/day
- 4
transformerssafetensorsqwen3text-generationasr-post-processingspoken-to-writtentext-normalizationconversationalzhdataset:Aye10032/WenetSpeech-Formal-Textbase_model:Qwen/Qwen3-4Bbase_model:finetune:Qwen/Qwen3-4B
Publisher
Aye10032View publisher statistics →Model family
Based on base-model relationships reported by the source's metadata.
Base model
- Qwen3-4B6.5M
Sibling models
- zerank-2-reranker653.6K
- Qwen3-4B-GGUF457.1K
- Parable-Qwen3-4B-Claude-Fable-5-GGUF417.2K
- Qwen3-4B-GGUF408.9K
- Qwen3-4B-GGUF273.9K
- Qwen3-4B-AWQ253.2K
- Qwen3-4B242.4K
- loras188.8K
Similar models
| Model | DL 30D |
|---|---|
| Qwen3-4BQwen | 6.5M |
| Qwen3-4B-Instruct-2507Qwen | 4M |
| Qwen3-4B-BaseQwen | 1.4M |
| Qwen3-4B-Thinking-2507Qwen | 405K |
| Qwen3-4B-AWQQwen | 253.2K |
| qwen3-4b-base-dapo-v4ReliquaryForge | 215.3K |