ast-finetuned-audioset-10-10-0.4593
Audio Spectrogram Transformer (AST) model fine-tuned on AudioSet. It was introduced in the paper AST: Audio Spectrogram Transformer by Gong et al. and first released in this repository.
Params
90 M
Context
—
Downloads 30d
1.9 M
Likes
389
Download history
daily snapshots · 106 days
▲ 807 K in the last 30 days (73.9%)
1.9 M1.1 M
Oct 12Oct 22Nov 1Nov 10
1.9 M688 K
Aug 13Sep 12Oct 12Nov 10
1.9 M620 K
Jul 28Sep 1Oct 6Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f32 | 0.3 GB | 0.9 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- ASTForAudioClassification
- Parameters
- 90 M
- Tensor type
- F32
- Layers / heads
- 12 / 12
- Licence
- bsd-3-clause
- First seen on the Hub
- 2022-11-14
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any audio-classification model