whisper-medium
Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains without the need for fine-tuning.
Params
760 M
Context
—
Downloads 30d
379 K
Likes
316
Download history
daily snapshots · 106 days
▲ 74 K in the last 30 days (24.3%)
379 K307 K
Oct 12Oct 22Nov 1Nov 10
397 K305 K
Aug 13Sep 12Oct 12Nov 10
397 K305 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 | 3.1 GB | 4.0 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
- WhisperForConditionalGeneration
- Parameters
- 760 M
- Tensor type
- F32
- Vocabulary
- 51,865
- Licence
- apache-2.0
- First seen on the Hub
- 2022-09-26
- Training datasets
- undisclosed
- Common Voice 11.0 (reported)
- 53.87
- LibriSpeech (clean) (reported)
- 2.9
- LibriSpeech (other) (reported)
- 5.9
- Added to our catalog
- 2026-07-28
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any automatic-speech-recognition model