openai / automatic-speech-recognition updated 2 years ago

whisper-small

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
240 M
Context
Downloads 30d
2.9 M
Likes
600
Commercial use: allowed apache-2.0 Not gated SAFETENSORS 99 languages View on Hugging Face ↗

Download history

daily snapshots · 55 days
▲ 136 K in the last 30 days (4.9%)
3.1 M2.2 M
Jul 28Aug 15Sep 2Sep 20

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors f32 1.0 GB 1.6 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
240 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)
87.3
Common Voice 13.0 (reported)
125.69809089961
LibriSpeech (clean) (reported)
3.4322137778867
LibriSpeech (other) (reported)
7.6283045270602
Added to our catalog
2026-07-28
Compare with any automatic-speech-recognition model