openai / automatic-speech-recognition updated 2 years ago

whisper-base

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
70 M
Context
Downloads 30d
1.6 M
Likes
289
Commercial use: allowed apache-2.0 Not gated SAFETENSORS 99 languages View on Hugging Face ↗

Download history

daily snapshots · 55 days
▲ 888 K in the last 30 days (36.0%)
6.4 M1.6 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 0.3 GB 0.8 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
70 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)
131
LibriSpeech (clean) (reported)
5.0087691176193
LibriSpeech (other) (reported)
12.849362732121
Added to our catalog
2026-07-28
Compare with any automatic-speech-recognition model