distil-whisper / automatic-speech-recognition updated 4 months ago

distil-large-v3

Distil-Whisper was proposed in the paper Robust Knowledge Distillation via Large-Scale Pseudo Labelling.

Params
760 M
Context
Downloads 30d
517 K
Likes
382
Commercial use: allowed mit Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 56 days
▲ 368 K in the last 30 days (41.6%)
1.7 M511 K
Jul 28Aug 15Sep 3Sep 21

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 f16 4.5 GB 5.6 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
760 M
Tensor type
F16
Vocabulary
51,866
Licence
mit
First seen on the Hub
2024-03-21
Training datasets
undisclosed
Added to our catalog
2026-07-28
Compare with any automatic-speech-recognition model