AI & ML interests

Robust knowledge distillation of the Whisper model via large-scale pseudo-labelling.

Distil-Whisper

[Paper] [Models] [Colab] [Training Code]

Distil-Whisper is a distilled version of Whisper that is 6 times faster, 49% smaller, and performs within 1% word error rate (WER) on out-of-distribution evaluation sets:

Model Params / M Rel. Latency ↑ Short-Form WER ↓ Long-Form WER ↓
large-v3 1550 1.0 8.4 11.0
distil-large-v3 756 6.3 9.7 10.8
distil-large-v2 756 5.8 10.1 11.6
distil-medium.en 394 6.8 11.1 12.4
distil-small.en 166 5.6 12.1 12.8

For most applications, we recommend the latest distil-large-v3 checkpoint, since it is the most performant distilled checkpoint and compatible across all Whisper libraries. The only exception is resource-constrained applications with very little memory, such as on-device or mobile applications, where the distil-small.en is a great choice, since it is only 166M parameters and performs within 4% WER of Whisper large-v3.

Note: Distil-Whisper is currently only available for English speech recognition. We are working with the community to distill Whisper on other languages. If you are interested in distilling Whisper in your language, check out the provided training code. We will soon update the repository with multilingual checkpoints when ready!