
speech recognitionfamily
Distil-Whisper
Knowledge-distilled versions of Whisper trained on pseudo-labelled open data, for faster speech recognition with close to Whisper accuracy.
Levelfamily
Classspeech recognition
Parametersnot in the notes
Contextnot in the notes
Released1 Nov 2023
Opennessopen weights permissive
Runs onnot in the notes
Statusactive
Lineage
distil-large-v3.5 belongs to this familyspeech recognition5 Dec 2024756.41M
distil-large-v3 belongs to this familyspeech recognition21 Mar 2024756.41M
distil-small.en belongs to this familyspeech recognition6 Dec 2023166.13MWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.
Identity
- Developer
- Hugging Face
- Family
- not in the notes
- Released
- 1 Nov 2023 sourcesannouncement page
- Weights published
- –
- Record checked
- 12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- dense transformer encoder-decoder transformer distilled from Whisper
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- 166M (distil-small.en) to 756M (distil-large-v3 and v3.5); further checkpoints distil-medium.en and distil-large-v2.
- Context length
- not in the notes
- Input
- audio
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights permissive
- Licence
- MIT License sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- English
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Industry Use Cases
No industry use case links this model.
Links
Developer
Hugging Facestartup, USA / France
Hugging Facestartup, USA / FranceModel
Distil-WhisperHugging Face, speech recognition
Distil-WhisperHugging Face, speech recognitionUse Casesnone recorded
Who Runs Itnone recorded
Models 3
Organisations 1
Sources
- arxiv.org/abs/2311.00430 https://arxiv.org/abs/2311.00430
- github.com/huggingface/distil-whisper https://github.com/huggingface/distil-whisper
- huggingface.co/distil-whisper/distil-large-v3 https://huggingface.co/distil-whisper/distil-large-v3
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Distil-Whisper", https://aurion.semai.id/models/hugging-face-distil-whisper/, records of October 2026.