Model · Hugging Face · Speech-To-Text
Distil-Whisper
Hugging Face's distillation of Whisper (distil-large-v3.5). Faster than Whisper-large-v3-Turbo on long-form audio at small accuracy cost; English-only — pick when you don't need multilingual.
- Modality
- Speech-To-Text
- License
- MIT (Open)
- Parameter size
- 756M
- Released
- November 1, 2023
- Last verified
- October 28, 2026
- Runs locally
- Yes
What you need to run it
- Mac
- Yes. Any Apple Silicon Mac (M1 or newer) with at least 8 GB of memory. Newer chips are faster, but memory is what decides whether it runs.
- Windows / Linux PC
- NVIDIA works best. A graphics card with at least 4 GB (6 GB recommended) of video memory.
- No graphics card
- Works. Runs on a normal computer's processor, just slower.
Small enough for any recent Mac or a plain CPU; whisper.cpp and MLX Whisper both run it.
Numbers are for: official fp16 weights (756M). Our estimate from the model’s size — the maker publishes no figure.
Strengths
- ~6× faster than the equivalent Whisper checkpoint
- MIT-licensed
- Drop-in compatible with Whisper inference code
Weaknesses
- English-only — no multilingual support
- Slight word-error-rate regression vs full Whisper
Try it
| Where | Type | Notes |
|---|---|---|
| Hugging Face | weights | MIT |
Used in solutions
Official sources
- Model card model
- Paper paper
Change log
- — Added hardware requirements (Mac support, memory, NVIDIA). Source: HF model card + size.
- — Verified still current but dormant: the huggingface/distil-whisper GitHub repo was last pushed 2025-01-08 and the newest checkpoints in the distil-whisper org date from March 2025. Still MIT and usable; for newer open English transcription see NVIDIA Parakeet, and for multilingual see Whisper large-v3 Turbo or Qwen3-ASR.
- — Verified current against the full distil-whisper org (12 models). The distil-large-v3.5 family is newest; no v4 exists. Worth knowing: distil-large-v3 still has roughly 90x the downloads of v3.5.
- — Updated to distil-large-v3.5 (trained on ~4× more data; faster than Whisper-large-v3-Turbo on long-form).
- — Initial entry.
Esc