distil-whisper/distil-large-v3
automatic-speech-recognition model by distil-whisper
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Distil-Whisper was proposed in the paper Robust Knowledge Distillation via Large-Scale Pseudo Labelling. This is the third and final installment of the Distil-Whisper English series. It the knowledge distilled version of OpenAI's Whisper large-v3, the latest and most performant Whisper model to date. Compared to previous Distil-Whisper models, the distillation procedure for distil-large-v3 has been adapted to give superior long-form transcription accuracy with OpenAI's sequential long-form algorithm. The result is a distilled model that performs to within 1% WER of large-v3 on long-form audio using both the sequential and chunked algorithms, and outperforms distil-large-v2 by 4.8% using the sequential algorithm. The model is also faster than previous Distil-Whisper models: 6.3x faster than large-v3, and 1.1x faster than distil-large-v2. Since the sequential algorithm is the "de-facto" transcription algorithm across the most popular Whisper libraries (Whisper cpp, Faster-Whisper, OpenAI Whisper), this distilled model is designed to be compatible with these libraries. You…
Read the full model card ↗ · Preview checked 2026-10-31T04:49:08.930Z
Inside the original model card — Document outline
- Distil-Whisper: distil-large-v3
- Table of Contents
- Transformers Usage
- Short-Form Transcription
- Sequential Long-Form
- Chunked Long-Form
- Speculative Decoding
- Additional Speed & Memory Improvements
- Flash Attention 2
- Torch Scale-Product-Attention (SDPA)
- Torch compile
- 4-bit and 8-bit Inference
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: mit. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
distil-whisper/distil-large-v3 is a automatic-speech-recognition model repository published by distil-whisper on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- automatic-speech-recognition
- Library
- transformers
- Recent downloads (30 days)
- 733,184
- Cumulative likes
- 384
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 756,405,760
- Architecture
- WhisperForConditionalGeneration
- License
- mit
- Access
- Not gated by Hugging Face
- Created
- 2024-03-21T12:10:42.000Z
- Last modified
- 2026-04-21T08:00:18.000Z
Compatibility and lineage
Reported languages: en
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:51:32.899Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
jonatasgrosman/wav2vec2-large-xlsr-53-japanese