---
language:
  - en
tags:
  - audio
  - automatic-speech-recognition
license: mit
---

# Distil-Whisper: distil-large-v3 for Whisper cpp

This repository contains the model weights for [distil-large-v3](https://huggingface.co/distil-whisper/distil-large-v3)
converted to [GGML](https://github.com/ggerganov/ggml) format. GGML is the weight format expected by C/C++ packages 
such as [Whisper.cpp](https://github.com/ggerganov/whisper.cpp), for which we provide an example below.

Compared to previous Distil-Whisper releases, distil-large-v3 is specifically designed to be compatible
with the OpenAI Whisper long-form transcription algorithm. In our benchmark over 4 out-of-distribution datasets, distil-large-v3
outperformed distil-large-v2 by 5% WER average. Thus, you can expect significant performance gains by switching to this 
latest checkpoint.

## Usage

Distil-Whisper can be run with the [Whisper.cpp](https://github.com/ggerganov/whisper.cpp) package with the original 
sequential long-form transcription algorithm. In a provisional benchmark on Mac M1, distil-large-v3 is over 5x faster 
than Whisper large-v3, while performing to within 0.8% WER over long-form audio.

Steps for getting started:

1. Clone the Whisper.cpp repository:
```
git clone https://github.com/ggerganov/whisper.cpp.git
cd whisper.cpp
```
2. Install the Hugging Face Hub Python package:
```bash
pip install --upgrade huggingface_hub
```
And download the GGML weights for distil-large-v3 using the following Python snippet:

```python
from huggingface_hub import hf_hub_download

hf_hub_download(repo_id='distil-whisper/distil-large-v3-ggml', filename='ggml-distil-large-v3.bin', local_dir='./models')
```

Note that if you do not have a Python environment set-up, you can also download the weights directly with `wget`:

```bash
wget https://huggingface.co/distil-whisper/distil-large-v3-ggml/resolve/main/ggml-distil-large-v3.bin -P ./models
```

3. Run inference using the provided sample audio:

```bash
make -j && ./main -m models/ggml-distil-large-v3.bin -f samples/jfk.wav
```

## Model Details

For more information about the distil-large-v3 model, refer to the original [model card](https://huggingface.co/distil-whisper/distil-large-v3).

## License

Distil-Whisper inherits the [MIT license](https://github.com/huggingface/distil-whisper/blob/main/LICENSE) from OpenAI's Whisper model.

## Citation

If you use this model, please consider citing the [Distil-Whisper paper](https://arxiv.org/abs/2311.00430):
```
@misc{gandhi2023distilwhisper,
      title={Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling}, 
      author={Sanchit Gandhi and Patrick von Platen and Alexander M. Rush},
      year={2023},
      eprint={2311.00430},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
```