You can deploy this model and start earning money today!

distil-whisper/
distil-large-v3.5-openai

Name: distil-large-v3.5-openai
Availability: InStock

audio

automatic-speech-recognition

2311.00430

mit

Views

No views yet

Distil-Whisper: Distil-Large-v3.5 for OpenAI Whisper

This repository contains the model weights for distil-large-v3.5 converted to OpenAI Whisper format.

Python Usage

To use the model in the original Whisper format, first ensure you have the openai-whisper package installed.

For this example, we'll also install 🤗 Datasets to load a toy audio dataset from the Hugging Face Hub:

bash

pip install --upgrade pip
pip install --upgrade openai-whisper datasets[audio]

The following code-snippet demonstrates how to transcribe a sample file from the LibriSpeech dataset loaded using 🤗 Datasets:

python

from datasets import load_dataset
from huggingface_hub import hf_hub_download
import whisper

model_path = hf_hub_download(repo_id="distil-whisper/distil-large-v3.5-openai", filename="model.bin")
model = whisper.load_model(model_path)

dataset = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
sample = dataset[0]["audio"]["path"]

result = model.transcribe(sample, language="en")
print(result["text"])

Note that the model weights will be downloaded and saved to your cache the first time you run the example. Subsequently, you can re-use the same example, and the weights will be loaded directly from your cache without having to download them again.

To transcribe a local audio file, simply pass the path to the audio file as the audio argument to transcribe:

python

result = model.transcribe(model, audio="audio.mp3", language="en")
print(result["text"])

CLI Usage

The Distil-Whisper model can also be used with the OpenAI Whisper CLI. First, pip install the Hugging Face Hub package:

pip install --upgrade huggingface_hub

Next, download the weights for distil-large-v3 locally:

huggingface-cli download distil-whisper/distil-large-v3.5-openai model.bin --local-dir distil-large-v3.5

Finally, use the OpenAI Whisper CLI to transcribe:

whisper audio.mp3 --model distil-large-v3.5/model.bin --language en

Model Details

For more information about the Distil-Large-v3.5 model, refer to the original model card.

License

Distil-Whisper inherits the MIT license from OpenAI's Whisper model.

Citation

If you use this model, please consider citing the Distil-Whisper paper:

@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}
}