Distil Large V3.5 ONNX

🚀 Distil-Whisper: Distil-Large-v3.5

Distil-Whisper is a knowledge-distilled version of OpenAI's Whisper-Large-v3, offering high efficiency and better performance, suitable for automatic speech recognition.

Distil-Whisper is the knowledge-distilled version of OpenAI's Whisper-Large-v3, described in the paper Robust Knowledge Distillation via Large-Scale Pseudo Labelling. As the newest addition to the Distil-Whisper English family, Distil-Large-v3.5 maintains the high efficiency of its predecessors while delivering better performance.

Compared to earlier models, Distil-Large-v3.5 has been trained on over 4× more diverse public data (98k hours) and uses a "patient" teacher with an extended training schedule and aggressive data augmentation (SpecAugment) during distillation. This results in enhanced robustness and accuracy compared to previous Distil-Whisper models, making it suitable as a drop-in replacement.

Why consider Distil-Large-v3.5 when Whisper-Large-v3-Turbo already exists?

1. It offers a different balance between accuracy and efficiency, remains ~1.5x faster than Whisper-Large-v3-Turbo while performing slightly better on short-form transcription and falling ~1% behind on long-form transcription.
2. It works perfectly as a draft model for speculative decoding with Whisper-Large-v3. By keeping the encoder frozen during training, we need to load just two extra decoder layers and forward the encoder only once. This achieves ~2x faster inference compared to Whisper-Large-v3 while maintaining identical outputs.

This model is a 🤗 collaborative effort between Bofeng Huang, Eustache Le Bihan, Steven Zheng, Vaibhav Srivastav, and Joshua Lochner.

🚀 Quick Start

Distil-Whisper Distil-Large-v3.5 is a powerful model for automatic speech recognition. You can quickly start using it through the following steps.

📦 Installation

If you haven't already, you can install the Transformers.js JavaScript library from NPM using:

npm i @huggingface/transformers

💻 Usage Examples

Basic Usage

You can then transcribe audio as follows:

import { pipeline } from '@huggingface/transformers';

const transcriber = await pipeline('automatic-speech-recognition', 'distil-whisper/distil-large-v3.5-ONNX');

const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav';
const output = await transcriber(url);
// { text: "And so, my fellow Americans, ask not what your country can do for you. Ask what you can do for your country." }

📄 License

This project is licensed under the MIT license.