moonshine base O N N X

Introduction

The Moonshine Base ONNX model, developed by the ONNX Community, is designed for automatic speech recognition tasks. It uses the Transformers.js library for deployment, making it suitable for JavaScript environments.

Architecture

The model is based on the UsefulSensors/moonshine-base architecture and is compatible with the ONNX format. It is integrated with the Transformers.js library, enabling efficient deployment in web environments.

Training

Details about the training process are not explicitly provided in the documentation. However, it utilizes the robust capabilities of the UsefulSensors/moonshine-base model for automatic speech recognition.

Guide: Running Locally

1. Install Transformers.js:
   Ensure you have Node.js installed. Use npm to install the Transformers.js library:

   npm i @huggingface/transformers
   

2. Use the Model:
   Use the following JavaScript code to perform automatic speech recognition:

   import { pipeline } from "@huggingface/transformers";
   
   const transcriber = await pipeline("automatic-speech-recognition", "onnx-community/moonshine-base-ONNX");
   const output = await transcriber("https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav");
   console.log(output);
   

3. Cloud GPUs:
   Although the model runs in a JavaScript environment, consider using cloud services with GPU support for other heavy tasks.

License

The Moonshine Base ONNX model is released under the MIT License, allowing flexibility for both personal and commercial use.