The model is now added to WebAI.js. Run it in your browser with no code required.

#3
by AxolsWebAI - opened

Hi there,

We've packaged this model inside our open-source library WebAI.js, letting you run it directly in the browser with just a few lines of code—no backend hosting required:

import { WebAI } from '@axols/webai-js';

const webai = await WebAI.create({
  modelId: "whisper-base",
  dev: true
});

await webai.init({
  mode: "webai",
  precision: "q8",
  device: "wasm",
});

const generation = await webai.generate({
  userInput: {
    audio_blob_url: "blob:https://www.webai-js.com/c2c25b40-2fc5-4bce-a540-099098ee0906"
  },
  modelConfig: {
    language: "en",
    return_timestamps: true,
    condition_on_prev_tokens: true
  },
  generateConfig: {
    chunk_length_s: 30
  }
});

🔬 Try Whisper-Base Instantly (No Code Required)

You can benchmark and test the model directly here:
https://www.webai-js.com/models/whisper-base/playground

image


📘 Full API Reference

Detailed parameter explanations can be found here:
https://www.webai-js.com/models/whisper-base/api-reference/v1/class-api/methods/webai-generate

image


🧡 Fully Open Source

WebAI.js is completely open source and free to use.
Star or contribute on GitHub:
https://github.com/axolsai/webai-js

Thanks

Sign up or log in to comment