docs/Whisper/WhisperAPI.md

# API Documentation for `Lenylvt/Whisper-API`
This documentation outlines how to use the Whisper API through Python and JavaScript.

## API Endpoint

The API can be accessed using the `gradio_client` Python library [docs](https://www.gradio.app/guides/getting-started-with-the-python-client) or the `@gradio/client` JavaScript package [docs](https://www.gradio.app/guides/getting-started-with-the-js-client).

## Python Usage

### Step 1: Installation

To begin, ensure the `gradio_client` library is installed.

```python
pip install gradio_client
```

### Step 2: Making a Request

Identify the API endpoint for the function you wish to utilize. Replace the placeholders in the following code snippet with your actual input data. If accessing a private Space, you may need to include your Hugging Face token.

**API Name**: `/predict`

```python
from gradio_client import Client

client = Client("Lenylvt/Whisper-API")
result = client.predict(
    "https://github.com/gradio-app/gradio/raw/main/test/test_files/audio_sample.wav",  # filepath in 'Upload Audio' Audio component
    "base",  # Model size in 'Model Size' Dropdown component (e.g., 'base', 'small', 'medium', 'large', 'large-v2', 'large-v3')
    api_name="/predict"
)
print(result)
```

**Return Type(s):**

- A `str` representing the output in the 'output' Textbox component.

## JavaScript Usage

### Step 1: Installation

For JavaScript usage, make sure the `@gradio/client` package is included in your project.

```bash
npm i -D @gradio/client
```

### Step 2: Making a Request

Similar to Python, locate the API endpoint that fits your requirements. Replace the placeholder values with your own data. Include your Hugging Face token if you are accessing a private Space.

**API Name**: `/predict`

```javascript
import { client } from "@gradio/client";
const response_0 = await fetch("https://github.com/gradio-app/gradio/raw/main/test/test_files/audio_sample.wav");
const exampleAudio = await response_0.blob();
                        
const app = await client("Lenylvt/Whisper-API");
const result = await app.predict("/predict", [
    exampleAudio,  // blob in 'Upload Audio' Audio component        
    "base",        // string in 'Model Size' Dropdown component
]);

console.log(result.data);
```

**Return Type(s):**

- A `string` representing the output in the 'output' Textbox component.